PyTorchKR Papers

“Visual Question Answering”

총 2,807편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2610.16722v1cs.CL

Lost in Contrast: Instruction-Preserving Decoding for Reliable Visual Question Answering

Visual contrastive decoding corrects answers using the prediction difference between the original image and a reference condition, yet the same contrast also turns supported abstentions into incorrect answers. We find that abstentions are lost at two stages: contrastive decoding with candidate filtering can exclude the abstention token before any comparison takes place, and the reference branch's response to the abstention instruction is removed when the reference prediction is subtracted. We therefore propose instruction-preserving decoding, which keeps the effect of the abstention instruction on the original-image prediction intact while leaving the contrast strength freely adjustable. Using a perturbed image and an image-free prediction as references, we obtain IP-VCD and IP-M3ID. On decision utility (DU), which credits both correct answers and supported abstentions, both methods outperform all compared non-IP baselines on every one of nine models on VizWiz, and IP-VCD also leads on eight of nine models on Food-101. Candidate measurements and paired per-question comparisons show that computing the instruction effect and the visual contrast term separately lets contrastive decoding support both correct answers and supported abstentions.

arXiv:2404.09797공식 코드 · Papers with Code

TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding

The advent of Large Multimodal Models (LMMs) has sparked a surge in research aimed at harnessing their remarkable reasoning abilities. However, for understanding text-rich images, challenges persist in fully leveraging the potential of LMMs, and existing methods struggle with effectively processing high-resolution images. In this work, we propose TextCoT, a novel Chain-of-Thought framework for text-rich image understanding. TextCoT utilizes the captioning ability of LMMs to grasp the global context of the image and the grounding capability to examine local textual regions. This allows for the extraction of both global and local visual information, facilitating more accurate question-answering. Technically, TextCoT consists of three stages, including image overview, coarse localization, and fine-grained observation. The image overview stage provides a comprehensive understanding of the global scene information, and the coarse localization stage approximates the image area containing the answer based on the question asked. Then, integrating the obtained global image descriptions, the final stage further examines specific regions to provide accurate answers. Our method is free of extra training, offering immediate plug-and-play functionality. Extensive experiments are conducted on a series of text-rich image question-answering benchmark datasets based on several advanced LMMs, and the results demonstrate the effectiveness and strong generalization ability of our method. Code is available at https://github.com/bzluan/TextCoT.

arXiv:2012.15484

Seeing is Knowing! Fact-based Visual Question Answering using Knowledge Graph Embeddings

Fact-based Visual Question Answering (FVQA), a challenging variant of VQA, requires a QA-system to include facts from a diverse knowledge graph (KG) in its reasoning process to produce an answer. Large KGs, especially common-sense KGs, are known to be incomplete, i.e., not all non-existent facts are always incorrect. Therefore, being able to reason over incomplete KGs for QA is a critical requirement in real-world applications that has not been addressed extensively in the literature. We develop a novel QA architecture that allows us to reason over incomplete KGs, something current FVQA state-of-the-art (SOTA) approaches lack due to their critical reliance on fact retrieval. We use KG Embeddings, a technique widely used for KG completion, for the downstream task of FVQA. We also employ a new image representation technique we call 'Image-as-Knowledge' to enable this capability, alongside a simple one-step CoAttention mechanism to attend to text and image during QA. Our FVQA architecture is faster during inference time, being O(m), as opposed to existing FVQA SOTA methods which are O(N log N), where m = number of vertices, N = number of edges = O(m^2). KG embeddings are shown to hold complementary information to word embeddings: a combination of both metrics permits performance comparable to SOTA methods in the standard answer retrieval task, and significantly better (26% absolute) in the proposed missing-edge reasoning task.

arXiv:2406.07089v4cs.CV공식 코드 · Papers with Code

RS-Agent: 지능형 에이전트를 통한 원격 탐사 작업 자동화

RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent

RS-Agent는 구조화된 작업 계획과 도구 오케스트레이션을 통해 사용자 의도를 전문적인 원격 탐사 워크플로우와 연결하는 도메인 적응형 지능 에이전트로, 중앙 컨트롤러, 동적 툴킷, Solution Space, Knowledge Space의 네 가지 구성요소로 이루어진다. Task-Aware Retrieval과 가중 이중 경로 검색-증강 생성 방법인 DualRAG를 도입하여 9개 데이터셋, 18개 원격 탐사 작업 실험에서 95% 이상의 작업 계획 정확도와 함께 장면 분류, 객체 계수, 시각적 질의응답에서 최신 MLLM 대비 현저히 높은 성능을 달성하였다.

