PyTorchKR Papers

최신 논문

총 2,558편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2501.07109

The Quest for Visual Understanding: A Journey Through the Evolution of Visual Question Answering

Visual Question Answering (VQA) is an interdisciplinary field that bridges the gap between computer vision (CV) and natural language processing(NLP), enabling Artificial Intelligence(AI) systems to answer questions about images. Since its inception in 2015, VQA has rapidly evolved, driven by advances in deep learning, attention mechanisms, and transformer-based models. This survey traces the journey of VQA from its early days, through major breakthroughs, such as attention mechanisms, compositional reasoning, and the rise of vision-language pre-training methods. We highlight key models, datasets, and techniques that shaped the development of VQA systems, emphasizing the pivotal role of transformer architectures and multimodal pre-training in driving recent progress. Additionally, we explore specialized applications of VQA in domains like healthcare and discuss ongoing challenges, such as dataset bias, model interpretability, and the need for common-sense reasoning. Lastly, we discuss the emerging trends in large multimodal language models and the integration of external knowledge, offering insights into the future directions of VQA. This paper aims to provide a comprehensive overview of the evolution of VQA, highlighting both its current state and potential advancements.

arXiv:2501.06828

GeoPix: Multi-Modal Large Language Model for Pixel-level Image Understanding in Remote Sensing

Multi-modal large language models (MLLMs) have achieved remarkable success in image- and region-level remote sensing (RS) image understanding tasks, such as image captioning, visual question answering, and visual grounding. However, existing RS MLLMs lack the pixel-level dialogue capability, which involves responding to user instructions with segmentation masks for specific instances. In this paper, we propose GeoPix, a RS MLLM that extends image understanding capabilities to the pixel level. This is achieved by equipping the MLLM with a mask predictor, which transforms visual features from the vision encoder into masks conditioned on the LLM's segmentation token embeddings. To facilitate the segmentation of multi-scale objects in RS imagery, a class-wise learnable memory module is integrated into the mask predictor to capture and store class-wise geo-context at the instance level across the entire dataset. In addition, to address the absence of large-scale datasets for training pixel-level RS MLLMs, we construct the GeoPixInstruct dataset, comprising 65,463 images and 140,412 instances, with each instance annotated with text descriptions, bounding boxes, and masks. Furthermore, we develop a two-stage training strategy to balance the distinct requirements of text generation and masks prediction in multi-modal multi-task optimization. Extensive experiments verify the effectiveness and superiority of GeoPix in pixel-level segmentation tasks, while also maintaining competitive performance in image- and region-level benchmarks.

arXiv:2501.05690

Overcoming Language Priors for Visual Question Answering Based on Knowledge Distillation

Previous studies have pointed out that visual question answering (VQA) models are prone to relying on language priors for answer predictions. In this context, predictions often depend on linguistic shortcuts rather than a comprehensive grasp of multimodal knowledge, which diminishes their generalization ability. In this paper, we propose a novel method, namely, KDAR, leveraging knowledge distillation to address the prior-dependency dilemmas within the VQA task. Specifically, the regularization effect facilitated by soft labels from a well-trained teacher is employed to penalize overfitting to the most common answers. The soft labels, which serve a regularization role, also provide semantic guidance that narrows the range of candidate answers. Additionally, we design an adaptive sample-wise reweighting learning strategy to further mitigate bias by dynamically adjusting the importance of each sample. Experimental results demonstrate that our method enhances performance in both OOD and IID settings. Our method achieves state-of-the-art performance on the VQA-CPv2 out-of-distribution (OOD) benchmark, significantly outperforming previous state-of-the-art approaches.

