We present SensorLM, a family of sensor-language foundation models that enable wearable sensor data understanding with natural language. Despite its pervasive nature, aligning and interpreting sensor data with language remains challenging due to the lack of paired, richly annotated sensor-text descriptions in uncurated, real-world wearable data. We introduce a hierarchical caption generation pipeline designed to capture statistical, structural, and semantic information from sensor data. This approach enabled the curation of the largest sensor-language dataset to date, comprising over 59.7 million hours of data from more than 103,000 people. Furthermore, SensorLM extends prominent multimodal pretraining architectures (e.g., CLIP, CoCa) and recovers them as specific variants within a generic architecture. Extensive experiments on real-world tasks in human activity analysis and healthcare verify the superior performance of SensorLM over state-of-the-art in zero-shot recognition, few-shot learning, and cross-modal retrieval. SensorLM also demonstrates intriguing capabilities including scaling behaviors, label efficiency, sensor captioning, and zero-shot generalization to unseen tasks. Code is available at https://github.com/Google-Health/consumer-health-research/tree/main/sensorlm.

Although there have been automated approaches and tools supporting toxicity censorship for social posts, most of them focus on detection. Toxicity censorship is a complex process, wherein detection is just an initial task and a user can have further needs such as rationale understanding and content modification. For this problem, we conduct a need-finding study to investigate people's diverse needs in toxicity censorship and then build a ChatGPT-based censorship tool named DeMod accordingly. DeMod is equipped with the features of explainable De tection and personalized Mod ification, providing fine-grained detection results, detailed explanations, and personalized modification suggestions. We also implemented the tool and recruited 35 Weibo users for evaluation. The results suggest DeMod's multiple strengths like the richness of functionality, the accuracy of censorship, and ease of use. Based on the findings, we further propose several insights into the design of content censorship systems.

Danmu (or “bullet screen”), a popular feature on video sharing platforms, plays a crucial role in facilitating knowledge sharing and learning. In recent years, danmu has drawn attention to automatic generation methods. However, existing methods mostly utilize limited content sources, such as the video itself (e.g., subtitles) and neighboring danmus, while other valuable sources remain underexplored. To this end, this article proposes a Category-Guided Note-to-Danmu conversion model (CG-NTD) by leveraging user-generated notes. The model is designed to identify unique contents within the notes and convert them into danmus while also showing the source note categories. CG-NTD classifies the notes by fusing them with subtitle and neighboring danmu features. Then, it uses a cross-attention mechanism to integrate the note’s category feature with note, subtitle, and danmu contexts to identify three keywords from the notes as the generated danmus. Using Bilibili as the research site, we implement a plugin prototype named BNoteToDanmu. Automatic and human evaluations reveal that CG-NTD outperforms BiLSTM, mT5, and BERT baselines in Precision, Recall, and F1-score metrics and generates more understandable and relevant danmus than ChatGPT. Moreover, the plugin demonstrates promising applications, such as assisting users in viewing videos, posting danmus, and recognizing high-quality notes. These findings offer insights into leveraging user creations to generate danmu to enhance its learning value on video sharing platforms.

We demonstrate text as a strong cross-modal interface. Rather than relying on deep embeddings to connect image and language as the interface representation, our approach represents an image as text, from which we enjoy the interpretability and flexibility inherent to natural language. We employ an autoencoder that uses a pre-trained text-to-image diffusion model for decoding. The encoder is trained to transform an input image into text, which is then fed into the fixed text-to-image diffusion decoder to reconstruct the original input ─a process we term De-Diffusion. Experiments validate both the precision and comprehensiveness of De-Diffusion text representing images, such that it can be readily ingested by off-the-shelf text-to-image tools and LLMs for diverse multi-modal tasks. For example, a single De-Diffusion model can generalize to provide transferable prompts for different text-to-image tools, and also achieves a new state of the art on open-ended vision-language tasks by simply prompting large language models with few-shot examples. Project page: dediffusion.github.io.