arXiv:1806.04284공식 코드 · Papers with Code

iParaphrasing: Extracting Visually Grounded Paraphrases via an Image

A paraphrase is a restatement of the meaning of a text in other words. Paraphrases have been studied to enhance the performance of many natural language processing tasks. In this paper, we propose a novel task iParaphrasing to extract visually grounded paraphrases (VGPs), which are different phrasal expressions describing the same visual concept in an image. These extracted VGPs have the potential to improve language and image multimodal tasks such as visual question answering and image captioning. How to model the similarity between VGPs is the key of iParaphrasing. We apply various existing methods as well as propose a novel neural network-based method with image attention, and report the results of the first attempt toward iParaphrasing.

arXiv:2502.00989

ChartCitor: Multi-Agent Framework for Fine-Grained Chart Visual Attribution

Large Language Models (LLMs) can perform chart question-answering tasks but often generate unverified hallucinated responses. Existing answer attribution methods struggle to ground responses in source charts due to limited visual-semantic context, complex visual-text alignment requirements, and difficulties in bounding box prediction across complex layouts. We present ChartCitor, a multi-agent framework that provides fine-grained bounding box citations by identifying supporting evidence within chart images. The system orchestrates LLM agents to perform chart-to-table extraction, answer reformulation, table augmentation, evidence retrieval through pre-filtering and re-ranking, and table-to-chart mapping. ChartCitor outperforms existing baselines across different chart types. Qualitative user studies show that ChartCitor helps increase user trust in Generative AI by providing enhanced explainability for LLM-assisted chart QA and enables professionals to be more productive.

arXiv:2507.12441공식 코드 · Papers with Code

Describe Anything Model for Visual Question Answering on Text-rich Images

Recent progress has been made in region-aware vision-language modeling, particularly with the emergence of the Describe Anything Model (DAM). DAM is capable of generating detailed descriptions of any specific image areas or objects without the need for additional localized image-text alignment supervision. We hypothesize that such region-level descriptive capability is beneficial for the task of Visual Question Answering (VQA), especially in challenging scenarios involving images with dense text. In such settings, the fine-grained extraction of textual information is crucial to producing correct answers. Motivated by this, we introduce DAM-QA, a framework with a tailored evaluation protocol, developed to investigate and harness the region-aware capabilities from DAM for the text-rich VQA problem that requires reasoning over text-based information within images. DAM-QA incorporates a mechanism that aggregates answers from multiple regional views of image content, enabling more effective identification of evidence that may be tied to text-related elements. Experiments on six VQA benchmarks show that our approach consistently outperforms the baseline DAM, with a notable 7+ point gain on DocVQA. DAM-QA also achieves the best overall performance among region-aware models with fewer parameters, significantly narrowing the gap with strong generalist VLMs. These results highlight the potential of DAM-like models for text-rich and broader VQA tasks when paired with efficient usage and integration strategies. Our code is publicly available at https://github.com/Linvyl/DAM-QA.git.

arXiv:2106.14476

Adventurer's Treasure Hunt: A Transparent System for Visually Grounded Compositional Visual Question Answering based on Scene Graphs

With the expressed goal of improving system transparency and visual grounding in the reasoning process in VQA, we present a modular system for the task of compositional VQA based on scene graphs. Our system is called "Adventurer's Treasure Hunt" (or ATH), named after an analogy we draw between our model's search procedure for an answer and an adventurer's search for treasure. We developed ATH with three characteristic features in mind: 1. By design, ATH allows us to explicitly quantify the impact of each of the sub-components on overall VQA performance, as well as their performance on their individual sub-task. 2. By modeling the search task after a treasure hunt, ATH inherently produces an explicit, visually grounded inference path for the processed question. 3. ATH is the first GQA-trained VQA system that dynamically extracts answers by querying the visual knowledge base directly, instead of selecting one from a specially learned classifier's output distribution over a pre-fixed answer vocabulary. We report detailed results on all components and their contributions to overall VQA performance on the GQA dataset and show that ATH achieves the highest visual grounding score among all examined systems.

