We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts, which we define as either short noun phrases (e.g., “yellow school bus”), image exemplars, or a combination of both. Promptable Concept Segmentation (PCS) takes such prompts and returns segmentation masks and unique identities for all matching object instances. To advance PCS, we build a scalable data engine that produces a high-quality dataset with 4M unique concept labels, including hard negatives, across images and videos. Our model consists of a vision backbone shared between an image-level detector and a memory-based video tracker. Recognition and localization are decoupled with a presence head, which significantly boosts detection accuracy. SAM 3 delivers a 2x gain over existing systems in both image and video PCS, and improves previous SAM capabilities in interactive visual segmentation tasks. We open source SAM 3 along with our new Segment Anything with Concepts (SA-Co) benchmark.

We present Segment Anything Model 2 (SAM 2), a foundation model towards solving promptable visual segmentation in images and videos. We build a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. Our model is a simple transformer architecture with streaming memory for real-time video processing. SAM 2 trained on our data provides strong performance across a wide range of tasks. In video segmentation, we observe better accuracy, using 3x fewer interactions than prior approaches. In image segmentation, our model is more accurate and 6x faster than the Segment Anything Model (SAM). We believe that our data, model, and insights will serve as a significant milestone for video segmentation and related perception tasks. We are releasing our main model, the dataset, an interactive demo and code.

Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt [33], have demonstrated strong performance in various scenarios. While these models were originally designed for supervised learning with ImageNet labels, they can also potentially benefit from self-supervised learning techniques such as masked autoencoders (MAE) [14]. However, we found that simply combining these two approaches leads to subpar performance. In this paper, we propose a fully convolutional masked autoencoder framework and a new Global Response Normalization (GRN) layer that can be added to the ConvNeXt architecture to enhance inter-channel feature competition. This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets on various recognition benchmarks, including ImageNet classification, COCO detection, and ADE20K segmentation. We also provide pre-trained ConvNeXt V2 models of various sizes, ranging from an efficient 3.7M-parameter Atto model with 76.7% top-1 accuracy on ImageNet, to a 650M Huge model that achieves a state-of-the-art 88.9% accuracy using only public training data.

Performing 3D dense captioning and visual grounding requires a common and shared understanding of the underlying multimodal relationships. However, despite some previous attempts on connecting these two related tasks with highly task-specific neural modules, it remains understudied how to explicitly depict their shared nature to learn them simultaneously. In this work, we propose UniT3D, a simple yet effective fully unified transformer-based architecture for jointly solving 3D visual grounding and dense captioning. UniT3D enables learning a strong multimodal representation across the two tasks through a supervised joint pre-training scheme with bidirectional and seq-to-seq objectives. With a generic architecture design, UniT3D allows expanding the pre-training scope to more various training sources such as the synthesized data from 2D prior knowledge to benefit 3D vision-language tasks. Extensive experiments and analysis demonstrate that UniT3D obtains significant gains for 3D dense captioning and visual grounding.

We present Fast Language-Image Pre-training (FLIP), a simple and more efficient method for training CLIP [52]. Our method randomly masks out and removes a large portion of image patches during training. Masking allows us to learn from more image-text pairs given the same wall-clock time and contrast more samples per iteration with similar memory footprint. It leads to a favorable trade-off between accuracy and training time. In our experiments on 400 million image-text pairs, FLIP improves both accuracy and speed over the no-masking baseline. On a large diversity of downstream tasks, FLIP dominantly outperforms the CLIP counterparts trained on the same data. Facilitated by the speedup, we explore the scaling behavior of increasing the model size, data size, or training length, and report encouraging results and comparisons. We hope that our work will foster future research on scaling vision-language learning.

