Vision-Language Models (VLMs) have shown promise in various 2D visual tasks, yet their readiness for 3D clinical diagnosis remains unclear due to stringent demands for recognition precision, reasoning ability, and domain knowledge. To systematically evaluate these dimensions, we present DeepTumorVQA, a diagnostic visual question answering (VQA) benchmark targeting abdominal tumors in CT scans. It comprises 9,262 CT volumes (3.7M slices) from 17 public datasets, with 395K expert-level questions spanning four categories: Recognition, Measurement, Visual Reasoning, and Medical Reasoning. DeepTumorVQA introduces unique challenges, including small tumor detection and clinical reasoning across 3D anatomy. Benchmarking four advanced VLMs (RadFM, M3D, Merlin, CT-CHAT), we find current models perform adequately on measurement tasks but struggle with lesion recognition and reasoning, and are still not meeting clinical needs. Two key insights emerge: (1) large-scale multimodal pretraining plays a crucial role in DeepTumorVQA testing performance, making RadFM stand out among all VLMs. (2) Our dataset exposes critical differences in VLM components, where proper image preprocessing and design of vision modules significantly affect 3D perception. To facilitate medical multimodal research, we have released DeepTumorVQA as a rigorous benchmark: https://github.com/Schuture/DeepTumorVQA.
Recent methods for visual question answering rely on large-scale annotated datasets. Manual annotation of questions and answers for videos, however, is tedious, expensive and prevents scalability. In this work, we propose to avoid manual annotation and generate a large-scale training dataset for video question answering making use of automatic cross-modal supervision. We leverage a question generation transformer trained on text data and use it to generate question-answer pairs from transcribed video narrations. Given narrated videos, we then automatically generate the HowToVQA69M dataset with 69M video-question-answer triplets. To handle the open vocabulary of diverse answers in this dataset, we propose a training procedure based on a contrastive loss between a video-question multi-modal transformer and an answer transformer. We introduce the zero-shot VideoQA task and the VideoQA feature probe evaluation setting and show excellent results, in particular for rare answers. Furthermore, our method achieves competitive results on MSRVTT-QA, ActivityNet-QA, MSVD-QA and How2QA datasets. We also show that our VideoQA dataset generation approach generalizes to another source of web video and text data. We use our method to generate the WebVidVQA3M dataset from the WebVid dataset, i.e., videos with alt-text annotations, and show its benefits for training VideoQA models. Finally, for a detailed evaluation we introduce iVQA, a new VideoQA dataset with reduced language bias and high-quality manual annotations. Code, datasets and trained models are available at https://antoyang.github.io/just-ask.html
Multimodal representation learning is gaining more and more interest within the deep learning community. While bilinear models provide an interesting framework to find subtle combination of modalities, their number of parameters grows quadratically with the input dimensions, making their practical implementation within classical deep learning pipelines challenging. In this paper, we introduce BLOCK, a new multimodal fusion based on the block-superdiagonal tensor decomposition. It leverages the notion of block-term ranks, which generalizes both concepts of rank and mode ranks for tensors, already used for multimodal fusion. It allows to define new ways for optimizing the tradeoff between the expressiveness and complexity of the fusion model, and is able to represent very fine interactions between modalities while maintaining powerful mono-modal representations. We demonstrate the practical interest of our fusion model by using BLOCK for two challenging tasks: Visual Question Answering (VQA) and Visual Relationship Detection (VRD), where we design end-to-end learnable architectures for representing relevant interactions between modalities. Through extensive experiments, we show that BLOCK compares favorably with respect to state-of-the-art multimodal fusion models for both VQA and VRD tasks. Our code is available at https://github.com/Cadene/block.bootstrap.pytorch.