Image retrieval, i.e., finding desired images given a reference image, inherently encompasses rich, multi-faceted search intents that are difficult to capture solely using image-based measures. Recent works leverage text instructions to allow users to more freely express their search intents. However, they primarily focus on image pairs that are visually similar and/or can be characterized by a small set of pre-defined relations. The core thesis of this paper is that text instructions can enable retrieving images with richer relations beyond visual similarity. To show this, we introduce MagicLens, a series of self-supervised image retrieval models that support open-ended instructions. MagicLens is built on a key novel insight: image pairs that naturally occur on the same web pages contain a wide range of implicit relations (e.g., inside view of), and we can bring those implicit relations explicit by synthesizing instructions via foundation models. Trained on 36.7M (query image, instruction, target image) triplets with rich semantic relations mined from the web, MagicLens achieves results comparable with or better than prior best on eight benchmarks of various image retrieval tasks, while maintaining high parameter efficiency with a significantly smaller model size. Additional human analyses on a 1.4M-image unseen corpus further demonstrate the diversity of search intents supported by MagicLens. Code and models are publicly available at the https://open-vision-language.github.io/MagicLens/.

Dense prediction tasks, such as semantic segmentation, depth estimation, and surface normal prediction, can be easily formulated as per-pixel classification (discrete outputs) or regression (continuous outputs). This per-pixel prediction paradigm has remained popular due to the prevalence of fully convolutional networks. However, on the recent frontier of segmentation task, the community has been witnessing a shift of paradigm from per-pixel prediction to cluster-prediction with the emergence of transformer architectures, particularly the mask transformers, which directly predicts a label for a mask instead of a pixel. Despite this shift, methods based on the per-pixel prediction paradigm still dominate the benchmarks on the other dense prediction tasks that require continuous outputs, such as depth estimation and surface normal prediction. Motivated by the success of DORN and AdaBins in depth estimation, achieved by discretizing the continuous output space, we propose to generalize the cluster-prediction based method to general dense prediction tasks. This allows us to unify dense prediction tasks with the mask transformer framework. Remarkably, the resulting model PolyMaX demonstrates state-of-the-art performance on three benchmarks of NYUD-v2 dataset. We hope our simple yet effective design can inspire more research on exploiting mask transformers for more dense prediction tasks. Code and model will be made available1.

Semantic segmentation, which aims to classify every pixel in an image, is a key task in machine perception, with many applications across robotics and autonomous driving. Due to the high dimensionality of this task, most existing approaches use local operations, such as convolutions, to generate per-pixel features. However, these methods are typically unable to effectively leverage global context information due to the high computational costs of operating on a dense image. In this work, we propose a solution to this issue by leveraging the idea of superpixels, an over-segmentation of the image, and applying them with a modern transformer framework. In particular, our model learns to decompose the pixel space into a spatially low dimensional superpixel space via a series of local cross-attentions. We then apply multi-head self-attention to the superpixels to enrich the superpixel features with global context and then directly produce a class prediction for each superpixel. Finally, we directly project the superpixel class predictions back into the pixel space using the associations between the superpixels and the image pixel features. Reasoning in the superpixel space allows our method to be substantially more computationally efficient compared to convolution-based decoder methods. Yet, our method achieves state-of-the-art performance in semantic segmentation due to the rich superpixel features generated by the global self-attention mechanism. Our experiments on Cityscapes and ADE20K demonstrate that our method matches the state of the art in terms of accuracy, while outperforming in terms of model parameters and latency.

Batch normalization (BN) is a fundamental unit in modern deep neural networks. However, BN and its variants focus on normalization statistics but neglect the recovery step that uses linear transformation to improve the capacity of fitting complex data distributions. In this paper, we demonstrate that the recovery step can be improved by aggregating the neighborhood of each neuron rather than just considering a single neuron. Specifically, we propose a simple yet effective method named batch normalization with enhanced linear transformation (BNET) to embed spatial contextual information and improve representation ability. BNET can be easily implemented using the depth-wise convolution and seamlessly transplanted into existing architectures with BN. To our best knowledge, BNET is the first attempt to enhance the recovery step for BN. Furthermore, BN is interpreted as a special case of BNET from both spatial and spectral views. Experimental results demonstrate that BNET achieves consistent performance gains based on various backbones in a wide range of visual tasks. Moreover, BNET can accelerate the convergence of network training and enhance spatial information by assigning important neurons with large weights accordingly.

