Multi-modal Large Language Models (MLLMs) have introduced a novel dimension to document understanding, i.e., they endow large language models with visual comprehension capabilities; however, how to design a suitable image-text pre-training task for bridging the visual and language modality in document-level MLLMs remains underexplored. In this study, we introduce a novel visual-language alignment method that casts the key issue as a Visual Question Answering with Mask generation (VQAMask) task, optimizing two tasks simultaneously: VQA-based text parsing and mask generation. The former allows the model to implicitly align images and text at the semantic level. The latter introduces an additional mask generator (discarded during inference) to explicitly ensure alignment between visual texts within images and their corresponding image regions at a spatially-aware level. Together, they can prevent model hallucinations when parsing visual text and effectively promote spatially-aware feature representation learning. To support the proposed VQAMask task, we construct a comprehensive image-mask generation pipeline and provide a large-scale dataset with 6M data (MTMask6M). Subsequently, we demonstrate that introducing the proposed mask generation task yields competitive document-level understanding performance. Leveraging the proposed VQAMask, we introduce Marten, a training-efficient MLLM tailored for document-level understanding. Extensive experiments show that our Marten consistently achieves significant improvements among 8B-MLLMs in document-centric tasks. Code and datasets are available at https://github.com/PriNing/Marten.
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.
Visual question answering requires a system to provide an accurate natural language answer given an image and a natural language question. However, it is widely recognized that previous generic VQA methods often exhibit a tendency to memorize biases present in the training data rather than learning proper behaviors, such as grounding images before predicting answers. Therefore, these methods usually achieve high in-distribution but poor out-of-distribution performance. In recent years, various datasets and debiasing methods have been proposed to evaluate and enhance the VQA robustness, respectively. This paper provides the first comprehensive survey focused on this emerging fashion. Specifically, we first provide an overview of the development process of datasets from in-distribution and out-of-distribution perspectives. Then, we examine the evaluation metrics employed by these datasets. Thirdly, we propose a typology that presents the development process, similarities and differences, robustness comparison, and technical features of existing debiasing methods. Furthermore, we analyze and discuss the robustness of representative vision-and-language pre-training models on VQA. Finally, through a thorough review of the available literature and experimental analysis, we discuss the key areas for future research from various viewpoints.
This paper presents a state-of-the-art model for visual question answering (VQA), which won the first place in the 2017 VQA Challenge. VQA is a task of significant importance for research in artificial intelligence, given its multimodal nature, clear evaluation protocol, and potential real-world applications. The performance of deep neural networks for VQA is very dependent on choices of architectures and hyperparameters. To help further research in the area, we describe in detail our high-performing, though relatively simple model. Through a massive exploration of architectures and hyperparameters representing more than 3,000 GPU-hours, we identified tips and tricks that lead to its success, namely: sigmoid outputs, soft training targets, image features from bottom-up attention, gated tanh activations, output embeddings initialized using GloVe and Google Images, large mini-batches, and smart shuffling of training data. We provide a detailed analysis of their impact on performance to assist others in making an appropriate selection.
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.
장문서 멀티모달 질의응답은 대규모 문서에서 관련 청크를 검색하는 것 이상을 요구한다. 서로 다른 쿼리는 서로 다른 증거 활용 행동을 필요로 한다. 기존 멀티모달 RAG(검색-증강 생성) 시스템은 텍스트 청크, 페이지 이미지, 그래프 링크, 또는 이질적 문서 요소를 통해 증거 접근을 개선하지만, 대체로 쿼리와 무관한 증거 활용 전략을 적용하는 경우가 많다. 본 논문은 장문서 멀티모달 QA를 위한 작업 인식 정책 제어 RAG 프레임워크인 TAP-RAG를 제안한다. TAP-RAG는 주 컨트롤러인 작업 인식 정책 컨트롤러(TAPC)와 두 개의 정책 안내 증거 실행기—작업 인식 쿼리 안내 플로우 확산(TA-QFD)과 작업 인식 시각 강화(TAVE)—로 구성된다. 각 쿼리에 대해 TAPC는 작업 사전 확률(task prior)을 예측하고, 시각/국소/전역 증거 신호를 추정하며, 실행 가능한 정책을 생성한다. TA-QFD는 멀티모달 문서 그래프 위에서 텍스트 및 구조적 증거를 확장하고, TAVE는 시각적 또는 레이아웃 증거가 필요할 때 페이지 이미지를 선택적으로 검사한다. 보호된 합성 단계는 텍스트, 시각, 구조적 증거를 융합하고 지원이 불충분할 때 답변을 기권한다. DocBench와 MMLongBench-Doc에서 TAP-RAG는 비교 시스템 중 최고의 전체 정확도를 달성하며, 각각 일치하는 멀티모달 RAG 기준선 대비 +9.1점(61.1에서 70.2) 및 +4.5점(42.2에서 46.7)을 향상시켰다.