While recent large-scale video-language pre-training made great progress in video question answering, the design of spatial modeling of video-language models is less fine-grained than that of image-language models; existing practices of temporal modeling also suffer from weak and noisy alignment between modalities. To learn fine-grained visual understanding, we decouple spatial-temporal modeling and propose a hybrid pipeline, Decoupled Spatial-Temporal Encoders, integrating an image- and a video-language encoder. The former encodes spatial semantics from larger but sparsely sampled frames independently of time, while the latter models temporal dynamics at lower spatial but higher temporal resolution. To help the video-language model learn temporal relations for video QA, we propose a novel pre-training objective, Temporal Referring Modeling, which requires the model to identify temporal positions of events in video sequences. Extensive experiments demonstrate that our model outperforms previous work pre-trained on orders of magnitude larger datasets.
Existing video segmenter and grounder approaches, exemplified by Sa2VA, directly fuse features within segmentation models. This often results in an undesirable entanglement of dynamic visual information and static semantics, thereby degrading segmentation accuracy. To systematically mitigate this issue, we propose DeSa2VA, a decoupling-enhanced prompting scheme integrating text pre-training and a linear decoupling module to address the information processing limitations inherent in SAM-2. Specifically, first, we devise a pre-training paradigm that converts textual ground-truth labels into point-level prompts while generating corresponding text masks. These masks are refined through a hybrid loss function to strengthen the model's semantic grounding capabilities. Next, we employ linear projection to disentangle hidden states that generated by a large language model into distinct textual and visual feature subspaces. Finally, a dynamic mask fusion strategy synergistically combines these decoupled features through triple supervision from predicted text/visual masks and ground-truth annotations. Extensive experiments demonstrate state-of-the-art performance across diverse tasks, including image segmentation, image question answering, video segmentation, and video question answering. Our codes are available at https://github.com/longmalongma/DeSa2VA.
On the way towards general Visual Question Answering (VQA) systems that are able to answer arbitrary questions, the need arises for evaluation beyond single-metric leaderboards for specific datasets. To this end, we propose a browser-based benchmarking tool for researchers and challenge organizers, with an API for easy integration of new models and datasets to keep up with the fast-changing landscape of VQA. Our tool helps test generalization capabilities of models across multiple datasets, evaluating not just accuracy, but also performance in more realistic real-world scenarios such as robustness to input noise. Additionally, we include metrics that measure biases and uncertainty, to further explain model behavior. Interactive filtering facilitates discovery of problematic behavior, down to the data sample level. As proof of concept, we perform a case study on four models. We find that state-of-the-art VQA models are optimized for specific tasks or datasets, but fail to generalize even to other in-domain test sets, for example they cannot recognize text in images. Our metrics allow us to quantify which image and question embeddings provide most robustness to a model. All code is publicly available.
Collecting fully annotated image datasets is challenging and expensive. Many types of weak supervision have been explored: weak manual annotations, web search results, temporal continuity, ambient sound and others. We focus on one particular unexplored mode: visual questions that are asked about images. The key observation that inspires our work is that the question itself provides useful information about the image (even without the answer being available). For instance, the question "what is the breed of the dog?" informs the AI that the animal in the scene is a dog and that there is only one dog present. We make three contributions: (1) providing an extensive qualitative and quantitative analysis of the information contained in human visual questions, (2) proposing two simple but surprisingly effective modifications to the standard visual question answering models that allow them to make use of weak supervision in the form of unanswered questions associated with images and (3) demonstrating that a simple data augmentation strategy inspired by our insights results in a 7.1% improvement on the standard VQA benchmark.
Visual question answering (VQA) is challenging not only because the model has to handle multi-modal information, but also because it is just so hard to collect sufficient training examples -- there are too many questions one can ask about an image. As a result, a VQA model trained solely on human-annotated examples could easily over-fit specific question styles or image contents that are being asked, leaving the model largely ignorant about the sheer diversity of questions. Existing methods address this issue primarily by introducing an auxiliary task such as visual grounding, cycle consistency, or debiasing. In this paper, we take a drastically different approach. We found that many of the "unknowns" to the learned VQA model are indeed "known" in the dataset implicitly. For instance, questions asking about the same object in different images are likely paraphrases; the number of detected or annotated objects in an image already provides the answer to the "how many" question, even if the question has not been annotated for that image. Building upon these insights, we present a simple data augmentation pipeline SimpleAug to turn this "known" knowledge into training examples for VQA. We show that these augmented examples can notably improve the learned VQA models' performance, not only on the VQA-CP dataset with language prior shifts but also on the VQA v2 dataset without such shifts. Our method further opens up the door to leverage weakly-labeled or unlabeled images in a principled way to enhance VQA models. Our code and data are publicly available at https://github.com/heendung/simpleAUG.