We present TubeFormer-DeepLab, the first attempt to tackle multiple core video segmentation tasks in a unified manner. Different video segmentation tasks (e.g., video semantic/instance/panoptic segmentation) are usually considered as distinct problems. State-of-the-art models adopted in the separate communities have diverged, and radically different approaches dominate in each task. By contrast, we make a crucial observation that video segmentation tasks could be generally formulated as the problem of assigning different predicted labels to video tubes (where a tube is obtained by linking segmentation masks along the time axis) and the labels may encode different values depending on the target task. The observation motivates us to develop TubeFormer-DeepLab, a simple and effective video mask transformer model that is widely applicable to multiple video segmentation tasks. TubeFormer-DeepLab directly predicts video tubes with task-specific labels (either pure semantic categories, or both semantic categories and instance identities), which not only significantly simplifies video segmentation models, but also advances state-of-the-art results on multiple video segmentation benchmarks.

We propose Clustering Mask Transformer (CMT-DeepLab), a transformer-based framework for panoptic segmentation designed around clustering. It rethinks the existing transformer architectures used in segmentation and detection; CMT-DeepLab considers the object queries as cluster centers, which fill the role of grouping the pixels when applied to segmentation. The clustering is computed with an alternating procedure, by first assigning pixels to the clusters by their feature affinity, and then updating the cluster centers and pixel features. Together, these operations comprise the Clustering Mask Transformer (CMT) layer, which produces cross-attention that is denser and more consistent with the final segmentation task. CMT-DeepLab improves the performance over prior art significantly by 4.4% PQ, achieving a new state-of-the-art of 55.7% PQ on the COCO test-dev set.

The key to a successful cascade architecture for precise instance segmentation is to fully leverage the relationship between bounding box detection and mask segmentation across multiple stages. Although modern instance segmentation cascades achieve leading performance, they mainly make use of a unidirectional relationship, i.e., mask segmentation can benefit from iteratively refined bounding box detection. In this paper, we investigate an alternative direction, i.e., how to take the advantage of precise mask segmentation for bounding box detection in a cascade architecture. We propose a Deeply Shape-guided Cascade (DSC) for instance segmentation, which iteratively imposes the shape guidances extracted from mask prediction at previous stage on bounding box detection at current stage. It forms a bi-directional relationship between the two tasks by introducing three key components: (1) Initial shape guidance: A mask-supervised Region Proposal Network (mPRN) with the ability to generate class-agnostic masks; (2) Explicit shape guidance: A mask-guided regionof-interest (RoI) feature extractor, which employs mask segmentation at previous stage to focus feature extraction at current stage within a region aligned well with the shape of the instance-of-interest rather than a rectangular RoI; (3) Implicit shape guidance: A feature fusion operation which feeds intermediate mask features at previous stage to the bounding box head at current stage. Experimental results show that DSC outperforms the state-of-the-art instance segmentation cascade, Hybrid Task Cascade (HTC), by a large margin and achieves 51.8 box AP and 45.5 mask AP on COCO test-dev. The code is released at: https://github.com/hding2455/DSC.

Many modern object detectors demonstrate outstanding performances by using the mechanism of looking and thinking twice. In this paper, we explore this mechanism in the backbone design for object detection. At the macro level, we propose Recursive Feature Pyramid, which incorporates extra feedback connections from Feature Pyramid Networks into the bottom-up backbone layers. At the micro level, we propose Switchable Atrous Convolution, which convolves the features with different atrous rates and gathers the results using switch functions. Combining them results in DetectoRS, which significantly improves the performances of object detection. On COCO test-dev, DetectoRS achieves state-of-the-art 55.7% box AP for object detection, 48.5% mask AP for instance segmentation, and 50.0% PQ for panoptic segmentation. The code is made publicly available1.

In this paper, we present ViP-DeepLab, a unified model attempting to tackle the long-standing and challenging inverse projection problem in vision, which we model as restoring the point clouds from perspective image sequences while providing each point with instance-level semantic interpretations. Solving this problem requires the vision models to predict the spatial location, semantic class, and temporally consistent instance label for each 3D point. ViP-DeepLab approaches it by jointly performing monocular depth estimation and video panoptic segmentation. We name this joint task as Depth-aware Video Panoptic Segmentation, and propose a new evaluation metric along with two derived datasets for it, which will be made available to the public. On the individual sub-tasks, ViP-DeepLab also achieves state-of-the-art results, outperforming previous methods by 5.1% VPQ on Cityscapes-VPS, ranking 1st on the KITTI monocular depth estimation benchmark, and 1st on KITTI MOTS pedestrian. The datasets and the evaluation codes are made publicly available1.

