We introduce ProcWORLD, a large-scale benchmark for partially observable embodied spatial reasoning and long-term planning with large language models (LLM) and vision language models (VLM).ProcWORLD features a wide range of challenging embodied navigation and object manipulation tasks, covering 16 task types, 5,000 rooms, and over 10 million evaluation trajectories with diverse data distribution.ProcWORLD supports configurable observation modes, ranging from text-only descriptions to vision-only observations.It enables text-based actions to control the agent following language instructions.ProcWORLD has presented significant challenges for LLMs and VLMs: (1) active information gathering given partial observations for disambiguation; (2) simultaneous localization and decision-making by tracking the spatio-temporal state-action distribution; (3) constrained reasoning with dynamic states subject to physical reachability.Our extensive evaluation of 15 foundation models and 5 reasoning algorithms (with over 1 million rollouts) indicates larger models perform better.However, ProcWORLD remains highly challenging for existing state-of-the-art models and in-context learning methods due to constrained reachability and the need of combinatorial spatial reasoning.

World models allow autonomous agents to plan and explore by predicting the visual outcomes of different actions. However, for robot manipulation, it is challenging to accurately model the fine-grained robot-object interaction within the visual space using existing methods which overlooks precise alignment between each action and the corresponding frame. In this paper, we present IRASim, a novel world model capable of generating videos with fine-grained robotobject interaction details, conditioned on historical observations and robot action trajectories. We train a diffusion transformer and introduce a novel frame-level actionconditioning module within each transformer block to explicitly model and strengthen the action-frame alignment. Extensive experiments show that: (1) the quality of the videos generated by our method surpasses all the baseline methods and scales effectively with increased model size and computation; (2) policy evaluations using IRASim exhibit a strong correlation with those using the ground-truth simulator, highlighting its potential to accelerate real-world policy evaluation; (3) testing-time scaling through model-based planning with IRASim significantly enhances policy performance, as evidenced by an improvement in the IoU metric on the Push-T benchmark from 0.637 to 0.961; (4) IRASim provides flexible action controllability, allowing virtual robotic arms in datasets to be controlled via a keyboard or VR controller. Video and code are available at https://gen-irasim.github.io/.

Legged locomotion over various terrains is challenging and requires precise perception of the robot and its surroundings from both proprioception and vision. However, learning directly from high-dimensional visual input is often data-inefficient and intricate. To address this issue, traditional methods attempt to learn a teacher policy with access to privileged information first and then learn a student policy to imitate the teacher's behavior with visual input. Despite some progress, this imitation framework prevents the student policy from achieving optimal performance due to the information gap between inputs. Furthermore, the learning process is unnatural since animals intuitively learn to traverse different terrains based on their understanding of the world without privileged knowledge. Inspired by this natural ability, we propose a simple yet effective method, World Model-based Perception (WMP), which builds a world model of the environment and learns a policy based on the world model. We illustrate that though completely trained in simulation, the world model can make accurate predictions of real-world trajectories, thus providing informative signals for the policy controller. Extensive simulated and real-world experiments demonstrate that WMP outperforms state-of-the-art baselines in traversability and robustness. Videos and Code are available at: https://wmp-loco.github.io/.

Recently, leveraging pre-trained vision-language models (VLMs) for building vision-language-action (VLA) models has emerged as a promising approach to effective robot manipulation learning. However, only few methods incorporate 3D signals into VLMs for action prediction, and they do not fully leverage the spatial structure inherent in 3D data, leading to low data efficiency. In this paper, we introduce a new paradigm for constructing 3D VLAs. Specifically, we first pre-train the VLM backbone to take 2D images as input and produce 2D heatmaps as output. Using this pre-trained VLM as the backbone, we then fine-tune the entire VLA model while maintaining alignment between inputs and outputs by: (1) projecting raw point cloud inputs into multi-view images, and (2) predicting heatmaps before generating the final action. Extensive experiments show that the resulting model, BridgeVLA, can learn 3D manipulation both efficiently and effectively. BridgeVLA outperforms state-of-the-art baselines across three simulation benchmarks. In RLBench, it improves the average success rate from 81.4\% to 88.2\%. In COLOSSEUM, it demonstrates significantly better performance in challenging generalization settings, boosting the average success rate from 56.7\% to 64.0\%. In GemBench, it surpasses all the comparing baseline methods in terms of average success rate. In real-robot experiments, BridgeVLA outperforms a state-of-the-art baseline method by 32\% on average. It generalizes robustly in multiple out-of-distribution settings, including visual disturbances and unseen instructions. Remarkably, it is able to achieve a success rate of 95.4\% on 10+ tasks with only 3 trajectories per task, while other VLA methods such as $\pi_{0}$ fail completely. Project Website: https://bridgevla.github.io/.

We present $\textbf{FlowRL}$, a novel framework for online reinforcement learning that integrates flow-based policy representation with Wasserstein-2-regularized optimization. We argue that in addition to training signals, enhancing the expressiveness of the policy class is crucial for the performance gains in RL. Flow-based generative models offer such potential, excelling at capturing complex, multimodal action distributions. However, their direct application in online RL is challenging due to a fundamental objective mismatch: standard flow training optimizes for static data imitation, while RL requires value-based policy optimization through a dynamic buffer, leading to difficult optimization landscapes. FlowRL first models policies via a state-dependent velocity field, generating actions through deterministic ODE integration from noise. We derive a constrained policy search objective that jointly maximizes Q through the flow polciy while bounding the Wasserstein-2 distance to a behavior-optimal policy implicitly derived from the replay buffer. This formulation effectively aligns the flow optimization with the RL objective, enabling efficient and value-aware policy learning despite the complexity of the policy class. Empirical evaluations on DMControl and Humanoidbench demonstrate that FlowRL achieves competitive performance in online reinforcement learning benchmarks.