arXiv:2501.05067

LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding

In this paper, we introduce LLaVA-Octopus, a novel video multimodal large language model. LLaVA-Octopus adaptively weights features from different visual projectors based on user instructions, enabling us to leverage the complementary strengths of each projector. We observe that different visual projectors exhibit distinct characteristics when handling specific tasks. For instance, some projectors excel at capturing static details, while others are more effective at processing temporal information, and some are better suited for tasks requiring temporal coherence. By dynamically adjusting feature weights according to user instructions, LLaVA-Octopus dynamically selects and combines the most suitable features, significantly enhancing the model's performance in multimodal tasks. Experimental results demonstrate that LLaVA-Octopus achieves excellent performance across multiple benchmarks, especially in tasks such as multimodal understanding, visual question answering, and video understanding, highlighting its broad application potential.

arXiv:2501.04568

Feedback-Driven Vision-Language Alignment with Minimal Human Supervision

Vision-language models (VLMs) have demonstrated remarkable potential in integrating visual and linguistic information, but their performance is often constrained by the need for extensive, high-quality image-text training data. Curation of these image-text pairs is both time-consuming and computationally expensive. To address this challenge, we introduce SVP (Sampling-based Visual Projection), a novel framework that enhances vision-language alignment without relying on manually curated text-image pairs or preference annotation. SVP leverages a small set of manually selected images, self-captioning and a pre-trained grounding model as a feedback mechanism to elicit latent information in VLMs. We evaluate our approach across six key areas: captioning, referring, visual question answering, multitasking, hallucination control, and object recall. Results demonstrate significant improvements, including a 14 % average improvement in captioning tasks, up to 12 % increase in object recall, and significantly reduced hallucinations, while maintaining question-answering capabilities. Using SVP, a small VLM achieves hallucination reductions similar to a model five times larger, while a VLM with initially poor referring capabilities more than doubles its performance, approaching parity with a model twice its size.

arXiv:2501.03786

KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration

Zero-shot anomaly detection (ZSAD) identifies anomalies without needing training samples from the target dataset, essential for scenarios with privacy concerns or limited data. Vision-language models like CLIP show potential in ZSAD but have limitations: relying on manually crafted fixed textual descriptions or anomaly prompts is time-consuming and prone to semantic ambiguity, and CLIP struggles with pixel-level anomaly segmentation, focusing more on global semantics than local details. To address these limitations, We introduce KAnoCLIP, a novel ZSAD framework that leverages vision-language models. KAnoCLIP combines general knowledge from a Large Language Model (GPT-3.5) and fine-grained, image-specific knowledge from a Visual Question Answering system (Llama3) via Knowledge-Driven Prompt Learning (KnPL). KnPL uses a knowledge-driven (KD) loss function to create learnable anomaly prompts, removing the need for fixed text prompts and enhancing generalization. KAnoCLIP includes the CLIP visual encoder with V-V attention (CLIP-VV), Bi-Directional Cross-Attention for Multi-Level Cross-Modal Interaction (Bi-CMCI), and Conv-Adapter. These components preserve local visual semantics, improve local cross-modal fusion, and align global visual features with textual information, enhancing pixel-level anomaly detection. KAnoCLIP achieves state-of-the-art performance in ZSAD across 12 industrial and medical datasets, demonstrating superior generalization compared to existing methods.

arXiv:2501.03939

Visual question answering: from early developments to recent advances -- a survey

Visual Question Answering (VQA) is an evolving research field aimed at enabling machines to answer questions about visual content by integrating image and language processing techniques such as feature extraction, object detection, text embedding, natural language understanding, and language generation. With the growth of multimodal data research, VQA has gained significant attention due to its broad applications, including interactive educational tools, medical image diagnosis, customer service, entertainment, and social media captioning. Additionally, VQA plays a vital role in assisting visually impaired individuals by generating descriptive content from images. This survey introduces a taxonomy of VQA architectures, categorizing them based on design choices and key components to facilitate comparative analysis and evaluation. We review major VQA approaches, focusing on deep learning-based methods, and explore the emerging field of Large Visual Language Models (LVLMs) that have demonstrated success in multimodal tasks like VQA. The paper further examines available datasets and evaluation metrics essential for measuring VQA system performance, followed by an exploration of real-world VQA applications. Finally, we highlight ongoing challenges and future directions in VQA research, presenting open questions and potential areas for further development. This survey serves as a comprehensive resource for researchers and practitioners interested in the latest advancements and future

