PyTorchKR Papers

“Visual Question Answering”

총 2,807편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2111.08609

Document AI: Benchmarks, Models and Applications

Document AI, or Document Intelligence, is a relatively new research topic that refers to the techniques for automatically reading, understanding, and analyzing business documents. It is an important research direction for natural language processing and computer vision. In recent years, the popularity of deep learning technology has greatly advanced the development of Document AI, such as document layout analysis, visual information extraction, document visual question answering, document image classification, etc. This paper briefly reviews some of the representative models, tasks, and benchmark datasets. Furthermore, we also introduce early-stage heuristic rule-based document analysis, statistical machine learning algorithms, and deep learning approaches especially pre-training methods. Finally, we look into future directions for Document AI research.

arXiv:1810.12366

Do Explanations make VQA Models more Predictable to a Human?

A rich line of research attempts to make deep neural networks more transparent by generating human-interpretable 'explanations' of their decision process, especially for interactive tasks like Visual Question Answering (VQA). In this work, we analyze if existing explanations indeed make a VQA model -- its responses as well as failures -- more predictable to a human. Surprisingly, we find that they do not. On the other hand, we find that human-in-the-loop approaches that treat the model as a black-box do.

arXiv:2410.20327

R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest

Artificial intelligence has made significant strides in medical visual question answering (Med-VQA), yet prevalent studies often interpret images holistically, overlooking the visual regions of interest that may contain crucial information, potentially aligning with a doctor's prior knowledge that can be incorporated with minimal annotations (e.g., bounding boxes). To address this gap, this paper introduces R-LLaVA, designed to enhance biomedical VQA understanding by integrating simple medical annotations as prior knowledge directly into the image space through CLIP. These annotated visual regions of interest are then fed into the LLaVA model during training, aiming to enrich the model's understanding of biomedical queries. Experimental evaluation on four standard Med-VQA datasets demonstrates R-LLaVA's superiority over existing state-of-the-art (SoTA) methods. Additionally, to verify the model's capability in visual comprehension, a novel multiple-choice medical visual understanding dataset is introduced, confirming the positive impact of focusing on visual regions of interest in advancing biomedical VQA understanding.

arXiv:2305.06988공식 코드 · Papers with Code

Self-Chained Image-Language Model for Video Localization and Question Answering

Recent studies have shown promising results on utilizing large pre-trained image-language models for video question answering. While these image-language models can efficiently bootstrap the representation learning of video-language models, they typically concatenate uniformly sampled video frames as visual inputs without explicit language-aware, temporal modeling. When only a portion of a video input is relevant to the language query, such uniform frame sampling can often lead to missing important visual cues. Although humans often find a video moment to focus on and rewind the moment to answer questions, training a query-aware video moment localizer often requires expensive annotations and high computational costs. To address this issue, we propose Self-Chained Video Localization-Answering (SeViLA), a novel framework that leverages a single image-language model (BLIP-2) to tackle both temporal keyframe localization and QA on videos. SeViLA framework consists of two modules: Localizer and Answerer, where both are parameter-efficiently fine-tuned from BLIP-2. We propose two ways of chaining these modules for cascaded inference and self-refinement. First, in the forward chain, the Localizer finds multiple language-aware keyframes in a video, which the Answerer uses to predict the answer. Second, in the reverse chain, the Answerer generates keyframe pseudo-labels to refine the Localizer, alleviating the need for expensive video moment localization annotations. Our SeViLA framework outperforms several strong baselines on 5 challenging video QA and event prediction benchmarks, and achieves the state-of-the-art in both fine-tuning (NExT-QA, STAR) and zero-shot (NExT-QA, STAR, How2QA, VLEP) settings. We also analyze the impact of Localizer, comparisons of Localizer with other temporal localization models, pre-training/self-refinement of Localizer, and varying the number of keyframes.