Establishing a reliable and iteratively refined robotic system is essential for deploying real-world applications. While Vision-Language-Action (VLA) models are widely recognized as the foundation model for such robotic deployment, their reliance on offline expert demonstrations critically limits their capacity for post-deployment refinement. To mitigate this limitation, we introduce Action Preference Optimization (APO), a method designed to refine VLA models by human-assisted preference alignment gathered through interaction with environments. This method begins with a human-robot collaboration framework for reliable failure correction and interaction trajectory collection through human intervention. However, directly leveraging these interaction trajectories for preference optimization is non-trivial due to the challenges of irreversible robotic actions and token distribution mismatch. To solve this, APO proposes an adaptive reweighting algorithm with binary desirability signals derived from interaction, empowering VLA models effectively suppress failure-prone actions while enhancing corrective action adaptation. Ultimately, APO equips VLA models with the crucial capability to learn from failure, paving the way for their iterative refinement and reliable deployment in dynamic environments. The experiments conducted in simulation and real-world scenarios prove superior generalization and robustness of our human-assisted framework across a variety of manipulation tasks. We believe this work could bring insights for efficient and stable optimization of VLA models through human-robot collaboration. The code and dataset are released at https://github.com/GeWu-Lab/Action-Preference-Optimization.

We present Chain-of-Action (CoA), a novel visuomotor policy paradigm built upon Trajectory Autoregressive Modeling. Unlike conventional approaches that predict next step action(s) forward, CoA generates an entire trajectory by explicit backward reasoning with task-specific goals through an action-level Chain-of-Thought (CoT) process. This process is unified within a single autoregressive structure: (1) the first token corresponds to a stable keyframe action that encodes the task-specific goals; and (2) subsequent action tokens are generated autoregressively, conditioned on the initial keyframe and previously predicted actions. This backward action reasoning enforces a global-to-local structure, allowing each local action to be tightly constrained by the final goal. To further realize the action reasoning structure, CoA incorporates four complementary designs: continuous action token representation; dynamic stopping for variable-length trajectory generation; reverse temporal ensemble; and multi-token prediction to balance action chunk modeling with global structure. As a result, CoA gives strong spatial generalization capabilities while preserving the flexibility and simplicity of a visuomotor policy. Empirically, we observe that CoA outperforms representative imitation learning algorithms such as ACT and Diffusion Policy across 60 RLBench tasks and 8 real-world tasks.

Due to the increasing demand for extreme-scale time-series data workloads in data centers, it is required to build a high-performance semantic caching system that leverages the semantics and results of historical queries to answer time-series queries. Existing caching solutions either ignore the semantics of queries, offering suboptimal performance, or focus only on specific scenarios, providing small-capacity, limited functionality. In this paper, we summarize the query patterns of time-series data workload and propose the definition of semantic time-series caching for the first time. Accordingly, we present a semantic time-series caching system, STsCache, based on a hybrid storage model with memory and NVMe SSD. We propose a series of optimized strategies, such as slab-based semantic data management, semantic index, semantic value-driven batch eviction, time-aware deduplication insertion, and lazy compaction. We implemented and evaluated STsCache via benchmarks and production environments. STsCache can increase throughput of popular time-series databases (InfluxDB, TimescaleDB) by 4.8–10.8X and reduce latency by 79.9%-93.5%. Compared with the latest time-series caching schemes (TSCache, BSCache), STsCache can increase throughput by 1.5–4.5X, reduce latency by 59.4%-81.9%, and increase hit ratios by 22.5%-82.4%.

Recent progress in vision language foundation models has shown their ability to understand multimodal data and resolve complicated vision language tasks, including robotics manipulation. We seek a straightforward way of making use of existing vision-language models (VLMs) with simple fine-tuning on robotics data. To this end, we derive a simple and novel vision-language manipulation framework, dubbed RoboFlamingo, built upon the open-source VLMs, OpenFlamingo. Unlike prior works, RoboFlamingo utilizes pre-trained VLMs for single-step vision-language comprehension, models sequential history information with an explicit policy head, and is slightly fine-tuned by imitation learning only on language-conditioned manipulation datasets. Such a decomposition provides RoboFlamingo the flexibility for open-loop control and deployment on low-performance platforms. By exceeding the state-of-the-art performance with a large margin on the tested benchmark, we show RoboFlamingo can be an effective and competitive alternative to adapt VLMs to robot control. Our extensive experimental results also reveal several interesting conclusions regarding the behavior of different pre-trained VLMs on manipulation tasks. We believe RoboFlamingo has the potential to be a cost-effective and easy-to-use solution for robotics manipulation, empowering everyone with the ability to fine-tune their own robotics policy. Our code will be made public upon acceptance.

Masked autoencoders have become popular training paradigms for self-supervised visual representation learning. These models randomly mask a portion of the input and reconstruct the masked portion according to assigned target representations. In this paper, we show that a careful choice of the target representation is unnecessary for learning good visual representation since different targets tend to derive similarly behaved models. Driven by this observation, we propose a multi-stage masked distillation pipeline and use a randomly initialized model as the teacher, enabling us to effectively train high-capacity models without any effort to carefully design the target representation. On various downstream tasks, the proposed method to perform masked knowledge distillation with bootstrapped teachers (dbot) outperforms previous self-supervised methods by nontrivial margins. We hope our findings, as well as the proposed method, could motivate people to rethink the roles of target representations in pre-training masked autoencoders.

