Anna Rohrbach

Sheng Shen, Chunyuan Li, Xiaowei Hu et al. · berkeley, gatech

The new generation of state-of-the-art computer vision systems are trained from natural language supervision, ranging from simple object category names to descriptive captions. This form of supervision ensures high generality and usability of the learned visual models, due to the broad concept coverage achieved via large-scale data collection process. Alternatively, we argue that learning with external knowledge is a promising way which leverages a much more structured source of supervision and offers sample efficiency. We propose K-LITE, a simple strategy to leverage external knowledge for building transferable visual systems: In training, it enriches entities in text with WordNet and Wiktionary knowledge, leading to an efficient and scalable approach to learning image representations that uses knowledge about the visual concepts. In evaluation, the text is also augmented with external knowledge and then used to reference learned visual concepts (or describe new ones) to enable zero-shot and few-shot transfer of the pre-trained models. We study the performance of K-LITE on two important computer vision problems, image classification and object detection, benchmarking on 20 and 13 different existing datasets, respectively. The proposed knowledge-augmented models show significant improvement in transfer learning performance over existing methods. Our code is available at https://github.com/microsoft/klite.

Grace Luo, Giscard Biamby, Trevor Darrell et al. · cmu

We demonstrate how language can improve geolocation: the task of predicting the location where an image was taken. Here we study explicit knowledge from human-written guidebooks that describe the salient and class-discriminative visual features humans use for geolocation. We propose the task of Geolocation via Guidebook Grounding that uses a dataset of StreetView images from a diverse set of locations and an associated textual guidebook for GeoGuessr, a popular interactive geolocation game. Our approach predicts a country for each image by attending over the clues automatically extracted from the guidebook. Supervising attention with country-level pseudo labels achieves the best performance. Our approach substantially outperforms a state-of-the-art image-only geolocation method, with an improvement of over 5% in Top-1 accuracy. Our dataset and code can be found at https://github.com/g-luo/geolocation_via_guidebook_grounding.

Sanjay Subramanian, William Merrill, Trevor Darrell et al. · berkeley

Training a referring expression comprehension (ReC) model for a new visual domain requires collecting referring expressions, and potentially corresponding bounding boxes, for images in the domain. While large-scale pre-trained models are useful for image classification across domains, it remains unclear if they can be applied in a zero-shot manner to more complex tasks like ReC. We present ReCLIP, a simple but strong zero-shot baseline that repurposes CLIP, a state-of-the-art large-scale model, for ReC. Motivated by the close connection between ReC and CLIP's contrastive pre-training objective, the first component of ReCLIP is a region-scoring method that isolates object proposals via cropping and blurring, and passes them to CLIP. However, through controlled experiments on a synthetic dataset, we find that CLIP is largely incapable of performing spatial reasoning off-the-shelf. Thus, the second component of ReCLIP is a spatial relation resolver that handles several types of spatial relations. We reduce the gap between zero-shot baselines from prior work and supervised models by as much as 29% on RefCOCOg, and on RefGTA (video game imagery), ReCLIP's relative improvement over supervised ReC models trained on real images is 8%.

Spencer Whitehead, Suzanne Petryk, Vedaad Shakib et al. · berkeley

Machine learning has advanced dramatically, narrowing the accuracy gap to humans in multimodal tasks like visual question answering (VQA). However, while humans can say "I don't know" when they are uncertain (i.e., abstain from answering a question), such ability has been largely neglected in multimodal research, despite the importance of this problem to the usage of VQA in real settings. In this work, we promote a problem formulation for reliable VQA, where we prefer abstention over providing an incorrect answer. We first enable abstention capabilities for several VQA models, and analyze both their coverage, the portion of questions answered, and risk, the error on that portion. For that, we explore several abstention approaches. We find that although the best performing models achieve over 70% accuracy on the VQA v2 dataset, introducing the option to abstain by directly using a model's softmax scores limits them to answering less than 7.5% of the questions to achieve a low risk of error (i.e., 1%). This motivates us to utilize a multimodal selection function to directly estimate the correctness of the predicted answers, which we show can increase the coverage by, for example, 2.3x from 6.8% to 15.6% at 1% risk. While it is important to analyze both coverage and risk, these metrics have a trade-off which makes comparing VQA models challenging. To address this, we also propose an Effective Reliability metric for VQA that places a larger cost on incorrect answers compared to abstentions. This new problem formulation, metric, and analysis for VQA provide the groundwork for building effective and reliable VQA models that have the self-awareness to abstain if and only if they don't know the answer.

Dong Huk Park, Grace Luo, Clayton Toste et al. · berkeley

We introduce precise object silhouette as a new form of user control in text-to-image diffusion models, which we dub Shape-Guided Diffusion. Our training-free method uses an Inside-Outside Attention mechanism during the inversion and generation process to apply a shape constraint to the cross- and self-attention maps. Our mechanism designates which spatial region is the object (inside) vs. background (outside) then associates edits to the correct region. We demonstrate the efficacy of our method on the shape-guided editing task, where the model must replace an object according to a text prompt and object mask. We curate a new ShapePrompts benchmark derived from MS-COCO and achieve SOTA results in shape faithfulness without a degradation in text alignment or image realism according to both automatic metrics and annotator ratings. Our data and code will be made available at https://shape-guided-diffusion.github.io.

Jun Chen, Ming Hu, Darren J. Coker et al. · mit

Monitoring animal behavior can facilitate conservation efforts by providing key insights into wildlife health, population status, and ecosystem function. Automatic recognition of animals and their behaviors is critical for capitalizing on the large unlabeled datasets generated by modern video devices and for accelerating monitoring efforts at scale. However, the development of automated recognition systems is currently hindered by a lack of appropriately labeled datasets. Existing video datasets 1) do not classify animals according to established biological taxonomies; 2) are too small to facilitate large-scale behavioral studies and are often limited to a single species; and 3) do not feature temporally localized annotations and therefore do not facilitate localization of targeted behaviors within longer video sequences. Thus, we propose MammalNet, a new large-scale animal behavior dataset with taxonomy-guided annotations of mammals and their common behaviors. MammalNet contains over 18K videos totaling 539 hours, which is ~10 times larger than the largest existing animal behavior dataset. It covers 17 orders, 69 families, and 173 mammal categories for animal categorization and captures 12 high-level animal behaviors that received focus in previous animal behavior studies. We establish three benchmarks on MammalNet: standard animal and behavior recognition, compositional low-shot animal and behavior recognition, and behavior detection. Our dataset and code have been made available at: https://mammal-net.github.io.