arXiv:2506.04983

TextVidBench: A Benchmark for Long Video Scene Text Understanding

Despite recent progress on the short-video Text-Visual Question Answering (ViteVQA) task - largely driven by benchmarks such as M4-ViteVQA - existing datasets still suffer from limited video duration and narrow evaluation scopes, making it difficult to adequately assess the growing capabilities of powerful multimodal large language models (MLLMs). To address these limitations, we introduce TextVidBench, the first benchmark specifically designed for long-video text question answering (>3 minutes). TextVidBench makes three key contributions: 1) Cross-domain long-video coverage: Spanning 9 categories (e.g., news, sports, gaming), with an average video length of 2306 seconds, enabling more realistic evaluation of long-video understanding. 2) A three-stage evaluation framework: "Text Needle-in-Haystack -> Temporal Grounding -> Text Dynamics Captioning". 3) High-quality fine-grained annotations: Containing over 5,000 question-answer pairs with detailed semantic labeling. Furthermore, we propose an efficient paradigm for improving large models through: (i) introducing the IT-Rope mechanism and temporal prompt engineering to enhance temporal perception, (ii) adopting non-uniform positional encoding to better handle long video sequences, and (iii) applying lightweight fine-tuning on video-text data. Extensive experiments on multiple public datasets as well as TextVidBench demonstrate that our new benchmark presents significant challenges to existing models, while our proposed method offers valuable insights into improving long-video scene text understanding capabilities.

arXiv:2207.11850

Visual Perturbation-aware Collaborative Learning for Overcoming the Language Prior Problem

Several studies have recently pointed that existing Visual Question Answering (VQA) models heavily suffer from the language prior problem, which refers to capturing superficial statistical correlations between the question type and the answer whereas ignoring the image contents. Numerous efforts have been dedicated to strengthen the image dependency by creating the delicate models or introducing the extra visual annotations. However, these methods cannot sufficiently explore how the visual cues explicitly affect the learned answer representation, which is vital for language reliance alleviation. Moreover, they generally emphasize the class-level discrimination of the learned answer representation, which overlooks the more fine-grained instance-level patterns and demands further optimization. In this paper, we propose a novel collaborative learning scheme from the viewpoint of visual perturbation calibration, which can better investigate the fine-grained visual effects and mitigate the language prior problem by learning the instance-level characteristics. Specifically, we devise a visual controller to construct two sorts of curated images with different perturbation extents, based on which the collaborative learning of intra-instance invariance and inter-instance discrimination is implemented by two well-designed discriminators. Besides, we implement the information bottleneck modulator on latent space for further bias alleviation and representation calibration. We impose our visual perturbation-aware framework to three orthodox baselines and the experimental results on two diagnostic VQA-CP benchmark datasets evidently demonstrate its effectiveness. In addition, we also justify its robustness on the balanced VQA benchmark.

arXiv:2504.09809

See or Recall: A Sanity Check for the Role of Vision in Solving Visualization Question Answer Tasks with Multimodal LLMs

Recent developments in multimodal large language models (MLLM) have equipped language models to reason about vision and language jointly. This permits MLLMs to both perceive and answer questions about data visualization across a variety of designs and tasks. Applying MLLMs to a broad range of visualization tasks requires us to properly evaluate their capabilities, and the most common way to conduct evaluation is through measuring a model's visualization reasoning capability, analogous to how we would evaluate human understanding of visualizations (e.g., visualization literacy). However, we found that in the context of visualization question answering (VisQA), how an MLLM perceives and reasons about visualizations can be fundamentally different from how humans approach the same problem. During the evaluation, even without visualization, the model could correctly answer a substantial portion of the visualization test questions, regardless of whether any selection options were provided. We hypothesize that the vast amount of knowledge encoded in the language model permits factual recall that supersedes the need to seek information from the visual signal. It raises concerns that the current VisQA evaluation may not fully capture the models' visualization reasoning capabilities. To address this, we propose a comprehensive sanity check framework that integrates a rule-based decision tree and a sanity check table to disentangle the effects of "seeing" (visual processing) and "recall" (reliance on prior knowledge). This validates VisQA datasets for evaluation, highlighting where models are truly "seeing", positively or negatively affected by the factual recall, or relying on inductive biases for question answering. Our study underscores the need for careful consideration in designing future visualization understanding studies when utilizing MLLMs.

arXiv:2610.34051v2cs.RO

BEHAVIOR-Spatial Benchmark: Evaluating Spatial Understanding for Robotics

Robot tasks require grounding spatial language in physical scenes, but task success alone cannot establish whether spatial instructions are followed. We present BEHAVIOR-Spatial, a benchmark built on BEHAVIOR-1K that measures spatial question answering, point-based target grounding, and robot action to examine how VLM spatial understanding relates to VLA behavior. It comprises 3,256 spatial questions across 49 activities, 1,240 grounding queries across 14 manipulation tasks, and action evaluations covering those 14 tasks and 10 navigation tasks. Our manipulation protocol evaluates held-out configurations and instruction following when the requested target changes within a fixed training layout. The baseline achieves 41.6% on held-out configurations but only 16.1% under changed instructions. VLM adaptation and robot-data pretraining provide limited improvements, whereas oracle visual target cues raise these rates to 60.3% and 38.0%, respectively. Perception evaluations reveal policy-dependent correlations between VLM question-answering and grounding accuracy and VLA manipulation performance. Together, these findings motivate evaluating spatial instruction following alongside task completion and examining when spatial perception performance translates into robot behavior. Project website: https://arielchen07.github.io/behavior-spatial/.