arXiv:2501.02201

Accounting for Focus Ambiguity in Visual Questions

No existing work on visual question answering explicitly accounts for ambiguity regarding where the content described in the question is located in the image. To fill this gap, we introduce VQ-FocusAmbiguity, the first VQA dataset that visually grounds each region described in the question that is necessary to arrive at the answer. We then provide an analysis showing how our dataset for visually grounding `questions' is distinct from visually grounding `answers', and characterize the properties of the questions and segmentations provided in our dataset. Finally, we benchmark modern models for two novel tasks: recognizing whether a visual question has focus ambiguity and localizing all plausible focus regions within the image. Results show that the dataset is challenging for modern models. To facilitate future progress on these tasks, we publicly share the dataset with an evaluation server at https://focusambiguity.github.io/.

arXiv:2501.02669공식 코드 · Papers with Code

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?

While Vision Language Models (VLMs) are impressive in tasks such as visual question answering (VQA) and image captioning, their ability to apply multi-step reasoning to images has lagged, giving rise to perceptions of modality imbalance or brittleness. Towards systematic study of such issues, we introduce a synthetic framework for assessing the ability of VLMs to perform algorithmic visual reasoning (AVR), comprising three tasks: Table Readout, Grid Navigation, and Visual Analogy. Each has two levels of difficulty, SIMPLE and HARD, and even the SIMPLE versions are difficult for frontier VLMs. We seek strategies for training on the SIMPLE version of the tasks that improve performance on the corresponding HARD task, i.e., S2H generalization. This synthetic framework, where each task also has a text-only version, allows a quantification of the modality imbalance, and how it is impacted by training strategy. Ablations highlight the importance of explicit image-to-text conversion in promoting S2H generalization when using auto-regressive training. We also report results of mechanistic study of this phenomenon, including a measure of gradient alignment that seems to identify training strategies that promote better S2H generalization.

arXiv:2501.03225공식 코드 · Papers with Code

Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation

The rapid development of vision language models (VLMs) demands rigorous and reliable evaluation. However, current visual question answering (VQA) benchmarks often depend on open-ended questions, making accurate evaluation difficult due to the variability in natural language responses. To address this, we introduce AutoConverter, an agentic framework that automatically converts these open-ended questions into multiple-choice format, enabling objective evaluation while reducing the costly multiple-choice question creation process. Our experiments demonstrate that AutoConverter can generate correct and challenging multiple-choice questions, with VLMs demonstrating consistently similar or lower accuracy on these questions compared to human-created ones. Using AutoConverter, we construct VMCBench, a benchmark created by transforming 20 existing VQA datasets into a unified multiple-choice format, totaling 9,018 questions. We comprehensively evaluate 33 state-of-the-art VLMs on VMCBench, setting a new standard for scalable, consistent, and reproducible VLM evaluation.

arXiv:2501.01720

Interpretable Face Anti-Spoofing: Enhancing Generalization with Multimodal Large Language Models

Face Anti-Spoofing (FAS) is essential for ensuring the security and reliability of facial recognition systems. Most existing FAS methods are formulated as binary classification tasks, providing confidence scores without interpretation. They exhibit limited generalization in out-of-domain scenarios, such as new environments or unseen spoofing types. In this work, we introduce a multimodal large language model (MLLM) framework for FAS, termed Interpretable Face Anti-Spoofing (I-FAS), which transforms the FAS task into an interpretable visual question answering (VQA) paradigm. Specifically, we propose a Spoof-aware Captioning and Filtering (SCF) strategy to generate high-quality captions for FAS images, enriching the model's supervision with natural language interpretations. To mitigate the impact of noisy captions during training, we develop a Lopsided Language Model (L-LM) loss function that separates loss calculations for judgment and interpretation, prioritizing the optimization of the former. Furthermore, to enhance the model's perception of global visual features, we design a Globally Aware Connector (GAC) to align multi-level visual representations with the language model. Extensive experiments on standard and newly devised One to Eleven cross-domain benchmarks, comprising 12 public datasets, demonstrate that our method significantly outperforms state-of-the-art methods.