Jonas Henry Grebe, Tobias Braun, Anna Rohrbach et al.

While the rapid adoption of multimodal generative models offers immense potential, it has also increased the risks of harmful content synthesis, deepfakes, and copyright infringements. To address these challenges, concept erasure has emerged as a prospective safeguard. However, as the field gradually transitions from U-Net-based diffusion models to Rectified Flow Transformers, erasure research has struggled to keep pace. In this work, we introduce GEM, a simple but highly effective erasure framework for Rectified Flow models. As part of our contribution, we establish a principled bridge between trajectory-based unlearning grounded in Generative Flow Networks and classic teacher-guided erasure: we translate trajectory-based signals into a teacher-guided flow-matching setup that unifies the strengths of both paradigms. Concretely, a teacher provides complementary attraction and repulsion signals that we combine into a single geometric guidance objective, yielding targeted suppression of unwanted concepts while preserving benign generation.

Medhini Narasimhan, Arsha Nagrani, Chen Sun et al.

YouTube users looking for instructions for a specific task may spend a long time browsing content trying to find the right video that matches their needs. Creating a visual summary (abridged version of a video) provides viewers with a quick overview and massively reduces search time. In this work, we focus on summarizing instructional videos, an under-explored area of video summarization. In comparison to generic videos, instructional videos can be parsed into semantically meaningful segments that correspond to important steps of the demonstrated task. Existing video summarization datasets rely on manual frame-level annotations, making them subjective and limited in size. To overcome this, we first automatically generate pseudo summaries for a corpus of instructional videos by exploiting two key assumptions: (i) relevant steps are likely to appear in multiple videos of the same task (Task Relevance), and (ii) they are more likely to be described by the demonstrator verbally (Cross-Modal Saliency). We propose an instructional video summarization network that combines a context-aware temporal video encoder and a segment scoring transformer. Using pseudo summaries as weak supervision, our network constructs a visual summary for an instructional video given only video and transcribed speech. To evaluate our model, we collect a high-quality test set, WikiHow Summaries, by scraping WikiHow articles that contain video demonstrations and visual depictions of steps allowing us to obtain the ground-truth summaries. We outperform several baselines and a state-of-the-art video summarization model on this new benchmark.

Elad Ben-Avraham, Roei Herzig, Karttikeya Mangalam et al.

This technical report describes the SViT approach for the Ego4D Point of No Return (PNR) Temporal Localization Challenge. We propose a learning framework StructureViT (SViT for short), which demonstrates how utilizing the structure of a small number of images only available during training can improve a video model. SViT relies on two key insights. First, as both images and videos contain structured information, we enrich a transformer model with a set of \emph{object tokens} that can be used across images and videos. Second, the scene representations of individual frames in video should "align" with those of still images. This is achieved via a "Frame-Clip Consistency" loss, which ensures the flow of structured information between images and videos. SViT obtains strong performance on the challenge test set with 0.656 absolute temporal localization error.

Mingyang Zhou, Grace Luo, Anna Rohrbach et al.

News Image Captioning requires describing an image by leveraging additional context from a news article. Previous works only coarsely leverage the article to extract the necessary context, which makes it challenging for models to identify relevant events and named entities. In our paper, we first demonstrate that by combining more fine-grained context that captures the key named entities (obtained via an oracle) and the global context that summarizes the news, we can dramatically improve the model's ability to generate accurate news captions. This begs the question, how to automatically extract such key entities from an image? We propose to use the pre-trained vision and language retrieval model CLIP to localize the visually grounded entities in the news article and then capture the non-visual entities via an open relation extraction model. Our experiments demonstrate that by simply selecting a better context from the article, we can significantly improve the performance of existing models and achieve new state-of-the-art performance on multiple benchmarks.

Dantong Niu, Amir Bar, Roei Herzig et al.

Existing video-based action recognition systems typically require dense annotation and struggle in environments when there is significant distribution shift relative to the training data. Current methods for video domain adaptation typically fine-tune the model using fully annotated data on a subset of target domain data or align the representation of the two domains using bootstrapping or adversarial learning. Inspired by the pivotal role of objects in recent supervised object-centric action recognition models, we present Object-based (yet Class-agnostic) Video Domain Adaptation (ODAPT), a simple yet effective framework for adapting the existing action recognition systems to new domains by utilizing a sparse set of frames with class-agnostic object annotations in a target domain. Our model achieves a +6.5 increase when adapting across kitchens in Epic-Kitchens and a +3.1 increase adapting between Epic-Kitchens and the EGTEA dataset. ODAPT is a general framework that can also be combined with previous unsupervised methods, offering a +5.0 boost when combined with the self-supervised multi-modal method MMSADA and a +1.7 boost when added to the adversarial-based method TA$^3$N on Epic-Kitchens.

Elad Ben-Avraham, Roei Herzig, Karttikeya Mangalam et al.

Recent action recognition models have achieved impressive results by integrating objects, their locations and interactions. However, obtaining dense structured annotations for each frame is tedious and time-consuming, making these methods expensive to train and less scalable. At the same time, if a small set of annotated images is available, either within or outside the domain of interest, how could we leverage these for a video downstream task? We propose a learning framework StructureViT (SViT for short), which demonstrates how utilizing the structure of a small number of images only available during training can improve a video model. SViT relies on two key insights. First, as both images and videos contain structured information, we enrich a transformer model with a set of \emph{object tokens} that can be used across images and videos. Second, the scene representations of individual frames in video should "align" with those of still images. This is achieved via a \emph{Frame-Clip Consistency} loss, which ensures the flow of structured information between images and videos. We explore a particular instantiation of scene structure, namely a \emph{Hand-Object Graph}, consisting of hands and objects with their locations as nodes, and physical relations of contact/no-contact as edges. SViT shows strong performance improvements on multiple video understanding tasks and datasets. Furthermore, it won in the Ego4D CVPR'22 Object State Localization challenge. For code and pretrained models, visit the project page at \url{https://eladb3.github.io/SViT/}

Nishad Singhi, Hritik Bansal, Arian Hosseini et al.