Masked Autoencoding (MAE) has emerged as an effective approach for pre-training representations across multiple domains. In contrast to discrete tokens in natural languages, the input for image MAE is continuous and subject to additional specifications. We systematically study each input specification during the pre-training stage, and find sequence length is a key axis that further scales MAE. Our study leads to a long-sequence version of MAE with minimal changes to the original recipe, by just decoupling the mask size from the patch size. For object detection and semantic segmentation, our long-sequence MAE shows consistent gains across all the experimental setups without extra computation cost during the transfer. While long-sequence pre-training is discerned most beneficial for detection and segmentation, we also achieve strong results on ImageNet-1K classification by keeping a standard image size and only increasing the sequence length. We hope our findings can provide new insights and avenues for scaling in computer vision.

State-of-the-art vision and vision-and-language models rely on large-scale visio-linguistic pretraining for obtaining good performance on a variety of downstream tasks. Generally, such models are often either cross-modal (contrastive) or multi-modal (with earlier fusion) but not both; and they often only target specific modalities or tasks. A promising direction would be to use a single holistic universal model, as a "foundation", that targets all modalities at once -- a true vision and language foundation model should be good at vision tasks, language tasks, and cross- and multi-modal vision and language tasks. We introduce FLAVA as such a model and demonstrate impressive performance on a wide range of 35 tasks spanning these target modalities.

We propose UniT, a Unified Transformer model to simultaneously learn the most prominent tasks across different domains

We propose UniT, a Unified Transformer model to simultaneously learn the most prominent tasks across different domains, ranging from object detection to natural language understanding and multimodal reasoning. Based on the transformer encoder-decoder architecture, our UniT model encodes each input modality with an encoder and makes predictions on each task with a shared decoder over the encoded input representations, followed by task-specific output heads. The entire model is jointly trained end-to-end with losses from each task. Compared to previous efforts on multi-task learning with transformers, we share the same model parameters across all tasks instead of separately fine-tuning task-specific models and handle a much higher variety of tasks across different domains. In our experiments, we learn 7 tasks jointly over 8 datasets, achieving strong performance on each task with significantly fewer parameters. Our code is available in MMF at https://mmf.sh.

We present Worldsheet, a method for novel view synthesis using just a single RGB image as input. The main insight is that simply shrink-wrapping a planar mesh sheet onto the input image, consistent with the learned intermediate depth, captures underlying geometry sufficient to generate photorealistic unseen views with large viewpoint changes. To operationalize this, we propose a novel differentiable texture sampler that allows our wrapped mesh sheet to be textured and rendered differentiably into an image from a target viewpoint. Our approach is category-agnostic, end-to-end trainable without using any 3D supervision, and requires a single image at test time. We also explore a simple extension by stacking multiple layers of Worldsheets to better handle occlusions. Worldsheet consistently outperforms prior state-of-the-art methods on single-image view synthesis across several datasets. Furthermore, this simple idea captures novel views surprisingly well on a wide range of high-resolution in-the-wild images, converting them into navigable 3D pop-ups. Video results and code are available at https://worldsheet.github.io.

Author(s): Hu, Ronghang | Advisor(s): Darrell, Trevor | Abstract: Vision-and-language tasks (such as answering a question about an image, grounding a referring expression, or following a natural language instruction to navigate through a visual environment) require jointly modeling and reasoning over the two modalities of image and text. We have witnessed significant progress in joint visual and linguistic reasoning, often through neural approaches trained with the help of larger datasets and more computation resources. However, is solving these vision-and-language tasks as simple as building models with more parameters and training them on more data? If not, how can we build better reasoning models that are data-efficient and generalize well?This thesis provides an answer to the above question with structured models for vision-and-language reasoning – models with architectures that take into account the patterns and regularities in human language, visual scenes, and agents’ skills. We begin with the task of referring expression grounding, where we show that significantly better accuracy and generalization can be achieved by taking into account the compositional structures in these expressions with our proposed Compositional Modular Networks (CMNs) in Chapter 2. We further address the visual question answering task in Chapter 3 with the End-to-End Module Networks (N2NMNs) based on dynamic compositional modules that align with the reasoning steps in the questions. In Chapter 4, we extend our work on modular reasoning and propose the Stack Neural Module Networks (SNMNs) that automatically induce a proper module layout with interpretable reasoning steps. Beyond modular reasoning, we also propose to construct context-aware representations of the visual scene with Language-Conditioned Graph Networks (LCGNs) in Chapter 5 for relational reasoning, and address the problem of reading text in images for question answering with iterative pointer-augmented multimodal transformers in Chapter 6. Finally, we show that embodied tasks also require structured models, and propose the Speaker-Follower models for the navigational instruction following task in Chapter 7 with the pair of a speaker model and a follower model that complement each other. In all these scenarios, we show that by taking into account the structures in the tasks and the input modalities, our models perform and generalize significantly better than their unstructured counterparts.