The key features of 5G network (i.e., high bandwidth, low latency, and high concurrency) along with the capability of supporting big data platforms with high mobility make it valuable in coping with emerging medical needs, such as COVID-19 and future healthcare challenges. However, enforcing the security aspect of a 5G-based smart healthcare system that hosts critical data and services is becoming more urgent and critical. Passive security mechanisms (e.g., data encryption and isolation) used in legacy medical platforms cannot provide sufficient protection for a healthcare system that is deployed in a distributed manner and fail to meet the need for data/service sharing across "cloud-edge-terminal" in the 5G era. In this article, we propose a security awareness and protection system that leverages zero-trust architecture for a 5G-based smart medical platform. Driven by the four key dimensions of 5G smart healthcare including "subject" (i.e., users, terminals, and applications), "object" (i.e., data, platforms, and services), "behavior," and "environment," our system constructs trustable dynamic access control models and achieves real-time network security situational awareness, continuous identity authentication, analysis of access behavior, and fine-grained access control. The proposed security system is implemented and tested thoroughly at industrial-grade, which proves that it satisfies the needs of active defense and end-to-end security enforcement of data, users, and services involved in a 5G-based smart medical system.

Recent anchor-based deep face detectors have achieved promising performance, but they are still struggling to detect hard faces, such as small, blurred and partially occluded faces. One reason is that they treat all images and faces equally, and ignore the imbalance between easy images and hard images; however large amounts of training images only contain easy faces, which are less helpful to learn robust detectors for hard faces. In this paper, we propose that the robustness of a face detector against hard faces can be improved by learning small faces on hard images. Our intuitions are (1) hard images are the images which contain at least one hard face, thus they facilitate training robust face detectors; (2) most hard faces are small faces and other types of hard faces can be easily shrunk to small faces. To this end, we build an anchor-based deep face detector, which only outputs a single high-resolution feature map with small anchors, to specifically learn small faces and train it by a novel hard image mining strategy which automatically adjusts training weights on images according to their difficulties. Extensive experiments have been conducted on WIDER FACE, FDDB, Pascal Faces, and AFW datasets and our method achieves APs of 95.7, 94.9 and 89.7 on easy, medium and hard WIDER FACE val dataset respectively, which verify the effectiveness of our methods, especially on detecting hard faces. Our detector is also lightweight and enjoys a fast inference speed. Code and model are available at https://github.com/bairdzhang/smallhardface.

We focus on the problem of training a deep neural network in generations. The flowchart is that, in order to optimize the target network (student), another network (teacher) with the same architecture is first trained, and used to provide part of supervision signals in the next stage. While this strategy leads to a higher accuracy, many aspects (e.g., why teacher-student optimization helps) still need further explorations.This paper studies this problem from a perspective of controlling the strictness in training the teacher network. Existing approaches mostly used a hard distribution (e.g., one-hot vectors) in training, leading to a strict teacher which itself has a high accuracy, but we argue that the teacher needs to be more tolerant, although this often implies a lower accuracy. The implementation is very easy, with merely an extra loss term added to the teacher network, facilitating a few secondary classes to emerge and complement to the primary class. Consequently, the teacher provides a milder supervision signal (a less peaked distribution), and makes it possible for the student to learn from inter-class similarity and potentially lower the risk of over-fitting. Experiments are performed on standard image classification tasks (CIFAR100 and ILSVRC2012). Although the teacher network behaves less powerful, the students show a persistent ability growth and eventually achieve higher classification accuracies than other competitors. Model ensemble and transfer feature extraction also verify the effectiveness of our approach.

In this paper, we study the problem of improving computational resource utilization of neural networks. Deep neural networks are usually over-parameterized for their tasks in order to achieve good performances, thus are likely to have underutilized computational resources. This observation motivates a lot of research topics, e.g. network pruning, architecture search, etc. As models with higher computational costs (e.g. more parameters or more computations) usually have better performances, we study the problem of improving the resource utilization of neural networks so that their potentials can be further realized. To this end, we propose a novel optimization method named Neural Rejuvenation. As its name suggests, our method detects dead neurons and computes resource utilization in real time, rejuvenates dead neurons by resource reallocation and reinitialization, and trains them with new training schemes. By simply replacing standard optimizers with Neural Rejuvenation, we are able to improve the performances of neural networks by a very large margin while using similar training efforts and maintaining their original resource usages. The code is available here: https://github.com/joe-siyuan-qiao/NeuralRejuvenation-CVPR19