Scaling test-time compute has emerged as a key strategy for enhancing the reasoning capabilities of large language models (LLMs), particularly in tasks like mathematical problem-solving. A traditional approach, Self-Consistency (SC), generates multiple solutions to a problem and selects the most common answer via majority voting. Another common method involves scoring each solution with a reward model (verifier) and choosing the best one. Recent advancements in Generative Reward Models (GenRM) reframe verification as a next-token prediction task, enabling inference-time scaling along a new axis. Specifically, GenRM generates multiple verification chains-of-thought to score each solution. Under a limited inference budget, this introduces a fundamental trade-off: should you spend the budget on scaling solutions via SC or generate fewer solutions and allocate compute to verification via GenRM? To address this, we evaluate GenRM against SC under a fixed inference budget. Interestingly, we find that SC is more compute-efficient than GenRM for most practical inference budgets across diverse models and datasets. For instance, GenRM first matches SC after consuming up to 8x the inference compute and requires significantly more compute to outperform it. Furthermore, we derive inference scaling laws for the GenRM paradigm, revealing that compute-optimal inference favors scaling solution generation more aggressively than scaling the number of verifications. Our work provides practical guidance on optimizing test-time scaling by balancing solution generation and verification. The code is available at https://github.com/nishadsinghi/sc-genrm-scaling.

Keanu Nichols, Divya Appapogu, Giscard Biamby et al.

Advanced image editing software enables easy creation of highly convincing image manipulations, which has been made even more accessible in recent years due to advances in generative AI. Manipulated images, while often harmless, could spread misinformation, create false narratives, and influence people's opinions on important issues. Despite this growing threat, there is limited research on detecting advanced manipulations across different visual domains. Thus, we introduce Analysis Under Domain-shifts, qualIty, Type, and Size (AUDITS), a comprehensive benchmark designed for studying axes of analysis in image manipulation detection. AUDITS comprises over 530K images from two distinct sources (user and news photos). We curate our dataset to support analysis across multiple axes using recent diffusion-based inpaintings, spanning a diverse range of manipulation types and sizes. We conduct experiments under different types of domain shift to evaluate robustness of existing image manipulation detection methods. Our goal is to drive further research in this area by offering new insights that would help develop more reliable and generalizable image manipulation detection methods.

Tobias Braun, Jonas Henry Grebe, Hossein Shakibania et al.

Unified autoregressive models (UAMs) are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared parameters and a multimodal vocabulary simplify the training pipeline and facilitate flexible multimodal generation, yet might introduce new vulnerabilities. In particular, we are the first to show that this unified architecture enables multimodal backdoor attacks, where a trigger can propagate malicious effects across multiple output modalities. Specifically, we present the Token by Token Backdoor Attack (ToBAC), the first backdoor attack targeting UAMs, exploring both data-based and model-based poisoning strategies. We demonstrate that innocuous characters or even common words can be transformed into triggers that elicit harmful behavior in autoregressive image generation. ToBAC can jointly manipulate visual outputs and accompanying text, increasing the perceived authenticity of fabricated content. With model access, ToBAC enables attacks on the unified Liquid model in which a subtle word (e.g., ``cool'') induces modality-aligned brand promotion or ideological influence in 55% of generations. Without model access, ToBAC can be induced through data poisoning, achieving an average success rate of 63.1% against JanusPro.

Aritra Marik, Marcel Klemt, Anna Rohrbach

With every advancement in generative AI models, forensics is under increasing pressure. The constant emergence of new generation techniques makes it impossible to collect data for each manipulation to train a deepfake detection model. Thus, generalizing to deepfakes unseen during training is one of the major challenges in current deepfake detection research. To tackle this challenge, we employ high-level semantic cues and argue that these cues can support low-level focused approaches in generalizing to unseen types of manipulations. In this work, we study emotions as a high-level semantic cue. We propose Emo-Boost, a multimodal deepfake detection framework that fuses an off-the-shelf RGB- and acoustic-focused deepfake detector with our emotion-based deepfake detector EmoForensics. EmoForensics utilises vision and audio emotion recognition modules and models intra- and inter-modal temporal consistency in emotion representations from an audio-visual stream. We found that EmoForensics and the low-level focused method capture complementary signals. Consequently, combining both signals in EmoBoost enhances the average cross-manipulation generalization AUC by 2.1% on FakeAVCeleb.

Yujin Jeong, Arnas Uselis, Seong Joon Oh et al.

Understanding visual scenes is fundamental to human intelligence. While discriminative models have significantly advanced computer vision, they often struggle with compositional understanding. In contrast, recent generative text-to-image diffusion models excel at synthesizing complex scenes, suggesting inherent compositional capabilities. Building on this, zero-shot diffusion classifiers have been proposed to repurpose diffusion models for discriminative tasks. While prior work offered promising results in discriminative compositional scenarios, these results remain preliminary due to a small number of benchmarks and a relatively shallow analysis of conditions under which the models succeed. To address this, we present a comprehensive study of the discriminative capabilities of diffusion classifiers on a wide range of compositional tasks. Specifically, our study covers three diffusion models (SD 1.5, 2.0, and, for the first time, 3-m) spanning 10 datasets and over 30 tasks. Further, we shed light on the role that target dataset domains play in respective performance; to isolate the domain effects, we introduce a new diagnostic benchmark \textsc{Self-Bench} comprised of images created by diffusion models themselves. Finally, we explore the importance of timestep weighting and uncover a relationship between domain gap and timestep sensitivity, particularly for SD3-m. To sum up, diffusion classifiers understand compositionality, but conditions apply! Code and dataset are available at https://github.com/eugene6923/Diffusion-Classifiers-Compositionality.

Nishad Singhi, Christian Bialas, Snehal Jauhri et al.