Generative pre-trained models have demonstrated remarkable effectiveness in language and vision domains by learning useful representations. In this paper, we extend the scope of this effectiveness by showing that visual robot manipulation can significantly benefit from large-scale video generative pre-training. We introduce GR-1, a GPT-style model designed for multi-task language-conditioned visual robot manipulation. GR-1 takes as inputs a language instruction, a sequence of observation images, and a sequence of robot states. It predicts robot actions as well as future images in an end-to-end manner. Thanks to a flexible design, GR-1 can be seamlessly finetuned on robot data after pre-trained on a large-scale video dataset. We perform extensive experiments on the challenging CALVIN benchmark and a real robot. On CALVIN benchmark, our method outperforms state-of-the-art baseline methods and improves the success rate from 88.9% to 94.9%. In the setting of zero-shot unseen scene generalization, GR-1 improves the success rate from 53.3% to 85.4%. In real robot experiments, GR-1 also outperforms baseline methods and shows strong potentials in generalization to unseen scenes and objects. We provide inaugural evidence that a unified GPT-style transformer, augmented with large-scale video generative pre-training, exhibits remarkable generalization to multi-task visual robot manipulation. Project page: https://GR1-Manipulation.github.io

Interactive visual grounding in Human-Robot Interaction (HRI) is challenging yet practical due to the inevitable ambiguity in natural languages. It requires robots to disambiguate the user’s input by active information gathering. Previous approaches often rely on predefined templates to ask disambiguation questions, resulting in performance reduction in realistic interactive scenarios. In this paper, we propose TiO, an end-to-end system for interactive visual grounding in human-robot interaction. Benefiting from a unified formulation of visual dialog and grounding, our method can be trained on a joint of extensive public data, and show superior generality to diversified and challenging open-world scenarios. In the experiments, we validate TiO on GuessWhat?! and InViG benchmarks, setting new state-of-the-art performance by a clear margin. Moreover, we conduct HRI experiments on the carefully selected 150 challenging scenes as well as real-robot platforms. Results show that our method demonstrates superior generality to diversified visual and language inputs with a high success rate. Codes and demos are available on https://jxu124.github.io/TiO/.

Yan Zeng, Hanbo Zhang, Jiani Zheng, Jiangnan Xia, Guoqiang Wei, Yang Wei, Yuchen Zhang, Tao Kong, Ruihua Song. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

We are witnessing significant progress on perception models, specifically those trained on large-scale internet images. However, efficiently generalizing these perception models to unseen embodied tasks is insufficiently studied, which will help various relevant applications (e.g., home robots). Unlike static perception methods trained on pre-collected images, the embodied agent can move around in the environment and obtain images of objects from any viewpoints. Therefore, efficiently learning the exploration policy and collection method to gather informative training samples is the key to this task. To do this, we first build a 3D semantic distribution map to train the exploration policy self-supervised by introducing the semantic distribution disagreement and the semantic distribution uncertainty rewards. Note that the map is generated from multi-view observations and can weaken the impact of misidentification from an unfamiliar viewpoint. Our agent is then encouraged to explore the objects with different semantic distributions across viewpoints, or uncertain semantic distributions. With the explored informative trajectories, we propose to select hard samples on trajectories based on the semantic distribution uncertainty to reduce unnecessary observations that can be correctly identified. Experiments show that the perception model fine-tuned with our method outperforms the baselines trained with other exploration policies. Further, we demonstrate the robustness of our method in real-robot experiments.

Language-based communications are essential in human-robot interaction, especially for the majority of non-expert users. In this paper, we present SeeAsk, an open-world interactive visual grounding system to grasp specified targets with ambiguous natural language instructions. The main contribution of SeeAsk is that it can robustly handle open-world scenes in terms of both open-set objects and open-vocabulary interactions. Specifically, our SeeAsk is built upon modern large-scale vision-language pre-trained models and traditional decision-making process, and shows promising results to be deployed in real-world scenarios. SeeAsk outperforms previous state-of-the-art algorithms with a clear margin in terms of not only success rate but also asking smarter and more informative questions. User studies also demonstrate its advantages over previous works.

Visual pre-training with large-scale real-world data has made great progress in recent years, showing great potential in robot learning with pixel observations. However, the recipes of visual pre-training for robot manipulation tasks are yet to be built. In this paper, we thoroughly investigate the effects of visual pre-training strategies on robot manipulation tasks from three fundamental perspectives: pre-training datasets, model architectures and training methods. Several significant experimental findings are provided that are beneficial for robot learning. Further, we propose a visual pre-training scheme for robot manipulation termed Vi-PRoM, which combines self-supervised learning and supervised learning. Concretely, the former employs contrastive learning to acquire underlying patterns from large-scale unlabeled data, while the latter aims learning visual semantics and temporal dynamics. Extensive experiments on robot manipulations in various simulation environments and the real robot demonstrate the superiority of the proposed scheme. Videos and more details can be found on https://explore-pretrain-robot.github.io.