arXiv:2501.01834

MoColl: Agent-Based Specific and General Model Collaboration for Image Captioning

Image captioning is a critical task at the intersection of computer vision and natural language processing, with wide-ranging applications across various domains. For complex tasks such as diagnostic report generation, deep learning models require not only domain-specific image-caption datasets but also the incorporation of relevant general knowledge to provide contextual accuracy. Existing approaches exhibit inherent limitations: specialized models excel in capturing domain-specific details but lack generalization, while vision-language models (VLMs) built on large language models (LLMs) leverage general knowledge but struggle with domain-specific adaptation. To address these limitations, this paper proposes a novel agent-enhanced model collaboration framework, which we call MoColl, designed to effectively integrate domain-specific and general knowledge. Specifically, our approach is to decompose complex image captioning tasks into a series of interconnected question-answer subtasks. A trainable visual question answering (VQA) model is employed as a specialized tool to focus on domain-specific visual analysis, answering task-specific questions based on image content. Concurrently, an LLM-based agent with general knowledge formulates these questions and synthesizes the resulting question-answer pairs into coherent captions. Beyond its role in leveraging the VQA model, the agent further guides its training to enhance its domain-specific capabilities. Experimental results on radiology report generation validate the effectiveness of the proposed framework, demonstrating significant improvements in the quality of generated reports.

arXiv:2501.01371

CLIP-UP: CLIP-Based Unanswerable Problem Detection for Visual Question Answering

Recent Vision-Language Models (VLMs) have demonstrated remarkable capabilities in visual understanding and reasoning, and in particular on multiple-choice Visual Question Answering (VQA). Still, these models can make distinctly unnatural errors, for example, providing (wrong) answers to unanswerable VQA questions, such as questions asking about objects that do not appear in the image. To address this issue, we propose CLIP-UP: CLIP-based Unanswerable Problem detection, a novel lightweight method for equipping VLMs with the ability to withhold answers to unanswerable questions. By leveraging CLIP to extract question-image alignment information, CLIP-UP requires only efficient training of a few additional layers, while keeping the original VLMs' weights unchanged. Tested across LLaVA models, CLIP-UP achieves state-of-the-art results on the MM-UPD benchmark for assessing unanswerability in multiple-choice VQA, while preserving the original performance on other tasks.

arXiv:2501.00569

Probing Visual Language Priors in VLMs

Despite recent advances in Vision-Language Models (VLMs), many still over-rely on visual language priors present in their training data rather than true visual reasoning. To examine the situation, we introduce ViLP, a visual question answering (VQA) benchmark that pairs each question with three potential answers and three corresponding images: one image whose answer can be inferred from text alone, and two images that demand visual reasoning. By leveraging image generative models, we ensure significant variation in texture, shape, conceptual combinations, hallucinated elements, and proverb-based contexts, making our benchmark images distinctly out-of-distribution. While humans achieve near-perfect accuracy, modern VLMs falter; for instance, GPT-4 achieves only 66.17% on ViLP. To alleviate this, we propose a self-improving framework in which models generate new VQA pairs and images, then apply pixel-level and semantic corruptions to form "good-bad" image pairs for self-training. Our training objectives compel VLMs to focus more on actual visual inputs and have demonstrated their effectiveness in enhancing the performance of open-source VLMs, including LLaVA-v1.5 and Cambrian.