Image descriptions can help visually impaired people to quickly understand the image content. While we made significant progress in automatically describing images and optical character recognition, current approaches are unable to include written text in their descriptions, although text is omnipresent in human environments and frequently critical to understand our surroundings. To study how to comprehend text in the context of an image we collect a novel dataset, TextCaps, with 145k captions for 28k images. Our dataset challenges a model to recognize text, relate it to its visual context, and decide what part of the text to copy or paraphrase, requiring spatial, semantic, and visual reasoning between multiple text tokens and visual entities, such as objects. We study baselines and adapt existing approaches to this new task, which we refer to as image captioning with reading comprehension. Our analysis with automatic and human studies shows that our new TextCaps dataset provides many new technical challenges over previous datasets.

Many visual scenes contain text that carries crucial information, and it is thus essential to understand text in images for downstream reasoning tasks. For example, a deep water label on a warning sign warns people about the danger in the scene. Recent work has explored the TextVQA task that requires reading and understanding text in images to answer a question. However, existing approaches for TextVQA are mostly based on custom pairwise fusion mechanisms between a pair of two modalities and are restricted to a single prediction step by casting TextVQA as a classification task. In this work, we propose a novel model for the TextVQA task based on a multimodal transformer architecture accompanied by a rich representation for text in images. Our model naturally fuses different modalities homogeneously by embedding them into a common semantic space where self-attention is applied to model inter- and intra- modality context. Furthermore, it enables iterative answer decoding with a dynamic pointer network, allowing the model to form an answer through multi-step prediction instead of one-step classification. Our model outperforms existing approaches on three benchmark datasets for the TextVQA task by a large margin.

Vision-and-Language Navigation (VLN) requires grounding instructions, such as "turn right and stop at the door", to routes in a visual environment. The actual grounding can connect language to the environment through multiple modalities, e.g. "stop at the door" might ground into visual objects, while "turn right" might rely only on the geometric structure of a route. We investigate where the natural language empirically grounds under two recent state-of-the-art VLN models. Surprisingly, we discover that visual features may actually hurt these models: models which only use route structure, ablating visual features, outperform their visual counterparts in unseen new environments on the benchmark Room-to-Room dataset. To better use all the available modalities, we propose to decompose the grounding procedure into a set of expert models with access to different modalities (including object detections) and ensemble them at prediction time, improving the performance of state-of-the-art models on the VLN task.

Solving grounded language tasks often requires reasoning about relationships between objects in the context of a given task. For example, to answer the question "What color is the mug on the plate?" we must check the color of the specific mug that satisfies the "on" relationship with respect to the plate. Recent work has proposed various methods capable of complex relational reasoning. However, most of their power is in the inference structure, while the scene is represented with simple local appearance features. In this paper, we take an alternate approach and build contextualized representations for objects in a visual scene to support relational reasoning. We propose a general framework of Language-Conditioned Graph Networks (LCGN), where each node represents an object, and is described by a context-aware representation from related objects through iterative message passing conditioned on the textual input. E.g., conditioning on the "on" relationship to the plate, the object "mug" gathers messages from the object "plate" to update its representation to "mug on the plate", which can be easily consumed by a simple classifier for answer prediction. We experimentally show that our LCGN approach effectively supports relational reasoning and improves performance across several tasks and datasets. Our code is available at http://ronghanghu.com/lcgn.