While large visual-language models (LVLM) have shown promising results on traditional visual question answering benchmarks, it is still challenging for them to answer complex VQA problems which requires diverse world knowledge. Motivated by the research of retrieval-augmented generation in the field of natural language processing, we use Dense Passage Retrieval (DPR) to retrieve related knowledge to help the model answer questions. However, DPR conduct retrieving in natural language space, which may not ensure comprehensive acquisition of image information. Thus, the retrieved knowledge is not truly conducive to helping answer the question, affecting the performance of the overall system. To address this issue, we propose a novel framework that leverages the visual-language model to select the key knowledge retrieved by DPR and answer questions. The framework consists of two modules: Selector and Answerer, where both are initialized by the LVLM and parameter-efficiently finetuned by self-bootstrapping: find key knowledge in the retrieved knowledge documents using the Selector, and then use them to finetune the Answerer to predict answers; obtain the pseudo-labels of key knowledge documents based on the predictions of the Answerer and weak supervision labels, and then finetune the Selector to select key knowledge; repeat. Our framework significantly enhances the performance of the baseline on the challenging open-domain Knowledge-based VQA benchmark, OK-VQA, achieving a state-of-the-art accuracy of 62.83%. Our code is publicly available at https://github.com/haodongze/Self-KSel-QAns.
Text and signs around roads provide crucial information for drivers, vital for safe navigation and situational awareness. Scene text recognition in motion is a challenging problem, while textual cues typically appear for a short time span, and early detection at a distance is necessary. Systems that exploit such information to assist the driver should not only extract and incorporate visual and textual cues from the video stream but also reason over time. To address this issue, we introduce RoadTextVQA, a new dataset for the task of video question answering (VideoQA) in the context of driver assistance. RoadTextVQA consists of $3,222$ driving videos collected from multiple countries, annotated with $10,500$ questions, all based on text or road signs present in the driving videos. We assess the performance of state-of-the-art video question answering models on our RoadTextVQA dataset, highlighting the significant potential for improvement in this domain and the usefulness of the dataset in advancing research on in-vehicle support systems and text-aware multimodal question answering. The dataset is available at http://cvit.iiit.ac.in/research/projects/cvit-projects/roadtextvqa
Being able to carry out complicated vision language reasoning tasks in 3D space represents a significant milestone in developing household robots and human-centered embodied AI. In this work, we demonstrate that a critical and distinct challenge in 3D vision language reasoning is situational awareness, which incorporates two key components: (1) The autonomous agent grounds its self-location based on a language prompt. (2) The agent answers open-ended questions from the perspective of its calculated position. To address this challenge, we introduce SIG3D, an end-to-end Situation-Grounded model for 3D vision language reasoning. We tokenize the 3D scene into sparse voxel representation and propose a language-grounded situation estimator, followed by a situated question answering module. Experiments on the SQA3D and ScanQA datasets show that SIG3D outperforms state-of-the-art models in situation estimation and question answering by a large margin (e.g., an enhancement of over 30% on situation estimation accuracy). Subsequent analysis corroborates our architectural design choices, explores the distinct functions of visual and textual tokens, and highlights the importance of situational awareness in the domain of 3D question answering.