arXiv:2608.26848v1cs.CV

MedFG-VQA: 경량 의료 VQA를 위한 저주파 메모리 및 그래프 어텐션

MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQA

의료 시각적 질문 답변(Med-VQA)은 임상 의사결정 지원에 큰 유망성을 지니고 있지만, 한정된 주석 데이터와 기존 대규모 비전-언어 모델의 높은 연산량 요구로 인해 난관에 직면해 있습니다. 본 논문에서는 DCT 기반 저주파 특징을 증강하기 위해 메모리 뱅크를 활용하고 효과적인 시각-텍스트 정렬(alignment)을 위해 그래프 강화 크로스 어텐션을 사용하는 경량 프레임워크인 MedFG-VQA를 제안합니다. 구체적으로, 본 접근법은 두 가지 핵심 구성 요소를 포함합니다: DCT 분해를 기반으로 구축된 학습 가능한 메모리 뱅크에서 검색하여 저주파 특징을 강화하는 주파수-메모리 융합(Frequency-Memory Fusion, FMF), 그리고 크로스 어텐션을 통해 시각-텍스트 특징을 정렬하고 그래프 합성곱 집계를 통해 이를 정제하는 그래프 인지 크로스 어텐션(Graph-Aware Cross-Attention, GACA)입니다. 데이터 부족 문제를 해결하기 위해, GPT-4o를 이용해 9가지 이미징 모달리티와 10대 주요 장기에 걸쳐 200만 개 이상의 질문-답변 쌍으로 구성된 대규모 합성 데이터셋인 SynMed-VQA를 구축했습니다. SynMed-VQA 및 세 가지 다른 표준 생체의학 VQA 벤치마크에 대한 광범위한 실험은 MedFG-VQA가 훨씬 큰 모델들과 비교하여 경쟁력 있거나 우수한 성능을 달성하는 동시에 연산 비용을 현저히 낮게 유지함을 입증하여, 임상 배포를 위한 효율성과 잠재력을 강조합니다.

arXiv:2403.16921

PropTest: Automatic Property Testing for Improved Visual Programming

Visual Programming has recently emerged as an alternative to end-to-end black-box visual reasoning models. This type of method leverages Large Language Models (LLMs) to generate the source code for an executable computer program that solves a given problem. This strategy has the advantage of offering an interpretable reasoning path and does not require finetuning a model with task-specific data. We propose PropTest, a general strategy that improves visual programming by further using an LLM to generate code that tests for visual properties in an initial round of proposed solutions. Our method generates tests for data-type consistency, output syntax, and semantic properties. PropTest achieves comparable results to state-of-the-art methods while using publicly available LLMs. This is demonstrated across different benchmarks on visual question answering and referring expression comprehension. Particularly, PropTest improves ViperGPT by obtaining 46.1\% accuracy (+6.0\%) on GQA using Llama3-8B and 59.5\% (+8.1\%) on RefCOCO+ using CodeLlama-34B.

arXiv:2106.01607

Grounding Complex Navigational Instructions Using Scene Graphs

Training a reinforcement learning agent to carry out natural language instructions is limited by the available supervision, i.e. knowing when the instruction has been carried out. We adapt the CLEVR visual question answering dataset to generate complex natural language navigation instructions and accompanying scene graphs, yielding an environment-agnostic supervised dataset. To demonstrate the use of this data set, we map the scenes to the VizDoom environment and use the architecture in \citet{gatedattention} to train an agent to carry out these more complex language instructions.