arXiv:2501.00289

Dual Diffusion for Unified Image Generation and Understanding

Diffusion models have gained tremendous success in text-to-image generation, yet still lag behind with visual understanding tasks, an area dominated by autoregressive vision-language models. We propose a large-scale and fully end-to-end diffusion model for multi-modal understanding and generation that significantly improves on existing diffusion-based multimodal models, and is the first of its kind to support the full suite of vision-language modeling capabilities. Inspired by the multimodal diffusion transformer (MM-DiT) and recent advances in discrete diffusion language modeling, we leverage a cross-modal maximum likelihood estimation framework that simultaneously trains the conditional likelihoods of both images and text jointly under a single loss function, which is back-propagated through both branches of the diffusion transformer. The resulting model is highly flexible and capable of a wide range of tasks including image generation, captioning, and visual question answering. Our model attained competitive performance compared to recent unified image understanding and generation models, demonstrating the potential of multimodal diffusion modeling as a promising alternative to autoregressive next-token prediction models.

arXiv:2501.00316공식 코드 · Papers with Code

MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models

Recent advancements in foundation models have enhanced AI systems' capabilities in autonomous tool usage and reasoning. However, their ability in location or map-based reasoning - which improves daily life by optimizing navigation, facilitating resource discovery, and streamlining logistics - has not been systematically studied. To bridge this gap, we introduce MapEval, a benchmark designed to assess diverse and complex map-based user queries with geo-spatial reasoning. MapEval features three task types (textual, API-based, and visual) that require collecting world information via map tools, processing heterogeneous geo-spatial contexts (e.g., named entities, travel distances, user reviews or ratings, images), and compositional reasoning, which all state-of-the-art foundation models find challenging. Comprising 700 unique multiple-choice questions about locations across 180 cities and 54 countries, MapEval evaluates foundation models' ability to handle spatial relationships, map infographics, travel planning, and navigation challenges. Using MapEval, we conducted a comprehensive evaluation of 28 prominent foundation models. While no single model excelled across all tasks, Claude-3.5-Sonnet, GPT-4o, and Gemini-1.5-Pro achieved competitive performance overall. However, substantial performance gaps emerged, particularly in MapEval, where agents with Claude-3.5-Sonnet outperformed GPT-4o and Gemini-1.5-Pro by 16% and 21%, respectively, and the gaps became even more amplified when compared to open-source LLMs. Our detailed analyses provide insights into the strengths and weaknesses of current models, though all models still fall short of human performance by more than 20% on average, struggling with complex map images and rigorous geo-spatial reasoning. This gap highlights MapEval's critical role in advancing general-purpose foundation models with stronger geo-spatial understanding.

arXiv:2412.20742공식 코드 · Papers with Code

UniRS: Unifying Multi-temporal Remote Sensing Tasks through Vision Language Models

The domain gap between remote sensing imagery and natural images has recently received widespread attention and Vision-Language Models (VLMs) have demonstrated excellent generalization performance in remote sensing multimodal tasks. However, current research is still limited in exploring how remote sensing VLMs handle different types of visual inputs. To bridge this gap, we introduce \textbf{UniRS}, the first vision-language model \textbf{uni}fying multi-temporal \textbf{r}emote \textbf{s}ensing tasks across various types of visual input. UniRS supports single images, dual-time image pairs, and videos as input, enabling comprehensive remote sensing temporal analysis within a unified framework. We adopt a unified visual representation approach, enabling the model to accept various visual inputs. For dual-time image pair tasks, we customize a change extraction module to further enhance the extraction of spatiotemporal features. Additionally, we design a prompt augmentation mechanism tailored to the model's reasoning process, utilizing the prior knowledge of the general-purpose VLM to provide clues for UniRS. To promote multi-task knowledge sharing, the model is jointly fine-tuned on a mixed dataset. Experimental results show that UniRS achieves state-of-the-art performance across diverse tasks, including visual question answering, change captioning, and video scene classification, highlighting its versatility and effectiveness in unifying these multi-temporal remote sensing tasks. Our code and dataset will be released soon.