In this paper, we present a novel method for mobile manipulators to perform multiple contact-rich manipulation tasks. While learning-based methods have the potential to generate actions in an end-to-end manner, they often suffer from insufficient action accuracy and robustness against noise. On the other hand, classical control-based methods can enhance system robustness, but at the cost of extensive parameter tuning. To address these challenges, we present MOMA-Force, a visual-force imitation method that seamlessly combines representation learning for perception, imitation learning for complex motion generation, and admittance whole-body control for system robustness and controllability. MOMA-Force enables a mobile manipulator to learn multiple complex contact-rich tasks with high success rates and small contact forces. In a real household setting, our method outperforms baseline methods in terms of task success rates. Moreover, our method achieves smaller contact forces and smaller force variances compared to baseline methods without force imitation. Overall, we offer a promising approach for efficient and robust mobile manipulation in the real world. Videos and more details can be found on https://visual-force-imitation.github.io.

Data augmentation is a critical technique in object detection, especially the augmentations targeting at scale invariance training (scale-aware augmentation). However, there has been little systematic investigation of how to design scale-aware data augmentation for object detection. We propose Scale-aware AutoAug to learn data augmentation policies for object detection. We define a new scale-aware search space, where both image- and instance-level augmentations are designed for maintaining scale robust feature learning. Upon this search space, we propose a new search metric, termed Pareto Scale Balance, to facilitate efficient augmentation policy search. In experiments, Scale-aware AutoAug yields significant and consistent improvement on various object detectors (e.g., RetinaNet, Faster R-CNN, Mask R-CNN, and FCOS), even compared with strong multi-scale training baselines. Our searched augmentation policies are generalized well to other datasets and instance-level tasks beyond object detection, e.g., instance segmentation. The search cost is much less than previous automated augmentation approaches for object detection, i.e., 8 GPUs across 2.5 days versus. 800 TPU-days. In addition, meaningful patterns can be summarized from our searched policies, which intuitively provide valuable knowledge for hand-crafted data augmentation design. Based on the searched scale-aware augmentation policies, we further introduce a dynamic training paradigm to adaptively determine specific augmentation policy usage during training. The dynamic paradigm consists of an heuristic manner for image-level augmentations and a differentiable copy-paste-based method for instance-level augmentations. The dynamic paradigm achieves further performance improvements to Scale-aware AutoAug without any additional burden on the long tailed LVIS benchmarks. We also demonstrate its ability to prevent over-fitting for large models, e.g., the Swin Transformer large model. Code and models are available at https://github.com/dvlab-research/SA-AutoAug.

Object detection serves as one of most fundamental computer vision tasks. Existing works on object detection heavily rely on dense object candidates, such as k anchor boxes pre-defined on all grids of an image feature map of size H×W. In this paper, we present Sparse R-CNN, a very simple and sparse method for object detection in images. In our method, a fixed sparse set of learned object proposals ( N in total) are provided to the object recognition head to perform classification and localization. By replacing HWk (up to hundreds of thousands) hand-designed object candidates with N (e.g., 100) learnable proposals, Sparse R-CNN makes all efforts related to object candidates design and one-to-many label assignment completely obsolete. More importantly, Sparse R-CNN directly outputs predictions without the non-maximum suppression (NMS) post-processing procedure. Thus, it establishes an end-to-end object detection framework. Sparse R-CNN demonstrates highly competitive accuracy, run-time and training convergence performance with the well-established detector baselines on the challenging COCO dataset and CrowdHuman dataset. We hope that our work can inspire re-thinking the convention of dense prior in object detectors and designing new high-performance detectors.

We present Twist, a simple and theoretically explainable self-supervised representation learning method by classifying large-scale unlabeled datasets in an end-to-end way. We employ a siamese network terminated by a softmax operation to produce twin class distributions of two augmented images. Without supervision, we enforce the class distributions of different augmentations to be consistent. However, simply minimizing the divergence between augmentations will generate collapsed solutions, i.e., outputting the same class distribution for all images. In this case, little information about the input images is preserved. To solve this problem, we propose to maximize the mutual information between the input image and the output class predictions. Specifically, we minimize the entropy of the distribution for each sample to make the class prediction assertive, and maximize the entropy of the mean distribution to make the predictions of different samples diverse. In this way, Twist can naturally avoid the collapsed solutions without specific designs such as asymmetric network, stop-gradient operation, or momentum encoder. As a result, Twist outperforms previous state-of-the-art methods on a wide range of tasks. Specifically on the semi-supervised classification task, Twist achieves 61.2% top-1 accuracy with 1% ImageNet labels using a ResNet-50 as backbone, surpassing previous best results by an improvement of 6.2%. Codes and pre-trained models are available at https://github.com/bytedance/TWIST.

Self-supervised learning aims to learn a universal feature representation without labels. To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and pixel-level prediction. To fill this gap, we aim to design an effective, dense self-supervised learning framework that directly works at the level of pixels (or local features) by taking into account the correspondence between local features. Specifically, we present dense contrastive learning (DenseCL), which implements self-supervised learning by optimizing a pairwise contrastive (dis)similarity loss at the pixel level between two views of input images. Compared to the supervised ImageNet pre-training and other self-supervised learning methods, our self-supervised DenseCL pre-training demonstrates consistently superior performance when transferring to downstream dense prediction tasks including object detection, semantic segmentation and instance segmentation. Specifically, our approach significantly outperforms the strong MoCo-v2 by 2.0% AP on PASCAL VOC object detection, 1.1% AP on COCO object detection, 0.9% AP on COCO instance segmentation, 3.0% mIoU on PASCAL VOC semantic segmentation and 1.8% mIoU on Cityscapes semantic segmentation. The improvements are up to 3.5% AP and 8.8% mIoU over MoCo-v2, and 6.1% AP and 6.1% mIoU over supervised counterpart with frozen-backbone evaluation protocol. Code and models are available at: https://git.io/DenseCL