arXiv:2209.14156공식 코드 · Papers with Code

TVLT: Textless Vision-Language Transformer

In this work, we present the Textless Vision-Language Transformer (TVLT), where homogeneous transformer blocks take raw visual and audio inputs for vision-and-language representation learning with minimal modality-specific design, and do not use text-specific modules such as tokenization or automatic speech recognition (ASR). TVLT is trained by reconstructing masked patches of continuous video frames and audio spectrograms (masked autoencoding) and contrastive modeling to align video and audio. TVLT attains performance comparable to its text-based counterpart on various multimodal tasks, such as visual question answering, image retrieval, video retrieval, and multimodal sentiment analysis, with 28x faster inference speed and only 1/3 of the parameters. Our findings suggest the possibility of learning compact and efficient visual-linguistic representations from low-level visual and audio signals without assuming the prior existence of text. Our code and checkpoints are available at: https://github.com/zinengtang/TVLT

arXiv:2006.06195공식 코드 · Papers with Code

Large-Scale Adversarial Training for Vision-and-Language Representation Learning

We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning. VILLA consists of two training stages: (i) task-agnostic adversarial pre-training; followed by (ii) task-specific adversarial finetuning. Instead of adding adversarial perturbations on image pixels and textual tokens, we propose to perform adversarial training in the embedding space of each modality. To enable large-scale training, we adopt the "free" adversarial training strategy, and combine it with KL-divergence-based regularization to promote higher invariance in the embedding space. We apply VILLA to current best-performing V+L models, and achieve new state of the art on a wide range of tasks, including Visual Question Answering, Visual Commonsense Reasoning, Image-Text Retrieval, Referring Expression Comprehension, Visual Entailment, and NLVR2.

arXiv:2505.07879

OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval

Vision-language retrieval-augmented generation (RAG) has become an effective approach for tackling Knowledge-Based Visual Question Answering (KB-VQA), which requires external knowledge beyond the visual content presented in images. The effectiveness of Vision-language RAG systems hinges on multimodal retrieval, which is inherently challenging due to the diverse modalities and knowledge granularities in both queries and knowledge bases. Existing methods have not fully tapped into the potential interplay between these elements. We propose a multimodal RAG system featuring a coarse-to-fine, multi-step retrieval that harmonizes multiple granularities and modalities to enhance efficacy. Our system begins with a broad initial search aligning knowledge granularity for cross-modal retrieval, followed by a multimodal fusion reranking to capture the nuanced multimodal information for top entity selection. A text reranker then filters out the most relevant fine-grained section for augmented generation. Extensive experiments on the InfoSeek and Encyclopedic-VQA benchmarks show our method achieves state-of-the-art retrieval performance and highly competitive answering results, underscoring its effectiveness in advancing KB-VQA systems.

arXiv:2403.19838공식 코드 · Papers with Code

Multi-Frame, Lightweight & Efficient Vision-Language Models for Question Answering in Autonomous Driving

Vision-Language Models (VLMs) and Multi-Modal Language models (MMLMs) have become prominent in autonomous driving research, as these models can provide interpretable textual reasoning and responses for end-to-end autonomous driving safety tasks using traffic scene images and other data modalities. However, current approaches to these systems use expensive large language model (LLM) backbones and image encoders, making such systems unsuitable for real-time autonomous driving systems where tight memory constraints exist and fast inference time is necessary. To address these previous issues, we develop EM-VLM4AD, an efficient, lightweight, multi-frame vision language model which performs Visual Question Answering for autonomous driving. In comparison to previous approaches, EM-VLM4AD requires at least 10 times less memory and floating point operations, while also achieving higher CIDEr and ROUGE-L scores than the existing baseline on the DriveLM dataset. EM-VLM4AD also exhibits the ability to extract relevant information from traffic views related to prompts and can answer questions for various autonomous driving subtasks. We release our code to train and evaluate our model at https://github.com/akshaygopalkr/EM-VLM4AD.

arXiv:2607.15241v1cs.CL

리더보드를 넘어: 신뢰할 수 있는 멀티모달 VQA를 위한 설계 교훈

Beyond the Leaderboard: Design Lessons for Trustworthy Multimodal VQA

의료 멀티모달 AI는 시각적·텍스트적 근거를 결합하면서도 신뢰할 수 있고 해석 가능해야 한다. MediaEval Medico 2025를 후향적 위(GI) 내시경 사례 연구로 활용하여, 질의응답과 설명 품질에 대한 아홉 개의 문서화된 시스템의 설계 선택을 분석한다. 사전학습 백본의 매개변수 효율적 적응은 강력한 챌린지 성능을 제공하지만, 답변 수준의 향상이 신뢰성 있고 완전한 임상적 추론으로 일관되게 이어지지는 않는다. 구조화된 추론과 명시적 그라운딩을 강제하는 방법은 이질적인 질문 유형 전반에서 더 신뢰할 수 있는 동작을 보이지만, 근거는 ablation 기반이라기보다 상관적이다. 이러한 결과는 어휘 중복을 넘어서는 평가, 표준화된 근거 연결 설명, 누출 인식 데이터 거버넌스, 경량 견고성 및 캘리브레이션 점검의 필요성을 뒷받침한다. 이러한 발견은 데이터 융합, 설명 가능성, 회복력 있는 평가에 기반한 신뢰할 수 있는 멀티모달 의료 AI를 지지한다.

