We present Visual Lexicon, a novel visual language that encodes rich image information into the text space of vocabulary tokens while retaining intricate visual details that are often challenging to convey in natural language. Unlike traditional methods that prioritize either high-level semantics (e.g., CLIP) or pixel-level reconstruction (e.g., VAE), ViLex simultaneously captures rich semantic content and fine visual details, enabling high-quality image generation and comprehensive visual scene understanding. Through a self-supervised learning pipeline, ViLex generates tokens optimized for reconstructing input images using a frozen text-to-image (T2I) diffusion model, preserving the detailed information necessary for high-fidelity semantic-level reconstruction. As an image embedding in the language space, ViLex tokens leverage the compositionality of natural languages, allowing them to be used independently as "text tokens" or combined with natural language tokens to prompt pretrained T2I models with both visual and textual inputs, mirroring how we interact with vision-language models (VLMs). Experiments demonstrate that ViLex achieves higher fidelity in image reconstruction compared to text embeddings—even with a single ViLex token. Moreover, ViLex successfully performs various DreamBooth tasks in a zero-shot, unsupervised manner without fine-tuning T2I models. Additionally, ViLex serves as a powerful vision encoder, consistently improving vision-language model performance across 15 benchmarks relative to a strong SigLIP baseline.

We present SegLLM, a novel multi-round interactive reasoning segmentation model that enhances LLM-based segmentation by exploiting conversational memory of both visual and textual outputs. By leveraging a mask-aware multimodal LLM, SegLLM re-integrates previous segmentation results into its input stream, enabling it to reason about complex user intentions and segment objects in relation to previously identified entities, including positional, interactional, and hierarchical relationships, across multiple interactions. This capability allows SegLLM to respond to visual and text queries in a chat-like manner. Evaluated on the newly curated MRSeg benchmark, SegLLM outperforms existing methods in multi- round interactive reasoning segmentation by over 20%. Additionally, we observed that training on multi-round reasoning segmentation data enhances performance on standard single-round referring segmentation and localization tasks, resulting in a 5.5% increase in cIoU for referring expression segmentation and a 4.5% improvement in [email protected] for referring expression localization.

Text-to-image diffusion models produce high quality images but do not offer control over individual instances in the image. We introduce InstanceDiffusion that adds precise instance-level control to text-to-image diffusion models. InstanceDiffusion supports free-form language conditions per instance and allows flexible ways to specify instance locations such as simple single points, scribbles, bounding boxes or intricate instance segmentation masks, and combinations thereof We propose three major changes to text-to-image models that enable precise instance-level control. Our UniFusion block enables instance-level conditions for text-to-image models, the ScaleU block improves image fidelity, and our Multi-instance Sampler improves generations for multiple instances. InstanceDiffusion significantly surpasses specialized state-of-the-art models for each location condition. Notably, on the COCO dataset, we out-perform previous state-of-the-art by 20.4%$AP_{50}^{box}$for box inputs, and 25.4% IoU for mask inputs.

Existing approaches to unsupervised video instance segmentation typically rely on motion estimates and experi-ence difficulties tracking small or divergent motions. We present VideoCutLER, a simple method for unsupervised multi-instance video segmentation without using motion-based learning signals like optical flow or training on natural videos. Our key insight is that using high-quality pseudo masks and a simple video synthesis method for model training is surprisingly sufficient to enable the resulting video model to effectively segment and track multiple instances across video frames. We show the first competitive unsupervised learning results on the challenging YouTube Vis-2019 benchmark, achieving 50.7%$AP_{50}^{video}$, surpassing the previous state-of-the-art by a large margin. VideoCutLER can also serve as a strong pretrained model for supervised video instance segmentation tasks, exceeding DINO by 15.9% on YouTubeVIS-2019 in terms of$AP^{video}$.