Reference Expression Generation (REG) and Comprehension (REC) are two highly correlated tasks. Modeling REG and REC simultaneously for utilizing the relation between them is a promising way to improve both. However, the problem of distinct inputs, as well as building connections between them in a single model, brings challenges to the design and training of the joint model. To address the problems, we propose a unified model for REG and REC, named UniRef. It unifies these two tasks with the carefully-designed Image-Region-Text Fusion layer (IRTF), which fuses the image, region and text via the image cross-attention and region cross-attention. Additionally, IRTF could generate pseudo input regions for the REC task to enable a uniform way for sharing the identical representation space across the REC and REG. We further propose Vision-conditioned Masked Language Modeling (VMLM) and Text-Conditioned Region Prediction (TRP) to pre-train UniRef model on multi-granular corpora. The VMLM and TRP are directly related to REG and REC, respectively, but could help each other. We conduct extensive experiments on three benchmark datasets, RefCOCO, RefCOCO+ and RefCOCOg. Experimental results show that our model outperforms previous state-of-the-art methods on both REG and REC.

Can a robot autonomously learn to design and construct a bridge from varying-sized blocks without a blueprint? It is a challenging task with long horizon and sparse reward - the robot has to figure out physically stable design schemes and feasible actions to manipulate and transport blocks. Due to diverse block sizes, the state space and action trajectories are vast to explore. In this paper, we propose a hierarchical approach for this problem. It consists of a reinforcement-learning designer to propose high-level building instructions and a motion-planning-based action generator to manipulate blocks at the low level. For high-level learning, we develop a novel technique, prioritized memory resetting (PMR) to improve exploration. PMR adaptively resets the state to those most critical configurations from a replay buffer so that the robot can resume training on partial architectures instead of from scratch. Furthermore, we augment PMR with auxiliary training objectives and fine-tune the designer with the locomotion generator. Our experiments in simulation and on a real deployed robotic system demonstrate that it is able to effectively construct bridges with blocks of varying sizes at a high success rate. Demos can be found at https://sites.google.com/view/bridge-pmr.

Object Goal Navigation (ObjectNav) task is to navigate an agent to an object category in unseen environments without a pre-built map. In this paper, we solve this task by predicting the distance to the target using semantically-related objects as cues. Based on the estimated distance to the target object, our method directly choose optimal midterm goals that are more likely to have a shorter path to the target. Specifically, based on the learned knowledge, our model takes a bird's-eye view semantic map as input, and estimates the path length from the frontier map cells to the target object. With the estimated distance map, the agent could simultaneously explore the environment and navigate to the target objects based on a simple human-designed strategy. Empirical results in visually realistic simulation environments show that the proposed method outperforms a wide range of baselines on success rate and efficiency. Real-robot experiment also demonstrates that our method generalizes well to the real world.

Compared to many other dense prediction tasks, e.g., semantic segmentation, it is the arbitrary number of instances that has made instance segmentation much more challenging. In order to predict a mask for each instance, mainstream approaches either follow the "detect-then-segment" strategy (e.g., Mask R-CNN), or predict embedding vectors first then cluster pixels into individual instances. In this paper, we view the task of instance segmentation from a completely new perspective by introducing the notion of "instance categories", which assigns categories to each pixel within an instance according to the instance's location. With this notion, we propose segmenting objects by locations (SOLO), a simple, direct, and fast framework for instance segmentation with strong performance. We derive a few SOLO variants (e.g., Vanilla SOLO, Decoupled SOLO, Dynamic SOLO) following the basic principle. Our method directly maps a raw input image to the desired object categories and instance masks, eliminating the need for the grouping post-processing or the bounding box detection. Our approach achieves state-of-the-art results for instance segmentation in terms of both speed and accuracy, while being considerably simpler than the existing methods. Besides instance segmentation, our method yields state-of-the-art results in object detection (from our mask byproduct) and panoptic segmentation. We further demonstrate the flexibility and high-quality segmentation of SOLO by extending it to perform one-stage instance-level image matting. Code is available at: https://git.io/AdelaiDet.

We propose Scale-aware AutoAug to learn data augmentation policies for object detection. We define a new scaleaware search space, where both image- and box-level augmentations are designed for maintaining scale invariance. Upon this search space, we propose a new search metric, termed Pareto Scale Balance, to facilitate search with high efficiency. In experiments, Scale-aware AutoAug yields significant and consistent improvement on various object detectors (e.g., RetinaNet, Faster R-CNN, Mask R-CNN, and FCOS), even compared with strong multi-scale training baselines. Our searched augmentation policies are transferable to other datasets and box-level tasks beyond object detection (e.g., instance segmentation and keypoint estimation) to improve performance. The search cost is much less than previous automated augmentation approaches for object detection. It is notable that our searched policies have meaningful patterns, which intuitively provide valuable insight for human data augmentation design. Code and models are available at https://github.com/Jia-ResearchLab/SA-AutoAug.