Recently, to comprehensively improve Vision Language Models (VLMs) for Visual Question Answering (VQA), several methods have been proposed to further reinforce the inference capabilities of VLMs to independently tackle VQA tasks rather than some methods that only utilize VLMs as aids to Large Language Models (LLMs). However, these methods ignore the rich common-sense knowledge inside the given VQA image sampled from the real world. Thus, they cannot fully use the powerful VLM for the given VQA question to achieve optimal performance. Attempt to overcome this limitation and inspired by the human top-down reasoning process, i.e., systematically exploring relevant issues to derive a comprehensive answer, this work introduces a novel, explainable multi-agent collaboration framework by leveraging the expansive knowledge of Large Language Models (LLMs) to enhance the capabilities of VLMs themselves. Specifically, our framework comprises three agents, i.e., Responder, Seeker, and Integrator, to collaboratively answer the given VQA question by seeking its relevant issues and generating the final answer in such a top-down reasoning process. The VLM-based Responder agent generates the answer candidates for the question and responds to other relevant issues. The Seeker agent, primarily based on LLM, identifies relevant issues related to the question to inform the Responder agent and constructs a Multi-View Knowledge Base (MVKB) for the given visual scene by leveraging the build-in world knowledge of LLM. The Integrator agent combines knowledge from the Seeker agent and the Responder agent to produce the final VQA answer. Extensive and comprehensive evaluations on diverse VQA datasets with a variety of VLMs demonstrate the superior performance and interpretability of our framework over the baseline method in the zero-shot setting without extra training cost.
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.
Zero-shot visual question answering (VQA) is a challenging task that requires reasoning across modalities. While some existing methods rely on a single rationale within the Chain of Thoughts (CoT) framework, they may fall short of capturing the complexity of the VQA problem. On the other hand, some other methods that use multiple rationales may still suffer from low diversity, poor modality alignment, and inefficient retrieval and fusion. In response to these challenges, we propose \emph{Mixture of Rationales (MoR)}, a novel multi-modal reasoning method that mixes multiple rationales for VQA. MoR uses a single frozen Vision-and-Language Pre-trained Models (VLPM) model to {dynamically generate, retrieve and fuse multi-modal thoughts}. We evaluate MoR on two challenging VQA datasets, i.e. NLVR2 and OKVQA, with two representative backbones OFA and VL-T5. MoR achieves a 12.43\% accuracy improvement on NLVR2, and a 2.45\% accuracy improvement on OKVQA-S( the science and technology category of OKVQA).
To completely understand a document, the use of textual information is not enough. Understanding visual cues, such as layouts and charts, is also required. While the current state-of-the-art approaches for document understanding (both OCR-based and OCR-free) work well, a thorough analysis of their capabilities and limitations has not yet been performed. Therefore, in this work, we addresses the limitation of current VisualQA models when applied to charts and plots. To investigate shortcomings of the state-of-the-art models, we conduct a comprehensive behavioral analysis, using ChartQA as a case study. Our findings indicate that existing models particularly underperform in answering questions related to the chart's structural and visual context, as well as numerical information. To address these issues, we propose three simple pre-training tasks that enforce the existing model in terms of both structural-visual knowledge, as well as its understanding of numerical questions. We evaluate our pre-trained model (called MatCha-v2) on three chart datasets - both extractive and abstractive question datasets - and observe that it achieves an average improvement of 1.7% over the baseline model.
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.
Knowledge-based Vision Question Answering (KB-VQA) systems address complex visual-grounded questions requiring external knowledge, such as web-sourced encyclopedia articles. Existing methods often use sequential and separate frameworks for the retriever and the generator with limited parametric knowledge sharing. However, since both retrieval and generation tasks require accurate understanding of contextual and external information, such separation can potentially lead to suboptimal system performance. Another key challenge is the integration of multimodal information. General-purpose multimodal pre-trained models, while adept at multimodal representation learning, struggle with fine-grained retrieval required for knowledge-intensive visual questions. Recent specialized pre-trained models mitigate the issue, but are computationally expensive. To bridge the gap, we propose a Unified Retrieval-Augmented VQA framework (UniRVQA). UniRVQA adapts general multimodal pre-trained models for fine-grained knowledge-intensive tasks within a unified framework, enabling cross-task parametric knowledge sharing and the extension of existing multimodal representation learning capability. We further introduce a reflective-answering mechanism that allows the model to explicitly evaluate and refine its knowledge boundary. Additionally, we integrate late interaction into the retrieval-augmented generation joint training process to enhance fine-grained understanding of queries and documents. Our approach achieves competitive performance against state-of-the-art models, delivering a significant 4.7% improvement in answering accuracy, and brings an average 7.5% boost in base MLLMs' VQA performance.
In recent years, visual question answering (VQA) has become topical. The premise of VQA's significance as a benchmark in AI, is that both the image and textual question need to be well understood and mutually grounded in order to infer the correct answer. However, current VQA models perhaps `understand' less than initially hoped, and instead master the easier task of exploiting cues given away in the question and biases in the answer distribution. In this paper we propose the inverse problem of VQA (iVQA). The iVQA task is to generate a question that corresponds to a given image and answer pair. We propose a variational iVQA model that can generate diverse, grammatically correct and content correlated questions that match the given answer. Based on this model, we show that iVQA is an interesting benchmark for visuo-linguistic understanding, and a more challenging alternative to VQA because an iVQA model needs to understand the image better to be successful. As a second contribution, we show how to use iVQA in a novel reinforcement learning framework to diagnose any existing VQA model by way of exposing its belief set: the set of question-answer pairs that the VQA model would predict true for a given image. This provides a completely new window into what VQA models `believe' about images. We show that existing VQA models have more erroneous beliefs than previously thought, revealing their intrinsic weaknesses. Suggestions are then made on how to address these weaknesses going forward.