arXiv:2310.05338

Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models

Object hallucination poses a significant challenge in vision-language (VL) models, often leading to the generation of nonsensical or unfaithful responses with non-existent objects. However, the absence of a general measurement for evaluating object hallucination in VL models has hindered our understanding and ability to mitigate this issue. In this work, we present NOPE (Negative Object Presence Evaluation), a novel benchmark designed to assess object hallucination in VL models through visual question answering (VQA). We propose a cost-effective and scalable approach utilizing large language models to generate 29.5k synthetic negative pronoun (NegP) data of high quality for NOPE. We extensively investigate the performance of 10 state-of-the-art VL models in discerning the non-existence of objects in visual questions, where the ground truth answers are denoted as NegP (e.g., "none"). Additionally, we evaluate their standard performance on visual questions on 9 other VQA datasets. Through our experiments, we demonstrate that no VL model is immune to the vulnerability of object hallucination, as all models achieve accuracy below 10\% on NegP. Furthermore, we uncover that lexically diverse visual questions, question types with large scopes, and scene-relevant objects capitalize the risk of object hallucination in VL models.

arXiv:2409.09748

Explore the Hallucination on Low-level Perception for MLLMs

The rapid development of Multi-modality Large Language Models (MLLMs) has significantly influenced various aspects of industry and daily life, showcasing impressive capabilities in visual perception and understanding. However, these models also exhibit hallucinations, which limit their reliability as AI systems, especially in tasks involving low-level visual perception and understanding. We believe that hallucinations stem from a lack of explicit self-awareness in these models, which directly impacts their overall performance. In this paper, we aim to define and evaluate the self-awareness of MLLMs in low-level visual perception and understanding tasks. To this end, we present QL-Bench, a benchmark settings to simulate human responses to low-level vision, investigating self-awareness in low-level visual perception through visual question answering related to low-level attributes such as clarity and lighting. Specifically, we construct the LLSAVisionQA dataset, comprising 2,990 single images and 1,999 image pairs, each accompanied by an open-ended question about its low-level features. Through the evaluation of 15 MLLMs, we demonstrate that while some models exhibit robust low-level visual capabilities, their self-awareness remains relatively underdeveloped. Notably, for the same model, simpler questions are often answered more accurately than complex ones. However, self-awareness appears to improve when addressing more challenging questions. We hope that our benchmark will motivate further research, particularly focused on enhancing the self-awareness of MLLMs in tasks involving low-level visual perception and understanding.

arXiv:1907.07804공식 코드 · Papers with Code

OmniNet: A unified architecture for multi-modal multi-task learning

Transformer is a popularly used neural network architecture, especially for language understanding. We introduce an extended and unified architecture that can be used for tasks involving a variety of modalities like image, text, videos, etc. We propose a spatio-temporal cache mechanism that enables learning spatial dimension of the input in addition to the hidden states corresponding to the temporal input sequence. The proposed architecture further enables a single model to support tasks with multiple input modalities as well as asynchronous multi-task learning, thus we refer to it as OmniNet. For example, a single instance of OmniNet can concurrently learn to perform the tasks of part-of-speech tagging, image captioning, visual question answering and video activity recognition. We demonstrate that training these four tasks together results in about three times compressed model while retaining the performance in comparison to training them individually. We also show that using this neural network pre-trained on some modalities assists in learning unseen tasks such as video captioning and video question answering. This illustrates the generalization capacity of the self-attention mechanism on the spatio-temporal cache present in OmniNet.

arXiv:2402.04615공식 코드 · Papers with Code

ScreenAI: A Vision-Language Model for UI and Infographics Understanding

Screen user interfaces (UIs) and infographics, sharing similar visual language and design principles, play important roles in human communication and human-machine interaction. We introduce ScreenAI, a vision-language model that specializes in UI and infographics understanding. Our model improves upon the PaLI architecture with the flexible patching strategy of pix2struct and is trained on a unique mixture of datasets. At the heart of this mixture is a novel screen annotation task in which the model has to identify the type and location of UI elements. We use these text annotations to describe screens to Large Language Models and automatically generate question-answering (QA), UI navigation, and summarization training datasets at scale. We run ablation studies to demonstrate the impact of these design choices. At only 5B parameters, ScreenAI achieves new state-of-the-artresults on UI- and infographics-based tasks (Multi-page DocVQA, WebSRC, MoTIF and Widget Captioning), and new best-in-class performance on others (Chart QA, DocVQA, and InfographicVQA) compared to models of similar size. Finally, we release three new datasets: one focused on the screen annotation task and two others focused on question answering.