The role of data in building AI systems has recently been emphasized by the emerging concept of data-centric AI. Unfortunately, in the real-world, datasets may contain dirty samples, such as poisoned samples from backdoor attack, noisy labels in crowdsourcing, and even hybrids of them. The presence of such dirty samples makes the DNNs vunerable and unreliable.Hence, it is critical to detect dirty samples to improve the quality and realiability of dataset. Existing detectors only focus on detecting poisoned samples or noisy labels, that are often prone to weak generalization when dealing with dirty samples from other domains.In this paper, we find a commonality of various dirty samples is visual-linguistic inconsistency between images and associated labels. To capture the semantic inconsistency between modalities, we propose versatile data cleanser (VDC) leveraging the surpassing capabilities of multimodal large language models (MLLM) in cross-modal alignment and reasoning.It consists of three consecutive modules: the visual question generation module to generate insightful questions about the image; the visual question answering module to acquire the semantics of the visual content by answering the questions with MLLM; followed by the visual answer evaluation module to evaluate the inconsistency.Extensive experiments demonstrate its superior performance and generalization to various categories and types of dirty samples. The code is available at \url{https://github.com/zihao-ai/vdc}.
Visual Commonsense Reasoning (VCR) predicts an answer with corresponding rationale, given a question-image input. VCR is a recently introduced visual scene understanding task with a wide range of applications, including visual question answering, automated vehicle systems, and clinical decision support. Previous approaches to solving the VCR task generally rely on pre-training or exploiting memory with long dependency relationship encoded models. However, these approaches suffer from a lack of generalizability and prior knowledge. In this paper we propose a dynamic working memory based cognitive VCR network, which stores accumulated commonsense between sentences to provide prior knowledge for inference. Extensive experiments show that the proposed model yields significant improvements over existing methods on the benchmark VCR dataset. Moreover, the proposed model provides intuitive interpretation into visual commonsense reasoning. A Python implementation of our mechanism is publicly available at https://github.com/tanjatang/DMVCR
Visual Question Answering (VQA) requires a fine-grained and simultaneous understanding of both the visual content of images and the textual content of questions. Therefore, designing an effective `co-attention' model to associate key words in questions with key objects in images is central to VQA performance. So far, most successful attempts at co-attention learning have been achieved by using shallow models, and deep co-attention models show little improvement over their shallow counterparts. In this paper, we propose a deep Modular Co-Attention Network (MCAN) that consists of Modular Co-Attention (MCA) layers cascaded in depth. Each MCA layer models the self-attention of questions and images, as well as the guided-attention of images jointly using a modular composition of two basic attention units. We quantitatively and qualitatively evaluate MCAN on the benchmark VQA-v2 dataset and conduct extensive ablation studies to explore the reasons behind MCAN's effectiveness. Experimental results demonstrate that MCAN significantly outperforms the previous state-of-the-art. Our best single model delivers 70.63$\%$ overall accuracy on the test-dev set. Code is available at https://github.com/MILVLG/mcan-vqa.
In this paper, we explore effective prompting techniques to enhance zero- and few-shot Visual Question Answering (VQA) performance in contemporary Vision-Language Models (VLMs). Central to our investigation is the role of question templates in guiding VLMs to generate accurate answers. We identify that specific templates significantly influence VQA outcomes, underscoring the need for strategic template selection. Another pivotal aspect of our study is augmenting VLMs with image captions, providing them with additional visual cues alongside direct image features in VQA tasks. Surprisingly, this augmentation significantly improves the VLMs' performance in many cases, even though VLMs "see" the image directly! We explore chain-of-thought (CoT) reasoning and find that while standard CoT reasoning causes drops in performance, advanced methods like self-consistency can help recover it. Furthermore, we find that text-only few-shot examples enhance VLMs' alignment with the task format, particularly benefiting models prone to verbose zero-shot answers. Lastly, to mitigate the challenges associated with evaluating free-form open-ended VQA responses using string-matching based VQA metrics, we introduce a straightforward LLM-guided pre-processing technique to adapt the model responses to the expected ground-truth answer distribution. In summary, our research sheds light on the intricacies of prompting strategies in VLMs for VQA, emphasizing the synergistic use of captions, templates, and pre-processing to enhance model efficacy.