Referring image segmentation aims to segment the objects referred by a natural language expression. Previous methods usually focus on designing an implicit and recurrent feature interaction mechanism to fuse the visual-linguistic features to directly generate the final segmentation mask without explicitly modeling the localization information of the referent instances. To tackle these problems, we view this task from another perspective by decoupling it into a "Locate-Then-Segment" (LTS) scheme. Given a language expression, people generally first perform attention to the corresponding target image regions, then generate a fine segmentation mask about the object based on its context. The LTS first extracts and fuses both visual and textual features to get a cross-modal representation, then applies a cross-model interaction on the visual-textual features to locate the referred object with position prior, and finally generates the segmentation result with a light-weight segmentation network. Our LTS is simple but surprisingly effective. On three popular benchmark datasets, the LTS outperforms all the previous state-of-the-arts methods by a large margin (e.g., +3.2% on RefCOCO+ and +3.4% on RefCOCOg). In addition, our model is more interpretable with explicitly locating the object, which is also proved by visualization experiments. We believe this framework is promising to serve as a strong baseline for referring image segmentation.

We present Sparse R-CNN, a purely sparse method for object detection in images. Existing works on object detection heavily rely on dense object candidates, such as k anchor boxes pre-defined on all grids of image feature map of size H × W. In our method, however, a fixed sparse set of learned object proposals, total length of N, are provided to object recognition head to perform classification and location. By eliminating HWk (up to hundreds of thousands) hand-designed object candidates to N (e.g. 100) learnable proposals, Sparse R-CNN completely avoids all efforts related to object candidates design and many-to-one label assignment. More importantly, final predictions are directly output without non-maximum suppression post-procedure. Sparse R-CNN demonstrates accuracy, run-time and training convergence performance on par with the well-established detector baselines on the challenging COCO dataset, e.g., achieving 45.0 AP in standard 3× training schedule and running at 22 fps using ResNet-50 FPN model. We hope our work could inspire re-thinking the convention of dense prior in object detectors. The code is available at: https://github.com/PeizeSun/SparseR-CNN.

To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and pixel-level prediction. To fill this gap, we aim to design an effective, dense self-supervised learning method that directly works at the level of pixels (or local features) by taking into account the correspondence between local features. We present dense contrastive learning (DenseCL), which implements self-supervised learning by optimizing a pairwise contrastive (dis)similarity loss at the pixel level between two views of input images.Compared to the baseline method MoCo-v2, our method introduces negligible computation overhead (only <1% slower), but demonstrates consistently superior performance when transferring to downstream dense prediction tasks including object detection, semantic segmentation and instance segmentation; and outperforms the state-of-the-art methods by a large margin. Specifically, over the strong MoCo-v2 baseline, our method achieves significant improvements of 2.0% AP on PASCAL VOC object detection, 1.1% AP on COCO object detection, 0.9% AP on COCO instance segmentation, 3.0% mIoU on PASCAL VOC semantic segmentation and 1.8% mIoU on Cityscapes semantic segmentation.Code and models are available at: https://git.io/DenseCL

It has been a challenge to learning skills for an agent from long-horizon unannotated demonstrations. Existing approaches like Hierarchical Imitation Learning(HIL) are prone to compounding errors or suboptimal solutions. In this paper, we propose Option-GAIL, a novel method to learn skills at long horizon. The key idea of Option-GAIL is modeling the task hierarchy by options and train the policy via generative adversarial optimization. In particular, we propose an Expectation-Maximization(EM)-style algorithm: an E-step that samples the options of expert conditioned on the current learned policy, and an M-step that updates the low- and high-level policies of agent simultaneously to minimize the newly proposed option-occupancy measurement between the expert and the agent. We theoretically prove the convergence of the proposed algorithm. Experiments show that Option-GAIL outperforms other counterparts consistently across a variety of tasks.

Grasping in cluttered scenes has always been a great challenge for robots, due to the requirement of the ability to well understand the scene and object information. Previous works usually assume that the geometry information of the objects is available, or utilize a step-wise, multi-stage strategy to predict the feasible 6-DoF grasp poses. In this work, we propose to formalize the 6-DoF grasp pose estimation as a simultaneous multi-task learning problem. In a unified framework, we jointly predict the feasible 6-DoF grasp poses, instance semantic segmentation, and collision information. The whole framework is jointly optimized and end-to-end differentiable. Our model is evaluated on large-scale benchmarks as well as the real robot system. On the public dataset, our method outperforms prior state-of-the-art methods by a large margin (+4.08 AP). We also demonstrate the implementation of our model on a real robotic platform and show that the robot can accurately grasp target objects in cluttered scenarios with a high success rate. Project link: https://openbyterobotics.github.io/sscl.

Autonomous assembly has been a desired functionality of many intelligent robot systems. We study a new challenging assembly task, designing and constructing a bridge without a blueprint. In this task, the robot needs to first design a feasible bridge architecture for arbitrarily wide cliffs and then manipulate the blocks reliably to construct a stable bridge according to the proposed design. In this paper, we propose a bi-level approach to tackle this task. At the high level, the system learns a bridge blueprint policy in a physical simulator using deep reinforcement learning and curriculum learning. A policy is represented as an attention-based neural network with object-centric input, which enables generalization to different number of blocks and cliff widths. For low-level control, we implement a motion-planning-based policy for real-robot motion control, which can be directly combined with a trained blueprint policy for real-world bridge construction without tuning. In our field study, our bi-level robot system demonstrates the capability of manipulating blocks to construct a diverse set of bridges with different architectures.

Monocular depth estimation enables 3D perception from a single 2D image, thus attracting much research attention for years. Almost all methods treat foreground and background regions (“things and stuff”) in an image equally. However, not all pixels are equal. Depth of foreground objects plays a crucial role in 3D object recognition and localization. To date how to boost the depth prediction accuracy of foreground objects is rarely discussed. In this paper, we first analyze the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground and background depth using separate optimization objectives and decoders. Our method significantly improves the depth estimation performance on foreground objects. Applying ForeSeE to 3D object detection, we achieve 7.5 AP gains and set new state-of-the-art results among other monocular methods. Code will be available at: https://github.com/WXinlong/ForeSeE.