arXiv:2406.11815

LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning

In recent years, instruction-tuned Large Multimodal Models (LMMs) have been successful at several tasks, including image captioning and visual question answering; yet leveraging these models remains an open question for robotics. Prior LMMs for robotics applications have been extensively trained on language and action data, but their ability to generalize in different settings has often been less than desired. To address this, we introduce LLARVA, a model trained with a novel instruction tuning method that leverages structured prompts to unify a range of robotic learning tasks, scenarios, and environments. Additionally, we show that predicting intermediate 2-D representations, which we refer to as "visual traces", can help further align vision and action spaces for robot learning. We generate 8.5M image-visual trace pairs from the Open X-Embodiment dataset in order to pre-train our model, and we evaluate on 12 different tasks in the RLBench simulator as well as a physical Franka Emika Panda 7-DoF robot. Our experiments yield strong performance, demonstrating that LLARVA - using 2-D and language representations - performs well compared to several contemporary baselines, and can generalize across various robot environments and configurations.

arXiv:2505.24120

CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs

Vision-Language Models (VLMs) have demonstrated remarkable progress in multimodal understanding, yet their capabilities for scientific reasoning remains inadequately assessed. Current multimodal benchmarks predominantly evaluate generic image comprehension or text-driven reasoning, lacking authentic scientific contexts that require domain-specific knowledge integration with visual evidence analysis. To fill this gap, we present CSVQA, a diagnostic multimodal benchmark specifically designed for evaluating scientific reasoning through domain-grounded visual question answering.Our benchmark features 1,378 carefully constructed question-answer pairs spanning diverse STEM disciplines, each demanding domain knowledge, integration of visual evidence, and higher-order reasoning. Compared to prior multimodal benchmarks, CSVQA places greater emphasis on real-world scientific content and complex reasoning.We additionally propose a rigorous evaluation protocol to systematically assess whether model predictions are substantiated by valid intermediate reasoning steps based on curated explanations. Our comprehensive evaluation of 15 VLMs on this benchmark reveals notable performance disparities, as even the top-ranked proprietary model attains only 49.6\% accuracy.This empirical evidence underscores the pressing need for advancing scientific reasoning capabilities in VLMs. Our CSVQA is released at https://huggingface.co/datasets/Skywork/CSVQA.

arXiv:2610.02878v1cs.CL

협력 원칙을 활용한 비전-언어 모델의 VQA 평가

Evaluating VQA in Vision Language Models using Cooperative Principles

본 연구에서는 질문이 그라이스의 대화 격률(Grice's maxims)을 위반할 때 시각적 질의응답(VQA)에서 비전-언어 모델(VLM)의 성능을 평가합니다. 이를 위해 VLM을 사용하여 불필요하거나 모호하거나 거짓인 정보를 추가하는 질문 수정자(question modifier)를 생성하며, 이러한 위반 사항이 존재할 때 평가 대상 VLM(ChatGPT, Claude, Gemini, Llava)의 성능이 저하됨을 보입니다. 나아가 인간이 화용론적으로 추론하는 방식과 VLM의 추론 방식 간의 차이, 그리고 사람이 유발한 위반 사항을 해결할 때와 AI가 생성한 위반 사항을 해결할 때 VLM 추론의 차이를 실증적으로 보여줍니다. 마지막으로 실험의 과업 수행 시간(time-on-task)으로 측정한 인간의 인지적 노력은 VLM이 유발한 위반 사항을 해결할 때 더 낮지만, VLM 자체는 이러한 경우에 덜 정확하게 수행함을 보입니다.

arXiv:2609.23495v1cs.CV

고해상도 MLLM에서 텍스트에 더 많은 어텐션을 기울여라

Pay More Attention To Text In High-Resolution MLLMs

고해상도 멀티모달 대규모 언어 모델(MLLM)의 실패는 흔히 시각적 문제로 귀결되어 세부적인 근거를 복원하거나 간섭을 억제하기 위한 줌(zooming), 크롭(cropping) 및 관련 시각적 개입을 유도해 왔습니다. 그러나 최근 연구에 따르면 관련 시각적 근거는 이미 중간 표현(intermediate representation)에 인코딩되어 있어 시각 측면의 개선만으로는 불충분함을 시사합니다. 이는 자연스럽게 다음과 같은 의문을 제기합니다. 남아있는 병목 현상은 시각적 탐색을 유도하는 텍스트에 있는 것일까? 본 연구에서는 기존에 간과되었던 언어적 병목 현상을 규명합니다. 즉, 답변 생성을 위해 구성된 질문이 위치 파악(localization)에 필요한 시각적 근거를 반드시 명시하지는 않는다는 점입니다. 이러한 불일치를 해결하기 위해, 최종 추론을 위한 원래 질문을 보존하면서 보완적인 근거 명세(evidence specifications)를 도출하는 학습(training) 불필요 컴파일러인 EviSpec을 제안합니다. 나아가 근거 명세와 위치 파악의 역할을 분리하는 일치 대조 실험(matched-control experiment)을 통해 이를 검증합니다. 탐색 예산이 고정된 상태에서 구조화된 근거 명세는 일반적인 요청 대비 8.6%의 상대적 성능 향상을 가져옵니다. 근거 지오메트리(geometry)가 일치된 상태에서 EviSpec으로 위치를 파악한 근거는 무작위 근거 대비 14.8%의 상대적 향상을 보입니다. 종합하면, 이러한 대조 실험은 단순히 시각적 접근성을 확장하기보다 찾아야 할 근거를 구체적으로 명시하는 것의 이점을 입증합니다. 5개의 모든 MLLM에 걸쳐 EviSpec은 3개 벤치마크 각각에서 해당하는 기준선(baseline) 대비 지속적으로 성능을 향상시키며, V\textsuperscript{*}Bench, HR-Bench-4K, HR-Bench-8K에서 각각 평균 \textbf{10.4%, 8.8%, 12.4%}의 상대적 성능 향상을 달성합니다. 고해상도 추론을 넘어, EviSpec은 시각적 질의응답(VQA) 및 환각(hallucination) 중심 벤치마크에서도 최고 성능(state-of-the-art)을 달성합니다.