Building generalist embodied agents capable of solving complex real-world tasks remains a fundamental challenge in AI. Multimodal Large Language Models (MLLMs) have significantly advanced the reasoning capabilities of such agents through strong vision-language knowledge and chain-of-thought (CoT) reasoning, yet remain brittle when faced with challenging out-of-distribution scenarios. To address this, we propose Verifier-Guided Action Selection (VegAS), a test-time framework designed to improve the robustness of MLLM-based embodied agents through an explicit verification step. At inference time, rather than committing to a single decoded action, VeGAS samples an ensemble of candidate actions and uses a generative verifier to identify the most reliable choice, without modifying the underlying policy. Crucially, we find that using an MLLM off-the-shelf as a verifier yields no improvement, motivating our LLM-driven data synthesis strategy, which automatically constructs a diverse curriculum of failure cases to expose the verifier to a rich distribution of potential errors at training time. Across embodied reasoning benchmarks spanning the Habitat and ALFRED environments, VeGAS consistently improves generalization, achieving up to a 36% relative performance gain over strong CoT baselines on the most challenging multi-object, long-horizon tasks.

Mark Rothermel, Marcus Kornmann, Marcus Rohrbach et al.

The growing scale of online misinformation urgently demands Automated Fact-Checking (AFC). Existing benchmarks for evaluating AFC systems, however, are largely limited in terms of task scope, modalities, domain, language diversity, realism, or coverage of misinformation types. Critically, they are static, thus subject to data leakage as their claims enter the pretraining corpora of LLMs. As a result, benchmark performance no longer reliably reflects the actual ability to verify claims. We introduce Verified Theses and Statements (VeriTaS), the first dynamic benchmark for multimodal AFC, designed to remain robust under ongoing large-scale pretraining of foundation models. VeriTaS currently comprises 24,000 real-world claims from 108 professional fact-checking organizations across 54 languages, covering textual and audiovisual content. Claims are added quarterly via a fully automated seven-stage pipeline that normalizes claim formulation, retrieves original media, and maps heterogeneous expert verdicts to a novel, standardized, and disentangled scoring scheme with textual justifications. Through human evaluation, we demonstrate that the automated annotations closely match human judgments. We commit to update VeriTaS in the future, establishing a leakage-resistant benchmark, supporting meaningful AFC evaluation in the era of rapidly evolving foundation models. We will make the code and data publicly available.

Ziyuan Chen, Yujin Jeong, Tobias Braun et al.

As text-to-image diffusion models become increasingly deployed in real-world applications, concerns about backdoor attacks have gained significant attention. Prior work on text-based backdoor attacks has largely focused on diffusion models conditioned on a single lightweight text encoder. However, more recent diffusion models that incorporate multiple large-scale text encoders remain underexplored in this context. Given the substantially increased number of trainable parameters introduced by multiple text encoders, an important question is whether backdoor attacks can remain both efficient and effective in such settings. In this work, we study Stable Diffusion 3, which uses three distinct text encoders and has not yet been systematically analyzed for text-encoder-based backdoor vulnerabilities. To understand the role of text encoders in backdoor attacks, we define four categories of attack targets and identify the minimal sets of encoders required to achieve effective performance for each attack objective. Based on this, we further propose Multi-Encoder Lightweight aTtacks (MELT), which trains only low-rank adapters while keeping the pretrained text encoder weight frozen. We demonstrate that tuning fewer than 0.2% of the total encoder parameters is sufficient for successful backdoor attacks on Stable Diffusion 3, revealing previously underexplored vulnerabilities in practical attack scenarios in multi-encoder settings.

Sheng Shen, Liunian Harold Li, Hao Tan et al.

Most existing Vision-and-Language (V&L) models rely on pre-trained visual encoders, using a relatively small set of manually-annotated data (as compared to web-crawled data), to perceive the visual world. However, it has been observed that large-scale pretraining usually can result in better generalization performance, e.g., CLIP (Contrastive Language-Image Pre-training), trained on a massive amount of image-caption pairs, has shown a strong zero-shot capability on various vision tasks. To further study the advantage brought by CLIP, we propose to use CLIP as the visual encoder in various V&L models in two typical scenarios: 1) plugging CLIP into task-specific fine-tuning; 2) combining CLIP with V&L pre-training and transferring to downstream tasks. We show that CLIP significantly outperforms widely-used visual encoders trained with in-domain annotated data, such as BottomUp-TopDown. We achieve competitive or better results on diverse V&L tasks, while establishing new state-of-the-art results on Visual Question Answering, Visual Entailment, and V&L Navigation tasks. We release our code at https://github.com/clip-vil/CLIP-ViL.

Ronghang Hu, Anna Rohrbach, Trevor Darrell et al.

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.

Jinkyu Kim, Anna Rohrbach, Trevor Darrell et al.

Deep neural perception and control networks have become key components of self-driving vehicles. User acceptance is likely to benefit from easy-to-interpret textual explanations which allow end-users to understand what triggered a particular behavior. Explanations may be triggered by the neural controller, namely introspective explanations, or informed by the neural controller's output, namely rationalizations. We propose a new approach to introspective explanations which consists of two parts. First, we use a visual (spatial) attention model to train a convolutional network end-to-end from images to the vehicle control commands, i.e., acceleration and change of course. The controller's attention identifies image regions that potentially influence the network's output. Second, we use an attention-based video-to-text model to produce textual explanations of model actions. The attention maps of controller and explanation model are aligned so that explanations are grounded in the parts of the scene that mattered to the controller. We explore two approaches to attention alignment, strong- and weak-alignment. Finally, we explore a version of our model that generates rationalizations, and compare with introspective explanations on the same video segments. We evaluate these models on a novel driving dataset with ground-truth human explanations, the Berkeley DeepDrive eXplanation (BDD-X) dataset. Code is available at https://github.com/JinkyuKimUCB/explainable-deep-driving.

Yujin Jeong, Arnas Uselis, Iro Laina et al.