Several unsupervised image segmentation approaches have been proposed which eliminate the need for dense manually-annotated segmentation masks; current models separately handle either semantic segmentation (e.g., STEGO) or class-agnostic instance segmentation (e.g., Cut-LER), but not both (i.e., panoptic segmentation). We propose an Unsupervised Universal Segmentation model (U2Seg) adept at performing various image segmentation tasks-instance, semantic and panoptic-using a novel uni-fied framework. U2Seg generates pseudo semantic labels for these segmentation tasks via leveraging self-supervised models followed by clustering; each cluster represents different semantic and/or instance membership of pixels. We then self-train the model on these pseudo semantic labels, yielding substantial performance gains over specialized methods tailored to each task: a+2.6APbox boost (vs. Cut-LER) in unsupervised instance segmentation on COCO and a + 7.0 PixelAcc increase (vs. STEGO) in unsupervised semantic segmentation on COCOStuff. Moreover, our method sets up a new baseline for unsupervised panoptic segmentation, which has not been previously explored. U2Seg is also a strong pretrained model for few-shot segmentation, sur-passing CutLERby+3.0APmask when trained on a low-data regime, e.g., only 1 % COCO labels. We hope our simple yet effective method can inspire more research on unsupervised universal image segmentation.

Current open-source Large Multimodal Models (LMMs) excel at tasks such as open-vocabulary language grounding and segmentation but can suffer under false premises when queries imply the existence of something that is not actually present in the image. We observe that existing methods that fine-tune an LMM to segment images significantly degrade their ability to reliably determine ('see”) if an object is present and to interact naturally with humans (“say”), a form of catastrophic forgetting. In this work, we propose a cascading and joint training approachfor LMMs to solve this task, avoiding catastrophic forgetting of previous skills. Our resulting model can “see” by detecting whether objects are present in an image, “Say” by telling the user if they are not, proposing alternative queries or correcting semantic errors in the query, and finally “segment” by outputting the mask of the desired objects if they exist. Additionally, we introduce a novel False Premise Correction benchmark dataset, an extension of existing RefCOCO(+/g) referring segmentation datasets (which we call FP-RefCOCO(+/g)). The results show that our method not only detects false premises up to 55% better than existing approaches, but under false premise conditions produces relative cIOU improvements of more than 31% over baselines, and produces natural language feedback judged helpful up to 67% of the time.

The Segmentation Anything Model (SAM) requires labor-intensive data labeling. We present Unsupervised SAM (UnSAM) for promptable and automatic whole-image segmentation that does not require human annotations. UnSAM utilizes a divide-and-conquer strategy to “discover” the hierarchical structure of visual scenes. We first leverage top-down clustering methods to partition an unlabeled image into instance/semantic level segments. For all pixels within a segment, a bottom-up clustering method is employed to iteratively merge them into larger groups, thereby forming a hierarchical structure. These unsupervised multi-granular masks are then utilized to supervise model training. Evaluated across seven popular datasets, UnSAM achieves competitive results with the supervised counterpart SAM, and surpasses the previous state-of-the-art in unsupervised segmentation by 11% in terms of AR. Moreover, we show that supervised SAM can also benefit from our self-supervised labels. By integrating our unsupervised pseudo masks into SA-1B’s ground-truth masks and training UnSAM with only 1% of SA-1B, a lightly semi-supervised UnSAM can often segment entities overlooked by supervised SAM, exceeding SAM’s AR by over 6.7% and AP by 3.9% on SA-1B.

We propose Cut-and-LEaRn (CutLER), a simple approach for training unsupervised object detection and seg-mentation models. We leverage the property of self-supervised models to ‘discover’ objects without supervision and amplify it to train a state-of-the-art localization model without any human labels. CutLER first uses our proposed MaskCut approach to generate coarse masks for multiple objects in an image, and then learns a detector on these masks using our robust loss function. We further improve performance by self-training the model on its predictions. Compared to prior work, CutLER is simpler, compatible with different detection architectures, and detects multiple objects. CutLER is also a zero-shot unsupervised detector and improves detection performance AP50by over 2.7× on 11 benchmarks across domains like video frames, paintings, sketches, etc. With finetuning, CutLER serves as a low-shot detector surpassing MoCo-v2 by 7.3% Apboxand 6.6% Apmaskon COCO when training with 5% labels.

Open-vocabulary image segmentation aims to partition an image into semantic regions according to arbitrary text descriptions. However, complex visual scenes can be naturally decomposed into simpler parts and abstracted at multiple lev4 els of granularity, introducing inherent segmentation ambiguity. Unlike existing methods that typically sidestep this ambiguity and treat it as an external factor, our approach actively incorporates a hierarchical representation encompassing different semantic-levels into the learning process. We propose a decoupled text-image fusion mechanism and representation learning modules for both “things” and “stuff”. Additionally, we systematically examine the differences that exist in the textual and visual features between these types of categories. Our resulting model, named HIPIE, tackles HIerarchical, oPen-vocabulary, and unIvErsal segmentation tasks within a unified framework. Benchmarked on diverse datasets, e.g., ADE20K,COCO, Pascal-VOC Part, and RefCOCO/RefCOCOg, HIPIE achieves the state-of14 the-art results at various levels of image comprehension, including semantic-level (e.g., semantic segmentation), instance-level (e.g., panoptic/referring segmentationand object detection), as well as part-level (e.g., part/subpart segmentation) tasks.