Multi-class object detection always involves the tasks of accurate target localization which is mainly related to bounding box regression. Smooth L1 loss is the most popular bounding box regression loss used in the current state-of-the-art object detection systems. However, such loss for regressing the parameters of a bounding box can't accurately and consistently regress the bounding box to the associated ground truth well. We instead propose the near-duplicated loss, a loss that better evaluate the disparity between the bounding box and the ground truth consistently. We present an approximate algorithm associated with a kernel function that not only considers the absolute distance but also involves the relative overlap area between the two bounding boxes. The new loss doesn't need additional supervision and is easy to embed into existing networks. Our final result, by incorporating the near-duplicated loss into the state-of-the-art object detection detectors (Faster RCNN, RetinaNet), shows consistent and significant improvements on popular object detection benchmarks (MS COCO and Pascal VOC).

In this work, we design a simple, direct, and fast framework for instance segmentation with strong performance. To this end, we propose a novel and effective approach, termed SOLOv2, following the principle of the SOLO method [32]. First, our new framework is empowered by an efficient and holistic instance mask representation scheme, which dynamically segments each instance in the image, without resorting to bounding box detection. Specifically, the object mask generation is decoupled into a mask kernel prediction and mask feature learning, which are responsible for generating convolution kernels and the feature maps to be convolved with, respectively. Second, SOLOv2 significantly reduces inference overhead with our novel matrix non-maximum suppression (NMS) technique. Our Matrix NMS performs NMS with parallel matrix operations in one shot, and yields better results. We demonstrate that the proposed SOLOv2 achieves the state-of-the- art performance with high efficiency, making it suitable for both mobile and cloud applications. A light-weight version of SOLOv2 executes at 31.3 FPS and yields 37.1% AP on COCO test-dev. Moreover, our state-of-the-art results in object detection (from our mask byproduct) and panoptic segmentation show the potential of SOLOv2 to serve as a new strong baseline for many instance-level recognition tasks. Code is available at https://git.io/AdelaiDet

We present FoveaBox, an accurate, flexible, and completely anchor-free framework for object detection. While almost all state-of-the-art object detectors utilize predefined anchors to enumerate possible locations, scales and aspect ratios for the search of the objects, their performance and generalization ability are also limited to the design of anchors. Instead, FoveaBox directly learns the object existing possibility and the bounding box coordinates without anchor reference. This is achieved by: (a) predicting category-sensitive semantic maps for the object existing possibility, and (b) producing category-agnostic bounding box for each position that potentially contains an object. The scales of target boxes are naturally associated with feature pyramid representations. In FoveaBox, an instance is assigned to adjacent feature levels to make the model more accurate.We demonstrate its effectiveness on standard benchmarks and report extensive experimental analysis. Without bells and whistles, FoveaBox achieves state-of-the-art single model performance on the standard COCO and Pascal VOC object detection benchmark. More importantly, FoveaBox avoids all computation and hyper-parameters related to anchor boxes, which are often sensitive to the final detection performance. We believe the simple and effective approach will serve as a solid baseline and help ease future research for object detection. The code has been made publicly available athttps://github.com/taokong/FoveaBox.

We propose a light-weight video frame interpolation algorithm. Our key innovation is an instance-level supervision that allows information to be learned from the high-resolution version of similar objects. Our experiment shows that the proposed method can generate state-of-the-art results across different datasets, with fractional computation resources (time and memory) of competing methods. Given two image frames, a cascade network creates an intermediate frame with 1) a flow-warping module that computes coarse bi-directional optical flow and creates an interpolated image via flow-based warping, followed by 2) an image synthesis module to make fine-scale corrections. In the learning stage, object detection proposals are generated on the interpolated image. Lower resolution objects are zoomed into, and the learning algorithms using an adversarial loss trained on high-resolution objects to guide the system towards the instance-level refinement corrects details of object shape and boundaries.

Different functional areas of the human brain play different roles in brain activity, which has not been paid sufficient research attention in the brain-computer interface (BCI) field. This paper presents a new approach for electroencephalography (EEG) classification that applies attention-based transfer learning. Our approach considers the importance of different brain functional areas to improve the accuracy of EEG classification, and provides an additional way to automatically identify brain functional areas associated with new activities without the involvement of a medical professional. We demonstrate empirically that our approach out-performs state-of-the-art approaches in the task of EEG classification, and the results of visualization indicate that our approach can detect brain functional areas related to a certain task.

Taking the feature pyramids into account has become a crucial way to boost the object detection performance. While various pyramid representations have been developed, previous works are still inefficient to integrate the semantical information over different scales. Moreover, recent object detectors are suffering from accurate object location applications, mainly due to the coarse definition of the "positive" examples at training and predicting phases. In this paper, we begin by analyzing current pyramid solutions, and then propose a novel architecture by reconfiguring the feature hierarchy in a flexible yet effective way. In particular, our architecture consists of two lightweight and trainable processes: global attention and local reconfiguration. The global attention is to emphasize the global information of each feature scale, while the local reconfiguration is to capture the local correlations across different scales. Both the global attention and local reconfiguration are non-linear and thus exhibit more expressive ability. Then, we discover that the loss function for object detectors during training is the central cause of the inaccurate location problem. We propose to address this issue by reshaping the standard cross entropy loss such that it focuses more on accurate predictions. Both the feature reconfiguration and the consistent loss could be utilized in popular one-stage (SSD, RetinaNet) and two-stage (Faster R-CNN) detection frameworks. Extensive experimental evaluations on PASCAL VOC 2007, PASCAL VOC 2012 and MS COCO datasets demonstrate that, our models achieve consistent and significant boosts compared with other state-of-the-art methods.