Text-to-image diffusion models achieve impressive visual fidelity, yet they remain unreliable in multi-object generation. Despite extensive empirical evidence of these failures, the underlying causes remain unclear. We begin by asking how much of this limitation arises from the data itself. To disentangle data effects, we consider two regimes across different dataset sizes: (1) concept generalization, where each individual concept is observed during training under potentially imbalanced data distributions, and (2) compositional generalization, where specific combinations of concepts are systematically held out. To study these regimes, we introduce mosaic (Multi-Object Spatial relations, AttrIbution, Counting), a controlled framework for dataset generation. By training diffusion models on mosaic, we find that scene complexity plays a dominant role rather than concept imbalance, and that counting is uniquely difficult to learn in low-data regimes. Moreover, compositional generalization collapses as more concept combinations are held out during training. These findings highlight fundamental limitations of diffusion models and motivate stronger inductive biases and data design for robust multi-object compositional generation.

Tobias Braun, Mark Rothermel, Marcus Rohrbach et al.

The proliferation of disinformation demands reliable and scalable fact-checking solutions. We present Dynamic Evidence-based FAct-checking with Multimodal Experts (DEFAME), a modular, zero-shot MLLM pipeline for open-domain, text-image claim verification. DEFAME operates in a six-stage process, dynamically selecting the tools and search depth to extract and evaluate textual and visual evidence. Unlike prior approaches that are text-only, lack explainability, or rely solely on parametric knowledge, DEFAME performs end-to-end verification, accounting for images in claims and evidence while generating structured, multimodal reports. Evaluation on the popular benchmarks VERITE, AVerITeC, and MOCHEG shows that DEFAME surpasses all previous methods, establishing itself as the new state-of-the-art fact-checking system for uni- and multimodal fact-checking. Moreover, we introduce a new multimodal benchmark, ClaimReview2024+, featuring claims after the knowledge cutoff of GPT-4o, avoiding data leakage. Here, DEFAME drastically outperforms the GPT-4o baselines, showing temporal generalizability and the potential for real-time fact-checking.

Jonas Henry Grebe, Tobias Braun, Marcus Rohrbach et al.

The expansion of large-scale text-to-image diffusion models has raised growing concerns about their potential to generate undesirable or harmful content, ranging from fabricated depictions of public figures to sexually explicit images. To mitigate these risks, prior work has devised machine unlearning techniques that attempt to erase unwanted concepts through fine-tuning. However, in this paper, we introduce a new threat model, Toxic Erasure (ToxE), and demonstrate how recent unlearning algorithms, including those explicitly designed for robustness, can be circumvented through targeted backdoor attacks. The threat is realized by establishing a link between a trigger and the undesired content. Subsequent unlearning attempts fail to erase this link, allowing adversaries to produce harmful content. We instantiate ToxE via two established backdoor attacks: one targeting the text encoder and another manipulating the cross-attention layers. Further, we introduce Deep Intervention Score-based Attack (DISA), a novel, deeper backdoor attack that optimizes the entire U-Net using a score-based objective, improving the attack's persistence across different erasure methods. We evaluate five recent concept erasure methods against our threat model. For celebrity identity erasure, our deep attack circumvents erasure with up to 82% success, averaging 57% across all erasure methods. For explicit content erasure, ToxE attacks can elicit up to 9 times more exposed body parts, with DISA yielding an average increase by a factor of 2.9. These results highlight a critical security gap in current unlearning strategies.

Reihaneh Zohrabi, Hosein Hasani, Akshita Gupta et al.

Large vision-language models can produce object hallucinations in image descriptions, highlighting the need for effective detection and mitigation strategies. Prior work commonly relies on the model's attention weights on visual tokens as a detection signal. We reveal that coarse-grained attention-based analysis is unreliable due to hidden confounders, specifically token position and object repetition in a description. This leads to Simpson's paradox: the attention trends reverse or disappear when statistics are aggregated. Based on this observation, we introduce HaloProbe, a Bayesian framework that factorizes external description statistics and internal decoding signals to estimate token-level hallucination probabilities. HaloProbe uses balanced training to isolate internal evidence and combines it with learned prior over external features to recover the true posterior. While intervention-based mitigation methods often degrade utility or fluency by modifying models' internals, we use HaloProbe as an external scoring signal for non-invasive mitigation. Our experiments show that HaloProbe-guided decoding reduces hallucinations more effectively than state-of-the-art intervention-based methods while preserving utility.

Reihaneh Zohrabi, Hosein Hasani, Mahdieh Soleymani Baghshah et al.

Out-of-distribution (OOD) detection is crucial for ensuring the reliability and safety of machine learning models in real-world applications, where they frequently face data distributions unseen during training. Despite progress, existing methods are often vulnerable to spurious correlations that mislead models and compromise robustness. To address this, we propose SPROD, a novel prototype-based OOD detection approach that explicitly addresses the challenge posed by unknown spurious correlations. Our post-hoc method refines class prototypes to mitigate bias from spurious features without additional data or hyperparameter tuning, and is broadly applicable across diverse backbones and OOD detection settings. We conduct a comprehensive spurious correlation OOD detection benchmarking, comparing our method against existing approaches and demonstrating its superior performance across challenging OOD datasets, such as CelebA, Waterbirds, UrbanCars, Spurious Imagenet, and the newly introduced Animals MetaCoCo. On average, SPROD improves AUROC by 4.8% and FPR@95 by 9.4% over the second best.

Adnen Abdessaied, Anna Rohrbach, Marcus Rohrbach et al.

We present V$^2$Dial - a novel expert-based model specifically geared towards simultaneously handling image and video input data for multimodal conversational tasks. Current multimodal models primarily focus on simpler tasks (e.g., VQA, VideoQA, video-text retrieval) and often neglect the more challenging conversational counterparts, such as video and visual/image dialog. Moreover, works on both conversational tasks evolved separately from each other despite their apparent similarities limiting their applicability potential. To this end, we propose to unify both tasks using a single model that for the first time jointly learns the spatial and temporal features of images and videos by routing them through dedicated experts and aligns them using matching and contrastive learning techniques. Furthermore, we systemically study the domain shift between the two tasks by investigating whether and to what extent these seemingly related tasks can mutually benefit from their respective training data. Extensive evaluations on the widely used video and visual dialog datasets of AVSD and VisDial show that our model achieves new state-of-the-art results across four benchmarks both in zero-shot and fine-tuning settings.

Hector Rodriguez, Boris Meinardus, Anil Batra et al.