Hyperbolic space can naturally embed hierarchies, unlike Euclidean space. Hyperbolic Neural Networks (HNNs) exploit such representational power by lifting Euclidean features into hyperbolic space for classification, outperforming Euclidean neural networks (ENNs) on datasets with known semantic hierarchies. However, HNNs underperform ENNs on standard benchmarks without clear hierarchies, greatly restricting HNNs' applicability in practice. Our key insight is that HNNs' poorer general classification performance results from vanishing gradients during backpropagation, caused by their hybrid architecture connecting Euclidean features to a hyperbolic classifier. We propose an effective solution by simply clipping the Euclidean feature magnitude while training HNNs. Our experiments demonstrate that clipped HNNs become super-hyperbolic classifiers: They are not only consistently better than HNNs which already outperform ENNs on hierarchical data, but also on-par with ENNs on MNIST, CIFAR10, CIFAR100 and ImageNet benchmarks, with better adversarial robustness and out-of-distribution detection.

Unsupervised semantic segmentation aims to discover groupings within and across images that capture object-and view-invariance of a category without external supervision. Grouping naturally has levels of granularity, creating ambiguity in unsupervised segmentation. Existing methods avoid this ambiguity and treat it as a factor outside modeling, whereas we embrace it and desire hierarchical grouping consistency for unsupervised segmentation. We approach unsupervised segmentation as a pixel-wise feature learning problem. Our idea is that a good representation shall reveal not just a particular level of grouping, but any level of grouping in a consistent and predictable manner. We enforce spatial consistency of grouping and bootstrap feature learning with co-segmentation among multiple views of the same image, and enforce semantic consistency across the grouping hierarchy with clustering transformers between coarse- and fine-grained features. We deliver the first data-driven unsupervised hierarchical semantic segmentation method called Hierarchical Segment Grouping (HSG). Capturing visual similarity and statistical co-occurrences, HSG also outperforms existing un-supervised segmentation methods by a large margin on five major object- and scene-centric benchmarks.

Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting. Our key insight is that pseudo-labels are naturally imbalanced due to intrinsic data similarity, even when a model is trained on balanced source data and evaluated on balanced target data. If we address this previously unknown imbalanced classification problem arising from pseudo-labels instead of ground-truth training labels, we could remove model biases towards false majorities created by pseudo-labels. We propose a novel and effective debiased learning method with pseudo-labels, based on counterfactual reasoning and adaptive margins: The former removes the classifier response bias, whereas the latter adjusts the margin of each class according to the imbalance of pseudo-labels. Validated by extensive experimentation, our simple debiased learning delivers significant accuracy gains over the state-of-the-art on ImageNet-1K: 26% for semi-supervised learning with 0.2% annotations and 9% for zero-shot learning. Our code is available at: https://github.com/frank-xwang/debiased-pseudo-labeling.

Convolution is the main building block of a convolutional neural network (CNN). We observe that an optimized CNN often has highly correlated filters as the number of channels increases with depth, reducing the expressive power of feature representations. We propose Tied Block Convolution (TBC) that shares the same thinner filter over equal blocks of channels and produces multiple responses with a single filter. The concept of TBC can also be extended to group convolution and fully connected layers, and can be applied to various backbone networks and attention modules. Our extensive experimentation on classification, detection, instance segmentation, and attention demonstrates that TBC is consistently leaner and significantly better than standard convolution and group convolution. On attention, with 64 times fewer parameters, our TiedSE performs on par with the standard SE. On detection and segmentation, TBC can effectively handle highly overlapping instances, whereas standard CNNs often fail to accurately aggregate information in the presence of occlusion and result in multiple redundant partial object proposals. By sharing filters across channels, TBC reduces correlation and delivers a sizable gain of 6% in the average precision for object detection on MS-COCO when the occlusion ratio is 80%.