arXiv:2208.09374

VLMAE: Vision-Language Masked Autoencoder

Image and language modeling is of crucial importance for vision-language pre-training (VLP), which aims to learn multi-modal representations from large-scale paired image-text data. However, we observe that most existing VLP methods focus on modeling the interactions between image and text features while neglecting the information disparity between image and text, thus suffering from focal bias. To address this problem, we propose a vision-language masked autoencoder framework (VLMAE). VLMAE employs visual generative learning, facilitating the model to acquire fine-grained and unbiased features. Unlike the previous works, VLMAE pays attention to almost all critical patches in an image, providing more comprehensive understanding. Extensive experiments demonstrate that VLMAE achieves better performance in various vision-language downstream tasks, including visual question answering, image-text retrieval and visual grounding, even with up to 20% pre-training speedup.

arXiv:2505.20298공식 코드 · Papers with Code

MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding

Manga, or Japanese comics, is a richly multimodal narrative form that blends images and text in complex ways. Teaching large multimodal models (LMMs) to understand such narratives at a human-like level could help manga creators reflect on and refine their stories. To this end, we introduce two benchmarks for multimodal manga understanding: MangaOCR, which targets in-page text recognition, and MangaVQA, a novel benchmark designed to evaluate contextual understanding through visual question answering. MangaVQA consists of 526 high-quality, manually constructed question-answer pairs, enabling reliable evaluation across diverse narrative and visual scenarios. Building on these benchmarks, we develop MangaLMM, a manga-specialized model finetuned from the open-source LMM Qwen2.5-VL to jointly handle both tasks. Through extensive experiments, including comparisons with proprietary models such as GPT-4o and Gemini 2.5, we assess how well LMMs understand manga. Our benchmark and model provide a comprehensive foundation for evaluating and advancing LMMs in the richly narrative domain of manga.

arXiv:1902.01385

Embodied Multimodal Multitask Learning

Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question answering. In this paper, we propose a multitask model capable of jointly learning these multimodal tasks, and transferring knowledge of words and their grounding in visual objects across the tasks. The proposed model uses a novel Dual-Attention unit to disentangle the knowledge of words in the textual representations and visual concepts in the visual representations, and align them with each other. This disentangled task-invariant alignment of representations facilitates grounding and knowledge transfer across both tasks. We show that the proposed model outperforms a range of baselines on both tasks in simulated 3D environments. We also show that this disentanglement of representations makes our model modular, interpretable, and allows for transfer to instructions containing new words by leveraging object detectors.

arXiv:1811.00232

Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension

In this work, we introduce a novel algorithm for solving the textbook question answering (TQA) task which describes more realistic QA problems compared to other recent tasks. We mainly focus on two related issues with analysis of the TQA dataset. First, solving the TQA problems requires to comprehend multi-modal contexts in complicated input data. To tackle this issue of extracting knowledge features from long text lessons and merging them with visual features, we establish a context graph from texts and images, and propose a new module f-GCN based on graph convolutional networks (GCN). Second, scientific terms are not spread over the chapters and subjects are split in the TQA dataset. To overcome this so called "out-of-domain" issue, before learning QA problems, we introduce a novel self-supervised open-set learning process without any annotations. The experimental results show that our model significantly outperforms prior state-of-the-art methods. Moreover, ablation studies validate that both methods of incorporating f-GCN for extracting knowledge from multi-modal contexts and our newly proposed self-supervised learning process are effective for TQA problems.