The recent success of Large Language Models (LLMs) has prompted the extension to the multimodal domain, developing image-text Multimodal LLMs (MLLMs) and then video-text models. In this work, we investigate the challenge of contextual and temporal comprehension in video-language models by exploring the task of temporal localization in videos. To address this problem, prior works have developed complex task-specific architectures, novel modules to embed time into MLLMs, or leveraged additional input signals such as video transcripts to best encode contextual and temporal information. We find that most of these efforts are surpassed by a much simpler design. We introduce Chrono, a universal sequence blueprint that can be applied to any image-text pretrained MLLM. In extensive experiments spanning different MLLM architectures and sizes, finetuning and zero-shot settings, we demonstrate new state-of-the-art results in moment retrieval on the widely used benchmarks Charades-STA, QVHighlights, and ActivityNet Captions, as well as in grounded video question answering on NExT-GQA.

Suzanne Petryk, Spencer Whitehead, Joseph E. Gonzalez et al.

The ability to judge whether a caption correctly describes an image is a critical part of vision-language understanding. However, state-of-the-art models often misinterpret the correctness of fine-grained details, leading to errors in outputs such as hallucinating objects in generated captions or poor compositional reasoning. In this work, we explore Token-Level Confidence, or TLC, as a simple yet surprisingly effective method to assess caption correctness. Specifically, we fine-tune a vision-language model on image captioning, input an image and proposed caption to the model, and aggregate either algebraic or learned token confidences over words or sequences to estimate image-caption consistency. Compared to sequence-level scores from pretrained models, TLC with algebraic confidence measures achieves a relative improvement in accuracy by 10% on verb understanding in SVO-Probes and outperforms prior state-of-the-art in image and group scores for compositional reasoning in Winoground by a relative 37% and 9%, respectively. When training data are available, a learned confidence estimator provides further improved performance, reducing object hallucination rates in MS COCO Captions by a relative 30% over the original model and setting a new state-of-the-art.

Suzanne Petryk, Lisa Dunlap, Keyan Nasseri et al.

While real world challenges typically define visual categories with language words or phrases, most visual classification methods define categories with numerical indices. However, the language specification of the classes provides an especially useful prior for biased and noisy datasets, where it can help disambiguate what features are task-relevant. Recently, large-scale multimodal models have been shown to recognize a wide variety of high-level concepts from a language specification even without additional image training data, but they are often unable to distinguish classes for more fine-grained tasks. CNNs, in contrast, can extract subtle image features that are required for fine-grained discrimination, but will overfit to any bias or noise in datasets. Our insight is to use high-level language specification as advice for constraining the classification evidence to task-relevant features, instead of distractors. To do this, we ground task-relevant words or phrases with attention maps from a pretrained large-scale model. We then use this grounding to supervise a classifier's spatial attention away from distracting context. We show that supervising spatial attention in this way improves performance on classification tasks with biased and noisy data, including about 3-15% worst-group accuracy improvements and 41-45% relative improvements on fairness metrics.

Jack Hessel, Jena D. Hwang, Jae Sung Park et al.

Humans have remarkable capacity to reason abductively and hypothesize about what lies beyond the literal content of an image. By identifying concrete visual clues scattered throughout a scene, we almost can't help but draw probable inferences beyond the literal scene based on our everyday experience and knowledge about the world. For example, if we see a "20 mph" sign alongside a road, we might assume the street sits in a residential area (rather than on a highway), even if no houses are pictured. Can machines perform similar visual reasoning? We present Sherlock, an annotated corpus of 103K images for testing machine capacity for abductive reasoning beyond literal image contents. We adopt a free-viewing paradigm: participants first observe and identify salient clues within images (e.g., objects, actions) and then provide a plausible inference about the scene, given the clue. In total, we collect 363K (clue, inference) pairs, which form a first-of-its-kind abductive visual reasoning dataset. Using our corpus, we test three complementary axes of abductive reasoning. We evaluate the capacity of models to: i) retrieve relevant inferences from a large candidate corpus; ii) localize evidence for inferences via bounding boxes, and iii) compare plausible inferences to match human judgments on a newly-collected diagnostic corpus of 19K Likert-scale judgments. While we find that fine-tuning CLIP-RN50x64 with a multitask objective outperforms strong baselines, significant headroom exists between model performance and human agreement. Data, models, and leaderboard available at http://visualabduction.com/

Shruti Agarwal, Liwen Hu, Evonne Ng et al.

In today's era of digital misinformation, we are increasingly faced with new threats posed by video falsification techniques. Such falsifications range from cheapfakes (e.g., lookalikes or audio dubbing) to deepfakes (e.g., sophisticated AI media synthesis methods), which are becoming perceptually indistinguishable from real videos. To tackle this challenge, we propose a multi-modal semantic forensic approach to discover clues that go beyond detecting discrepancies in visual quality, thereby handling both simpler cheapfakes and visually persuasive deepfakes. In this work, our goal is to verify that the purported person seen in the video is indeed themselves by detecting anomalous facial movements corresponding to the spoken words. We leverage the idea of attribution to learn person-specific biometric patterns that distinguish a given speaker from others. We use interpretable Action Units (AUs) to capture a person's face and head movement as opposed to deep CNN features, and we are the first to use word-conditioned facial motion analysis. We further demonstrate our method's effectiveness on a range of fakes not seen in training including those without video manipulation, that were not addressed in prior work.

Giscard Biamby, Grace Luo, Trevor Darrell et al.

Detecting out-of-context media, such as "mis-captioned" images on Twitter, is a relevant problem, especially in domains of high public significance. In this work we aim to develop defenses against such misinformation for the topics of Climate Change, COVID-19, and Military Vehicles. We first present a large-scale multimodal dataset with over 884k tweets relevant to these topics. Next, we propose a detection method, based on the state-of-the-art CLIP model, that leverages automatically generated hard image-text mismatches. While this approach works well on our automatically constructed out-of-context tweets, we aim to validate its usefulness on data representative of the real world. Thus, we test it on a set of human-generated fakes created by mimicking in-the-wild misinformation. We achieve an 11% detection improvement in a high precision regime over a strong baseline. Finally, we share insights about our best model design and analyze the challenges of this emerging threat.

Xihui Liu, Dong Huk Park, Samaneh Azadi et al.