Unsupervised feature learning has made great strides with contrastive learning based on instance discrimination and invariant mapping, as benchmarked on curated class-balanced datasets. However, natural data could be highly correlated and long-tail distributed. Natural between-instance similarity conflicts with the presumed instance distinction, causing unstable training and poor performance.Our idea is to discover and integrate between-instance similarity into contrastive learning, not directly by instance grouping, but by cross-level discrimination (CLD) between instances and local instance groups. While invariant mapping of each instance is imposed by attraction within its augmented views, between-instance similarity could emerge from common repulsion against instance groups.Our batch-wise and cross-view comparisons also greatly improve the positive/negative sample ratio of contrastive learning and achieve better invariant mapping. To effect both grouping and discrimination objectives, we impose them on features separately derived from a shared representation. In addition, we propose normalized projection heads and unsupervised hyper-parameter tuning for the first time.Our extensive experimentation demonstrates that CLD is a lean and powerful add-on to existing methods such as NPID, MoCo, InfoMin, and BYOL on highly correlated, long-tail, or balanced datasets. It not only achieves new state-of-the-art on self-supervision, semi-supervision, and transfer learning benchmarks, but also beats MoCo v2 and SimCLR on every reported performance attained with a much larger compute. CLD effectively brings unsupervised learning closer to natural data and real-world applications. Our code is publicly available at: https://github.com/frank-xwang/CLD-UnsupervisedLearning.

Vision-based reinforcement learning (RL) is successful, but how to generalize it to unknown test environments remains challenging. Existing methods focus on training an RL policy that is universal to changing visual domains, whereas we focus on extracting visual foreground that is universal, feeding clean invariant vision to the RL policy learner. Our method is completely unsupervised, without manual annotations or access to environment internals.Given videos of actions in a training environment, we learn how to extract foregrounds with unsupervised keypoint detection, followed by unsupervised visual attention to automatically generate a foreground mask per video frame. We can then introduce artificial distractors and train a model to reconstruct the clean foreground mask from noisy observations. Only this learned model is needed during test to provide distraction-free visual input to the RL policy learner.Our Visual Attention and Invariance (VAI) method significantly outperforms the state-of-the-art on visual domain generalization, gaining 15~49% (61~229%) more cumulative rewards per episode on DeepMind Control (our DrawerWorld Manipulation) benchmarks. Our results demonstrate that it is not only possible to learn domain-invariant vision without any supervision, but freeing RL from visual distractions also makes the policy more focused and thus far better.

Despite increasing efforts on universal representations for visual recognition, few have addressed object detection. In this paper, we develop an effective and efficient universal object detection system that is capable of working on various image domains, from human faces and traffic signs to medical CT images. Unlike multi-domain models, this universal model does not require prior knowledge of the domain of interest. This is achieved by the introduction of a new family of adaptation layers, based on the principles of squeeze and excitation, and a new domain-attention mechanism. In the proposed universal detector, all parameters and computations are shared across domains, and a single network processes all domains all the time. Experiments, on a newly established universal object detection benchmark of 11 diverse datasets, show that the proposed detector outperforms a bank of individual detectors, a multi-domain detector, and a baseline universal detector, with a 1.3x parameter increase over a single-domain baseline detector. The code and benchmark are available at http://www.svcl.ucsd.edu/projects/universal-detection/.

The problem of data augmentation in feature space is considered. A new architecture, denoted the FeATure TransfEr Network (FATTEN), is proposed for the modeling of feature trajectories induced by variations of object pose. This architecture exploits a parametrization of the pose manifold in terms of pose and appearance. This leads to a deep encoder/decoder network architecture, where the encoder factors into an appearance and a pose predictor. Unlike previous attempts at trajectory transfer, FATTEN can be efficiently trained end-to-end, with no need to train separate feature transfer functions. This is realized by supplying the decoder with information about a target pose and the use of a multi-task loss that penalizes category- and pose-mismatches. In result, FATTEN discourages discontinuous or non-smooth trajectories that fail to capture the structure of the pose manifold, and generalizes well on object recognition tasks involving large pose variation. Experimental results on the artificial ModelNet database show that it can successfully learn to map source features to target features of a desired pose, while preserving class identity. Most notably, by using feature space transfer for data augmentation (w.r.t. pose and depth) on SUN-RGBD objects, we demonstrate considerable performance improvements on one/few-shot object recognition in a transfer learning setup, compared to current state-of-the-art methods.