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.
장시간 비디오 질의응답에서는 멀티모달 대규모 언어 모델이 엄격한 시각 토큰 예산 아래에서 추론해야 하므로, 넓은 시간적 범위와 세밀한 공간적 디테일 사이에 상충 관계가 발생한다. 균일 샘플링은 범위를 보존하지만 결정적인 국소 단서를 가리는 경우가 많고, 캡션 기반 또는 프레임 유사도 기반 검색은 정보 손실이 있는 대리 표현을 대상으로 하므로 움직임, 상태 변화, 전후 관계를 놓칠 수 있다. 우리는 장시간 비디오 추론을 시각 토큰 할당 문제로 재정의한다. 즉, 고정된 예산이 주어졌을 때 전역 맥락과 고해상도 국소 증거에 각각 얼마를 쓸지, 그리고 국소 증거를 비디오의 어느 위치에서 가져올지를 결정하는 문제이다. 우리는 전역 비디오 개관과 국소 시각 디테일 사이에 시각 토큰을 적응적으로 할당하는, 학습이 필요 없는 추론 프레임워크인 AdaAlloc을 제안한다. AdaAlloc은 먼저 전역/국소 할당 정책을 계획한 뒤, 시간적 그라운딩을 사용해 후보 증거 구간을 찾고 이를 정제하여 간결한 시간적 메모리로 만든다. 선택된 정책은 프레임 샘플링 밀도와 해상도를 모두 제어하며, 희소하고 해상도가 낮은 전역 프레임과 정제된 메모리에서 가져온 더 조밀하고 해상도가 높은 국소 프레임을 결합한다. 최종 응답기는 할당된 전역 맥락과 정제된 국소 증거에 대해 추론한다. LVBench, MLVU, VideoMME, LongVideoBench 전반에서 AdaAlloc은 예산이 동일한 균일 샘플링보다 최대 10.5%p 향상되었으며, 비교 대상인 프레임 선택 방법과 에이전트 방법을 각자 보고된 벤치마크에서 능가한다.
Writing reports by analyzing medical images is error-prone for inexperienced practitioners and time consuming for experienced ones. In this work, we present RepsNet that adapts pre-trained vision and language models to interpret medical images and generate automated reports in natural language. RepsNet consists of an encoder-decoder model: the encoder aligns the images with natural language descriptions via contrastive learning, while the decoder predicts answers by conditioning on encoded images and prior context of descriptions retrieved by nearest neighbor search. We formulate the problem in a visual question answering setting to handle both categorical and descriptive natural language answers. We perform experiments on two challenging tasks of medical visual question answering (VQA-Rad) and report generation (IU-Xray) on radiology image datasets. Results show that RepsNet outperforms state-of-the-art methods with 81.08 % classification accuracy on VQA-Rad 2018 and 0.58 BLEU-1 score on IU-Xray. Supplementary details are available at https://sites.google.com/view/repsnet
Vision Language Models (VLMs) have demonstrated strong performance in multi-modal tasks by effectively aligning visual and textual representations. However, most video understanding VLM research has been domain-agnostic, leaving the understanding of their transfer learning capability to specialized domains under-explored. In this work, we address this by exploring the adaptability of open-source VLMs to specific domains, and focusing on soccer as an initial case study. Our approach uses large-scale soccer datasets and LLM to create instruction-following data, and use them to iteratively fine-tune the general-domain VLM in a curriculum learning fashion (first teaching the model key soccer concepts to then question answering tasks). The final adapted model, trained using a curated dataset of 20k video clips, exhibits significant improvement in soccer-specific tasks compared to the base model, with a 37.5% relative improvement for the visual question-answering task and an accuracy improvement from 11.8% to 63.5% for the downstream soccer action classification task.
Vision-language models (VLMs) excel at tasks requiring joint understanding of visual and linguistic information. A particularly promising yet under-explored application for these models lies in answering questions based on various kinds of maps. This study investigates the efficacy of VLMs in answering questions based on choropleth maps, which are widely used for data analysis and representation. To facilitate and encourage research in this area, we introduce a novel map-based question-answering benchmark, consisting of maps from three geographical regions (United States, India, China), each containing 1000 questions. Our benchmark incorporates 43 diverse question templates, requiring nuanced understanding of relative spatial relationships, intricate map features, and complex reasoning. It also includes maps with discrete and continuous values, encompassing variations in color-mapping, category ordering, and stylistic patterns, enabling comprehensive analysis. We evaluate the performance of multiple VLMs on this benchmark, highlighting gaps in their abilities and providing insights for improving such models.
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}.