Controllable image synthesis models allow creation of diverse images based on text instructions or guidance from a reference image. Recently, denoising diffusion probabilistic models have been shown to generate more realistic imagery than prior methods, and have been successfully demonstrated in unconditional and class-conditional settings. We investigate fine-grained, continuous control of this model class, and introduce a novel unified framework for semantic diffusion guidance, which allows either language or image guidance, or both. Guidance is injected into a pretrained unconditional diffusion model using the gradient of image-text or image matching scores, without re-training the diffusion model. We explore CLIP-based language guidance as well as both content and style-based image guidance in a unified framework. Our text-guided synthesis approach can be applied to datasets without associated text annotations. We conduct experiments on FFHQ and LSUN datasets, and show results on fine-grained text-guided image synthesis, synthesis of images related to a style or content reference image, and examples with both textual and image guidance.

Roei Herzig, Elad Ben-Avraham, Karttikeya Mangalam et al.

Recently, video transformers have shown great success in video understanding, exceeding CNN performance; yet existing video transformer models do not explicitly model objects, although objects can be essential for recognizing actions. In this work, we present Object-Region Video Transformers (ORViT), an \emph{object-centric} approach that extends video transformer layers with a block that directly incorporates object representations. The key idea is to fuse object-centric representations starting from early layers and propagate them into the transformer-layers, thus affecting the spatio-temporal representations throughout the network. Our ORViT block consists of two object-level streams: appearance and dynamics. In the appearance stream, an "Object-Region Attention" module applies self-attention over the patches and \emph{object regions}. In this way, visual object regions interact with uniform patch tokens and enrich them with contextualized object information. We further model object dynamics via a separate "Object-Dynamics Module", which captures trajectory interactions, and show how to integrate the two streams. We evaluate our model on four tasks and five datasets: compositional and few-shot action recognition on SomethingElse, spatio-temporal action detection on AVA, and standard action recognition on Something-Something V2, Diving48 and Epic-Kitchen100. We show strong performance improvement across all tasks and datasets considered, demonstrating the value of a model that incorporates object representations into a transformer architecture. For code and pretrained models, visit the project page at \url{https://roeiherz.github.io/ORViT/}

Medhini Narasimhan, Anna Rohrbach, Trevor Darrell

A generic video summary is an abridged version of a video that conveys the whole story and features the most important scenes. Yet the importance of scenes in a video is often subjective, and users should have the option of customizing the summary by using natural language to specify what is important to them. Further, existing models for fully automatic generic summarization have not exploited available language models, which can serve as an effective prior for saliency. This work introduces CLIP-It, a single framework for addressing both generic and query-focused video summarization, typically approached separately in the literature. We propose a language-guided multimodal transformer that learns to score frames in a video based on their importance relative to one another and their correlation with a user-defined query (for query-focused summarization) or an automatically generated dense video caption (for generic video summarization). Our model can be extended to the unsupervised setting by training without ground-truth supervision. We outperform baselines and prior work by a significant margin on both standard video summarization datasets (TVSum and SumMe) and a query-focused video summarization dataset (QFVS). Particularly, we achieve large improvements in the transfer setting, attesting to our method's strong generalization capabilities.

Amir Bar, Xin Wang, Vadim Kantorov et al.

Recent self-supervised pretraining methods for object detection largely focus on pretraining the backbone of the object detector, neglecting key parts of detection architecture. Instead, we introduce DETReg, a new self-supervised method that pretrains the entire object detection network, including the object localization and embedding components. During pretraining, DETReg predicts object localizations to match the localizations from an unsupervised region proposal generator and simultaneously aligns the corresponding feature embeddings with embeddings from a self-supervised image encoder. We implement DETReg using the DETR family of detectors and show that it improves over competitive baselines when finetuned on COCO, PASCAL VOC, and Airbus Ship benchmarks. In low-data regimes DETReg achieves improved performance, e.g., when training with only 1% of the labels and in the few-shot learning settings.

Grace Luo, Trevor Darrell, Anna Rohrbach

Online misinformation is a prevalent societal issue, with adversaries relying on tools ranging from cheap fakes to sophisticated deep fakes. We are motivated by the threat scenario where an image is used out of context to support a certain narrative. While some prior datasets for detecting image-text inconsistency generate samples via text manipulation, we propose a dataset where both image and text are unmanipulated but mismatched. We introduce several strategies for automatically retrieving convincing images for a given caption, capturing cases with inconsistent entities or semantic context. Our large-scale automatically generated NewsCLIPpings Dataset: (1) demonstrates that machine-driven image repurposing is now a realistic threat, and (2) provides samples that represent challenging instances of mismatch between text and image in news that are able to mislead humans. We benchmark several state-of-the-art multimodal models on our dataset and analyze their performance across different pretraining domains and visual backbones.

Jae Sung Park, Trevor Darrell, Anna Rohrbach

Standard video and movie description tasks abstract away from person identities, thus failing to link identities across sentences. We propose a multi-sentence Identity-Aware Video Description task, which overcomes this limitation and requires to re-identify persons locally within a set of consecutive clips. We introduce an auxiliary task of Fill-in the Identity, that aims to predict persons' IDs consistently within a set of clips, when the video descriptions are given. Our proposed approach to this task leverages a Transformer architecture allowing for coherent joint prediction of multiple IDs. One of the key components is a gender-aware textual representation as well an additional gender prediction objective in the main model. This auxiliary task allows us to propose a two-stage approach to Identity-Aware Video Description. We first generate multi-sentence video descriptions, and then apply our Fill-in the Identity model to establish links between the predicted person entities. To be able to tackle both tasks, we augment the Large Scale Movie Description Challenge (LSMDC) benchmark with new annotations suited for our problem statement. Experiments show that our proposed Fill-in the Identity model is superior to several baselines and recent works, and allows us to generate descriptions with locally re-identified people.

Amir Bar, Roei Herzig, Xiaolong Wang et al.