arXiv:2412.20927

Enhanced Multimodal RAG-LLM for Accurate Visual Question Answering

Multimodal large language models (MLLMs), such as GPT-4o, Gemini, LLaVA, and Flamingo, have made significant progress in integrating visual and textual modalities, excelling in tasks like visual question answering (VQA), image captioning, and content retrieval. They can generate coherent and contextually relevant descriptions of images. However, they still face challenges in accurately identifying and counting objects and determining their spatial locations, particularly in complex scenes with overlapping or small objects. To address these limitations, we propose a novel framework based on multimodal retrieval-augmented generation (RAG), which introduces structured scene graphs to enhance object recognition, relationship identification, and spatial understanding within images. Our framework improves the MLLM's capacity to handle tasks requiring precise visual descriptions, especially in scenarios with challenging perspectives, such as aerial views or scenes with dense object arrangements. Finally, we conduct extensive experiments on the VG-150 dataset that focuses on first-person visual understanding and the AUG dataset that involves aerial imagery. The results show that our approach consistently outperforms existing MLLMs in VQA tasks, which stands out in recognizing, localizing, and quantifying objects in different spatial contexts and provides more accurate visual descriptions.

arXiv:2412.19954

ErgoChat: a Visual Query System for the Ergonomic Risk Assessment of Construction Workers

In the construction sector, workers often endure prolonged periods of high-intensity physical work and prolonged use of tools, resulting in injuries and illnesses primarily linked to postural ergonomic risks, a longstanding predominant health concern. To mitigate these risks, researchers have applied various technological methods to identify the ergonomic risks that construction workers face. However, traditional ergonomic risk assessment (ERA) techniques do not offer interactive feedback. The rapidly developing vision-language models (VLMs), capable of generating textual descriptions or answering questions about ergonomic risks based on image inputs, have not yet received widespread attention. This research introduces an interactive visual query system tailored to assess the postural ergonomic risks of construction workers. The system's capabilities include visual question answering (VQA), which responds to visual queries regarding workers' exposure to postural ergonomic risks, and image captioning (IC), which generates textual descriptions of these risks from images. Additionally, this study proposes a dataset designed for training and testing such methodologies. Systematic testing indicates that the VQA functionality delivers an accuracy of 96.5%. Moreover, evaluations using nine metrics for IC and assessments from human experts indicate that the proposed approach surpasses the performance of a method using the same architecture trained solely on generic datasets. This study sets a new direction for future developments in interactive ERA using generative artificial intelligence (AI) technologies.

arXiv:2412.20622공식 코드 · Papers with Code

HALLUCINOGEN: A Benchmark for Evaluating Object Hallucination in Large Visual-Language Models

Large Vision-Language Models (LVLMs) have demonstrated remarkable performance in performing complex multimodal tasks. However, they are still plagued by object hallucination: the misidentification or misclassification of objects present in images. To this end, we propose HALLUCINOGEN, a novel visual question answering (VQA) object hallucination attack benchmark that utilizes diverse contextual reasoning prompts to evaluate object hallucination in state-of-the-art LVLMs. We design a series of contextual reasoning hallucination prompts to evaluate LVLMs' ability to accurately identify objects in a target image while asking them to perform diverse visual-language tasks such as identifying, locating or performing visual reasoning around specific objects. Further, we extend our benchmark to high-stakes medical applications and introduce MED-HALLUCINOGEN, hallucination attacks tailored to the biomedical domain, and evaluate the hallucination performance of LVLMs on medical images, a critical area where precision is crucial. Finally, we conduct extensive evaluations of eight LVLMs and two hallucination mitigation strategies across multiple datasets to show that current generic and medical LVLMs remain susceptible to hallucination attacks.