Natural language explanations of deep neural network decisions provide an intuitive way for a AI agent to articulate a reasoning process. Current textual explanations learn to discuss class discriminative features in an image. However, it is also helpful to understand which attributes might change a classification decision if present in an image (e.g., "This is not a Scarlet Tanager because it does not have black wings.") We call such textual explanations counterfactual explanations, and propose an intuitive method to generate counterfactual explanations by inspecting which evidence in an input is missing, but might contribute to a different classification decision if present in the image. To demonstrate our method we consider a fine-grained image classification task in which we take as input an image and a counterfactual class and output text which explains why the image does not belong to a counterfactual class. We then analyze our generated counterfactual explanations both qualitatively and quantitatively using proposed automatic metrics.

In complex inferential tasks like question answering, machine learning models must confront two challenges: the need to implement a compositional reasoning process, and, in many applications, the need for this reasoning process to be interpretable to assist users in both development and prediction. Existing models designed to produce interpretable traces of their decision-making process typically require these traces to be supervised at training time. In this paper, we present a novel neural modular approach that performs compositional reasoning by automatically inducing a desired sub-task decomposition without relying on strong supervision. Our model allows linking different reasoning tasks though shared modules that handle common routines across tasks. Experiments show that the model is more interpretable to human evaluators compared to other state-of-the-art models: users can better understand the model's underlying reasoning procedure and predict when it will succeed or fail based on observing its intermediate outputs.

Most methods for object instance segmentation require all training examples to be labeled with segmentation masks. This requirement makes it expensive to annotate new categories and has restricted instance segmentation models to ~100 well-annotated classes. The goal of this paper is to propose a new partially supervised training paradigm, together with a novel weight transfer function, that enables training instance segmentation models on a large set of categories all of which have box annotations, but only a small fraction of which have mask annotations. These contributions allow us to train Mask R-CNN to detect and segment 3000 visual concepts using box annotations from the Visual Genome dataset and mask annotations from the 80 classes in the COCO dataset. We evaluate our approach in a controlled study on the COCO dataset. This work is a first step towards instance segmentation models that have broad comprehension of the visual world.

Existing visual explanation generating agents learn to fluently justify a class prediction. However, they may mention visual attributes which reflect a strong class prior, although the evidence may not actually be in the image. This is particularly concerning as ultimately such agents fail in building trust with human users. To overcome this limitation, we propose a phrase-critic model to refine generated candidate explanations augmented with flipped phrases which we use as negative examples while training. At inference time, our phrase-critic model takes an image and a candidate explanation as input and outputs a score indicating how well the candidate explanation is grounded in the image. Our explainable AI agent is capable of providing counter arguments for an alternative prediction, i.e. counterfactuals, along with explanations that justify the correct classification decisions. Our model improves the textual explanation quality of fine-grained classification decisions on the CUB dataset by mentioning phrases that are grounded in the image. Moreover, on the FOIL tasks, our agent detects when there is a mistake in the sentence, grounds the incorrect phrase and corrects it significantly better than other models.

Navigation guided by natural language instructions presents a challenging reasoning problem for instruction followers. Natural language instructions typically identify only a few high-level decisions and landmarks rather than complete low-level motor behaviors; much of the missing information must be inferred based on perceptual context. In machine learning settings, this is doubly challenging: it is difficult to collect enough annotated data to enable learning of this reasoning process from scratch, and also difficult to implement the reasoning process using generic sequence models. Here we describe an approach to vision-and-language navigation that addresses both these issues with an embedded speaker model. We use this speaker model to (1) synthesize new instructions for data augmentation and to (2) implement pragmatic reasoning, which evaluates how well candidate action sequences explain an instruction. Both steps are supported by a panoramic action space that reflects the granularity of human-generated instructions. Experiments show that all three components of this approach---speaker-driven data augmentation, pragmatic reasoning and panoramic action space---dramatically improve the performance of a baseline instruction follower, more than doubling the success rate over the best existing approach on a standard benchmark.