Videos of actions are complex signals containing rich compositional structure in space and time. Current video generation methods lack the ability to condition the generation on multiple coordinated and potentially simultaneous timed actions. To address this challenge, we propose to represent the actions in a graph structure called Action Graph and present the new ``Action Graph To Video'' synthesis task. Our generative model for this task (AG2Vid) disentangles motion and appearance features, and by incorporating a scheduling mechanism for actions facilitates a timely and coordinated video generation. We train and evaluate AG2Vid on the CATER and Something-Something V2 datasets, and show that the resulting videos have better visual quality and semantic consistency compared to baselines. Finally, our model demonstrates zero-shot abilities by synthesizing novel compositions of the learned actions. For code and pretrained models, see the project page https://roeiherz.github.io/AG2Video

Ronghang Hu, Daniel Fried, Anna Rohrbach et al.

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.

Dong Huk Park, Trevor Darrell, Anna Rohrbach

Describing what has changed in a scene can be useful to a user, but only if generated text focuses on what is semantically relevant. It is thus important to distinguish distractors (e.g. a viewpoint change) from relevant changes (e.g. an object has moved). We present a novel Dual Dynamic Attention Model (DUDA) to perform robust Change Captioning. Our model learns to distinguish distractors from semantic changes, localize the changes via Dual Attention over "before" and "after" images, and accurately describe them in natural language via Dynamic Speaker, by adaptively focusing on the necessary visual inputs (e.g. "before" or "after" image). To study the problem in depth, we collect a CLEVR-Change dataset, built off the CLEVR engine, with 5 types of scene changes. We benchmark a number of baselines on our dataset, and systematically study different change types and robustness to distractors. We show the superiority of our DUDA model in terms of both change captioning and localization. We also show that our approach is general, obtaining state-of-the-art results on the recent realistic Spot-the-Diff dataset which has no distractors.

Jae Sung Park, Marcus Rohrbach, Trevor Darrell et al.

While significant progress has been made in the image captioning task, video description is still in its infancy due to the complex nature of video data. Generating multi-sentence descriptions for long videos is even more challenging. Among the main issues are the fluency and coherence of the generated descriptions, and their relevance to the video. Recently, reinforcement and adversarial learning based methods have been explored to improve the image captioning models; however, both types of methods suffer from a number of issues, e.g. poor readability and high redundancy for RL and stability issues for GANs. In this work, we instead propose to apply adversarial techniques during inference, designing a discriminator which encourages better multi-sentence video description. In addition, we find that a multi-discriminator "hybrid" design, where each discriminator targets one aspect of a description, leads to the best results. Specifically, we decouple the discriminator to evaluate on three criteria: 1) visual relevance to the video, 2) language diversity and fluency, and 3) coherence across sentences. Our approach results in more accurate, diverse, and coherent multi-sentence video descriptions, as shown by automatic as well as human evaluation on the popular ActivityNet Captions dataset.

Anna Rohrbach, Lisa Anne Hendricks, Kaylee Burns et al.

Despite continuously improving performance, contemporary image captioning models are prone to "hallucinating" objects that are not actually in a scene. One problem is that standard metrics only measure similarity to ground truth captions and may not fully capture image relevance. In this work, we propose a new image relevance metric to evaluate current models with veridical visual labels and assess their rate of object hallucination. We analyze how captioning model architectures and learning objectives contribute to object hallucination, explore when hallucination is likely due to image misclassification or language priors, and assess how well current sentence metrics capture object hallucination. We investigate these questions on the standard image captioning benchmark, MSCOCO, using a diverse set of models. Our analysis yields several interesting findings, including that models which score best on standard sentence metrics do not always have lower hallucination and that models which hallucinate more tend to make errors driven by language priors.

Lisa Anne Hendricks, Kaylee Burns, Kate Saenko et al.

Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in training data. This can lead to incorrect captions in domains where unbiased captions are desired, or required, due to over reliance on the learned prior and image context. We investigate generation of gender specific caption words (e.g. man, woman) based on the person's appearance or the image context. We introduce a new Equalizer model that ensures equal gender probability when gender evidence is occluded in a scene and confident predictions when gender evidence is present. The resulting model is forced to look at a person rather than use contextual cues to make a gender specific prediction. The losses that comprise our model, the Appearance Confusion Loss and the Confident Loss, are general, and can be added to any description model in order to mitigate impacts of unwanted bias in a description dataset. Our proposed model has lower error than prior work when describing images with people and mentioning their gender and more closely matches the ground truth ratio of sentences including women to sentences including men.

Daniel Fried, Ronghang Hu, Volkan Cirik et al.

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.

Kaylee Burns, Lisa Anne Hendricks, Kate Saenko et al.

Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in training data (e.g., if a word is present in 60% of training sentences, it might be predicted in 70% of sentences at test time). This can lead to incorrect captions in domains where unbiased captions are desired, or required, due to over-reliance on the learned prior and image context. In this work we investigate generation of gender-specific caption words (e.g. man, woman) based on the person's appearance or the image context. We introduce a new Equalizer model that ensures equal gender probability when gender evidence is occluded in a scene and confident predictions when gender evidence is present. The resulting model is forced to look at a person rather than use contextual cues to make a gender-specific predictions. The losses that comprise our model, the Appearance Confusion Loss and the Confident Loss, are general, and can be added to any description model in order to mitigate impacts of unwanted bias in a description dataset. Our proposed model has lower error than prior work when describing images with people and mentioning their gender and more closely matches the ground truth ratio of sentences including women to sentences including men. We also show that unlike other approaches, our model is indeed more often looking at people when predicting their gender.

Anna Khoreva, Anna Rohrbach, Bernt Schiele

Most state-of-the-art semi-supervised video object segmentation methods rely on a pixel-accurate mask of a target object provided for the first frame of a video. However, obtaining a detailed segmentation mask is expensive and time-consuming. In this work we explore an alternative way of identifying a target object, namely by employing language referring expressions. Besides being a more practical and natural way of pointing out a target object, using language specifications can help to avoid drift as well as make the system more robust to complex dynamics and appearance variations. Leveraging recent advances of language grounding models designed for images, we propose an approach to extend them to video data, ensuring temporally coherent predictions. To evaluate our method we augment the popular video object segmentation benchmarks, DAVIS'16 and DAVIS'17 with language descriptions of target objects. We show that our language-supervised approach performs on par with the methods which have access to a pixel-level mask of the target object on DAVIS'16 and is competitive to methods using scribbles on the challenging DAVIS'17 dataset.