arXiv:2103.12248공식 코드 · Papers with Code

Multi-Modal Answer Validation for Knowledge-Based VQA

The problem of knowledge-based visual question answering involves answering questions that require external knowledge in addition to the content of the image. Such knowledge typically comes in various forms, including visual, textual, and commonsense knowledge. Using more knowledge sources increases the chance of retrieving more irrelevant or noisy facts, making it challenging to comprehend the facts and find the answer. To address this challenge, we propose Multi-modal Answer Validation using External knowledge (MAVEx), where the idea is to validate a set of promising answer candidates based on answer-specific knowledge retrieval. Instead of searching for the answer in a vast collection of often irrelevant facts as most existing approaches do, MAVEx aims to learn how to extract relevant knowledge from noisy sources, which knowledge source to trust for each answer candidate, and how to validate the candidate using that source. Our multi-modal setting is the first to leverage external visual knowledge (images searched using Google), in addition to textual knowledge in the form of Wikipedia sentences and ConceptNet concepts. Our experiments with OK-VQA, a challenging knowledge-based VQA dataset, demonstrate that MAVEx achieves new state-of-the-art results. Our code is available at https://github.com/jialinwu17/MAVEX

arXiv:2411.12713

CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs

Large Vision-Language Model (LVLM) systems have demonstrated impressive vision-language reasoning capabilities but suffer from pervasive and severe hallucination issues, posing significant risks in critical domains such as healthcare and autonomous systems. Despite previous efforts to mitigate hallucinations, a persistent issue remains: visual defect from vision-language misalignment, creating a bottleneck in visual processing capacity. To address this challenge, we develop Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs (CATCH), based on the Information Bottleneck theory. CATCH introduces Complementary Visual Decoupling (CVD) for visual information separation, Non-Visual Screening (NVS) for hallucination detection, and Adaptive Token-level Contrastive Decoding (ATCD) for hallucination mitigation. CATCH addresses issues related to visual defects that cause diminished fine-grained feature perception and cumulative hallucinations in open-ended scenarios. It is applicable to various visual question-answering tasks without requiring any specific data or prior knowledge, and generalizes robustly to new tasks without additional training, opening new possibilities for advancing LVLM in various challenging applications.

arXiv:1908.08530공식 코드 · Papers with Code

VL-BERT: Pre-training of Generic Visual-Linguistic Representations

We introduce a new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT for short). VL-BERT adopts the simple yet powerful Transformer model as the backbone, and extends it to take both visual and linguistic embedded features as input. In it, each element of the input is either of a word from the input sentence, or a region-of-interest (RoI) from the input image. It is designed to fit for most of the visual-linguistic downstream tasks. To better exploit the generic representation, we pre-train VL-BERT on the massive-scale Conceptual Captions dataset, together with text-only corpus. Extensive empirical analysis demonstrates that the pre-training procedure can better align the visual-linguistic clues and benefit the downstream tasks, such as visual commonsense reasoning, visual question answering and referring expression comprehension. It is worth noting that VL-BERT achieved the first place of single model on the leaderboard of the VCR benchmark. Code is released at \url{https://github.com/jackroos/VL-BERT}.

arXiv:2001.03712공식 코드 · Papers with Code

MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding

Visual-semantic embedding enables various tasks such as image-text retrieval, image captioning, and visual question answering. The key to successful visual-semantic embedding is to express visual and textual data properly by accounting for their intricate relationship. While previous studies have achieved much advance by encoding the visual and textual data into a joint space where similar concepts are closely located, they often represent data by a single vector ignoring the presence of multiple important components in an image or text. Thus, in addition to the joint embedding space, we propose a novel multi-head self-attention network to capture various components of visual and textual data by attending to important parts in data. Our approach achieves the new state-of-the-art results in image-text retrieval tasks on MS-COCO and Flicker30K datasets. Through the visualization of the attention maps that capture distinct semantic components at multiple positions in the image and the text, we demonstrate that our method achieves an effective and interpretable visual-semantic joint space.