Document Visual Question Answering (DocVQA) faces dual challenges in processing lengthy multimodal documents (text, images, tables) and performing cross-modal reasoning. Current document retrieval-augmented generation (DocRAG) methods remain limited by their text-centric approaches, frequently missing critical visual information. The field also lacks robust benchmarks for assessing multimodal evidence selection and integration. We introduce MMDocRAG, a comprehensive benchmark featuring 4,055 expert-annotated QA pairs with multi-page, cross-modal evidence chains. Our framework introduces innovative metrics for evaluating multimodal quote selection and enables answers that interleave text with relevant visual elements. Through large-scale experiments with 60 VLM/LLM models and 14 retrieval systems, we identify persistent challenges in multimodal evidence retrieval, selection, and integration.Key findings reveal advanced proprietary LVMs show superior performance than open-sourced alternatives. Also, they show moderate advantages using multimodal inputs over text-only inputs, while open-source alternatives show significant performance degradation. Notably, fine-tuned LLMs achieve substantial improvements when using detailed image descriptions. MMDocRAG establishes a rigorous testing ground and provides actionable insights for developing more robust multimodal DocVQA systems. Our benchmark and code are available at https://mmdocrag.github.io/MMDocRAG/.
Methods for teaching machines to answer visual questions have made significant progress in recent years, but current methods still lack important human capabilities, including integrating new visual classes and concepts in a modular manner, providing explanations for the answers and handling new domains without explicit examples. We propose a novel method that consists of two main parts: generating a question graph representation, and an answering procedure, guided by the abstract structure of the question graph to invoke an extendable set of visual estimators. Training is performed for the language part and the visual part on their own, but unlike existing schemes, the method does not require any training using images with associated questions and answers. This approach is able to handle novel domains (extended question types and new object classes, properties and relations) as long as corresponding visual estimators are available. In addition, it can provide explanations to its answers and suggest alternatives when questions are not grounded in the image. We demonstrate that this approach achieves both high performance and domain extensibility without any questions-answers training.
Knowledge-based visual question answering requires the ability of associating external knowledge for open-ended cross-modal scene understanding. One limitation of existing solutions is that they capture relevant knowledge from text-only knowledge bases, which merely contain facts expressed by first-order predicates or language descriptions while lacking complex but indispensable multimodal knowledge for visual understanding. How to construct vision-relevant and explainable multimodal knowledge for the VQA scenario has been less studied. In this paper, we propose MuKEA to represent multimodal knowledge by an explicit triplet to correlate visual objects and fact answers with implicit relations. To bridge the heterogeneous gap, we propose three objective losses to learn the triplet representations from complementary views: embedding structure, topological relation and semantic space. By adopting a pre-training and fine-tuning learning strategy, both basic and domain-specific multimodal knowledge are progressively accumulated for answer prediction. We outperform the state-of-the-art by 3.35% and 6.08% respectively on two challenging knowledge-required datasets: OK-VQA and KRVQA. Experimental results prove the complementary benefits of the multimodal knowledge with existing knowledge bases and the advantages of our end-to-end framework over the existing pipeline methods. The code is available at https://github.com/AndersonStra/MuKEA.
Video question answering is a challenging task, which requires agents to be able to understand rich video contents and perform spatial-temporal reasoning. However, existing graph-based methods fail to perform multi-step reasoning well, neglecting two properties of VideoQA: (1) Even for the same video, different questions may require different amount of video clips or objects to infer the answer with relational reasoning; (2) During reasoning, appearance and motion features have complicated interdependence which are correlated and complementary to each other. Based on these observations, we propose a Dual-Visual Graph Reasoning Unit (DualVGR) which reasons over videos in an end-to-end fashion. The first contribution of our DualVGR is the design of an explainable Query Punishment Module, which can filter out irrelevant visual features through multiple cycles of reasoning. The second contribution is the proposed Video-based Multi-view Graph Attention Network, which captures the relations between appearance and motion features. Our DualVGR network achieves state-of-the-art performance on the benchmark MSVD-QA and SVQA datasets, and demonstrates competitive results on benchmark MSRVTT-QA datasets. Our code is available at https://github.com/MMIR/DualVGR-VideoQA.
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.