In this paper, we are interested in the few-shot learning problem. In particular, we focus on a challenging scenario where the number of categories is large and the number of examples per novel category is very limited, e.g. 1, 2, or 3. Motivated by the close relationship between the parameters and the activations in a neural network associated with the same category, we propose a novel method that can adapt a pre-trained neural network to novel categories by directly predicting the parameters from the activations. Zero training is required in adaptation to novel categories, and fast inference is realized by a single forward pass. We evaluate our method by doing few-shot image recognition on the ImageNet dataset, which achieves the state-of-the-art classification accuracy on novel categories by a significant margin while keeping comparable performance on the large-scale categories. We also test our method on the MiniImageNet dataset and it strongly outperforms the previous state-of-the-art methods.

We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module. The segmentation branch is supervised by weak segmentation ground-truth, i.e., no extra annotation is required. In conjunction with that, we employ a global activation module which learns relationship between channels and object classes in a self-supervised manner. Comprehensive experimental results on both PASCAL VOC and MS COCO detection datasets demonstrate the effectiveness of the proposed method. In particular, with a VGG16 based DES, we achieve an mAP of 81.7 on VOC2007 test and an mAP of 32.8 on COCO test-dev with an inference speed of 31.5 milliseconds per image on a Titan Xp GPU. With a lower resolution version, we achieve an mAP of 79.7 on VOC2007 with an inference speed of 13.0 milliseconds per image.

Depth is one of the keys that make neural networks succeed in the task of large-scale image recognition. The state-of-the-art network architectures usually increase the depths by cascading convolutional layers or building blocks. In this paper, we present an alternative method to increase the depth. Our method is by introducing computation orderings to the channels within convolutional layers or blocks, based on which we gradually compute the outputs in a channel-wise manner. The added orderings not only increase the depths and the learning capacities of the networks without any additional computation costs, but also eliminate the overlap singularities so that the networks are able to converge faster and perform better. Experiments show that the networks based on our method achieve the state-of-the-art performances on CIFAR and ImageNet datasets.

Motivated by product detection in supermarkets, this paper studies the problem of object proposal generation in supermarket images and other natural images. We argue that estimation of object scales in images is helpful for generating object proposals, especially for supermarket images where object scales are usually within a small range. Therefore, we propose to estimate object scales of images before generating object proposals. The proposed method for predicting object scales is called ScaleNet. To validate the effectiveness of ScaleNet, we build three supermarket datasets, two of which are real-world datasets used for testing and the other one is a synthetic dataset used for training. In short, we extend the previous state-of-the-art object proposal methods by adding a scale prediction phase. The resulted method outperforms the previous state-of-the-art on the supermarket datasets by a large margin. We also show that the approach works for object proposal on other natural images and it outperforms the previous state-of-the-art object proposal methods on the MS COCO dataset. The supermarket datasets, the virtual supermarkets, and the tools for creating more synthetic datasets will be made public.

In this paper, we reveal the importance and benefits of introducing second-order operations into deep neural networks. We propose a novel approach named Second-Order Response Transform (SORT), which appends element-wise product transform to the linear sum of a two-branch network module. A direct advantage of SORT is to facilitate cross-branch response propagation, so that each branch can update its weights based on the current status of the other branch. Moreover, SORT augments the family of transform operations and increases the nonlinearity of the network, making it possible to learn flexible functions to fit the complicated distribution of feature space. SORT can be applied to a wide range of network architectures, including a branched variant of a chain-styled network and a residual network, with very light-weighted modifications. We observe consistent accuracy gain on both small (CIFAR10, CIFAR100 and SVHN) and big (ILSVRC2012) datasets. In addition, SORT is very efficient, as the extra computation overhead is less than 5%.

UnrealCV is a project to help computer vision researchers build virtual worlds using Unreal Engine 4 (UE4). It extends UE4 with a plugin by providing (1) A set of UnrealCV commands to interact with the virtual world. (2) Communication between UE4 and an external program, such as Caffe. UnrealCV can be used in two ways. The first one is using a compiled game binary with UnrealCV embedded. This is as simple as running a game, no knowledge of Unreal Engine is required. The second is installing UnrealCV plugin to Unreal Engine 4 (UE4) and use the editor of UE4 to build a new virtual world. UnrealCV is an open-source software under the MIT license. Since the initial release in September 2016, it has gathered an active community of users, including students and researchers.