Insufficient training data is a serious problem in all domains related to bioinformatics. Large-scale annotated electroencephalography (EEG) datasets are almost impossible to acquire because biological data acquisition is challenging and quality annotation is costly. Transfer learning relaxes the hypothesis that the training data must be independent and identically distributed (i.i. d.) with the test data, which motivates us to use transfer learning to solve the problem of insufficient training data in bioinformatics. We propose a new approach to transfer knowledge via a deep transfer learning framework, which includes an adaptive sample selection algorithm and a joint adversarial training algorithm. The adaptive sample selection algorithm dynamically adjusts the sample weights during the training process according to the distance between the source domain and the target domain. The joint adversarial training algorithm forces the network to learn a feature extractor suitable for the target domain based on a dataset from the source domain by using an adversarial network and a specific loss function. The experiments demonstrate that our approach has many advantages, such as robustness and accuracy, when applied to EEG classification tasks.

We present RON, an efficient and effective framework for generic object detection. Our motivation is to smartly associate the best of the region-based (e.g., Faster R-CNN) and region-free (e.g., SSD) methodologies. Under fully convolutional architecture, RON mainly focuses on two fundamental problems: (a) multi-scale object localization and (b) negative sample mining. To address (a), we design the reverse connection, which enables the network to detect objects on multi-levels of CNNs. To deal with (b), we propose the objectness prior to significantly reduce the searching space of objects. We optimize the reverse connection, objectness prior and object detector jointly by a multi-task loss function, thus RON can directly predict final detection results from all locations of various feature maps. Extensive experiments on the challenging PASCAL VOC 2007, PASCAL VOC 2012 and MS COCO benchmarks demonstrate the competitive performance of RON. Specifically, with VGG-16 and low resolution 384×384 input size, the network gets 81.3% mAP on PASCAL VOC 2007, 80.7% mAP on PASCAL VOC 2012 datasets. Its superiority increases when datasets become larger and more difficult, as demonstrated by the results on the MS COCO dataset. With 1.5G GPU memory at test phase, the speed of the network is 15 FPS, 3 times faster than the Faster R-CNN counterpart. Code will be made publicly available.

The robotic grasp detection is a great challenge in the area of robotics. Previous work mainly employs the visual approaches to solve this problem. In this paper, a hybrid deep architecture combining the visual and tactile sensing for robotic grasp detection is proposed. We have demonstrated that the visual sensing and tactile sensing are complementary to each other and important for the robotic grasping. A new THU grasp dataset has also been collected which contains the visual, tactile and grasp configuration information. The experiments conducted on a public grasp dataset and our collected dataset show that the performance of the proposed model is superior to state of the art methods. The results also indicate that the tactile data could help to enable the network to learn better visual features for the robotic grasp detection task.

Almost all of the current top-performing object detection networks employ region proposals to guide the search for object instances. State-of-the-art region proposal methods usually need several thousand proposals to get high recall, thus hurting the detection efficiency. Although the latest Region Proposal Network method gets promising detection accuracy with several hundred proposals, it still struggles in small-size object detection and precise localization (e.g., large IoU thresholds), mainly due to the coarseness of its feature maps. In this paper, we present a deep hierarchical network, namely HyperNet, for handling region proposal generation and object detection jointly. Our HyperNet is primarily based on an elaborately designed Hyper Feature which aggregates hierarchical feature maps first and then compresses them into a uniform space. The Hyper Features well incorporate deep but highly semantic, intermediate but really complementary, and shallow but naturally high-resolution features of the image, thus enabling us to construct HyperNet by sharing them both in generating proposals and detecting objects via an end-to-end joint training strategy. For the deep VGG16 model, our method achieves completely leading recall and state-of-the-art object detection accuracy on PASCAL VOC 2007 and 2012 using only 100 proposals per image. It runs with a speed of 5 fps (including all steps) on a GPU, thus having the potential for real-time processing.

Grasp an object from a stack of objects in real-time is still a challenge in robotics. This requires the robot to have the ability of both fast object discovery and grasp detection: a target object should be picked out from the stack first and then a proper grasp configuration is applied to grasp the object. In this paper, we propose a shared convolutional neural network (CNN) which can simultaneously implement these two tasks in real-time. The processing speed of the model is about 100 frames per second on a GPU which largely satisfies the requirement. Meanwhile, we also establish a labeled RGBD dataset which contains scenes of stacked objects for robotic grasping. At last, we demonstrate the implementation of our shared CNN model on a real robotic platform and show that the robot can accurately discover a target object from the stack and successfully grasp it.

Breast cancer is the most common form of cancer in women worldwide. The major impediment to finding cures for malignant breast cancers is the development of resistances to therapeutic treatments by tumors. The development of nanoparticles may provide an important opportunity for improvement in breast cancer treatments. Nanoparticles coupled with the specific targeting agents have the ability to track and eliminate breast cancer cells. In this paper, we present gold-based nanoparticles for breast cancer diagnosis and treatment. The proposed design can become a new method for the treatment of breast cancer tumors. Our design can eventually lead to clinical trials which will benefit breast cancer patients worldwide.