PyTorchKR Papers

최신 논문

총 1,759편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2504.20343공식 코드 · Papers with Code

MicarVLMoE: A Modern Gated Cross-Aligned Vision-Language Mixture of Experts Model for Medical Image Captioning and Report Generation

Medical image reporting (MIR) aims to generate structured clinical descriptions from radiological images. Existing methods struggle with fine-grained feature extraction, multimodal alignment, and generalization across diverse imaging types, often relying on vanilla transformers and focusing primarily on chest X-rays. We propose MicarVLMoE, a vision-language mixture-of-experts model with gated cross-aligned fusion, designed to address these limitations. Our architecture includes: (i) a multiscale vision encoder (MSVE) for capturing anatomical details at varying resolutions, (ii) a multihead dual-branch latent attention (MDLA) module for vision-language alignment through latent bottleneck representations, and (iii) a modulated mixture-of-experts (MoE) decoder for adaptive expert specialization. We extend MIR to CT scans, retinal imaging, MRI scans, and gross pathology images, reporting state-of-the-art results on COVCTR, MMR, PGROSS, and ROCO datasets. Extensive experiments and ablations confirm improved clinical accuracy, cross-modal alignment, and model interpretability. Code is available at https://github.com/AI-14/micar-vl-moe.

arXiv:2505.00742

Zoomer: Adaptive Image Focus Optimization for Black-box MLLM

Recent advancements in multimodal large language models (MLLMs) have broadened the scope of vision-language tasks, excelling in applications like image captioning and interactive question-answering. However, these models struggle with accurately processing visual data, particularly in tasks requiring precise object recognition and fine visual details. Stringent token limits often result in the omission of critical information, hampering performance. To address these limitations, we introduce \SysName, a novel visual prompting mechanism designed to enhance MLLM performance while preserving essential visual details within token limits. \SysName features three key innovations: a prompt-aware strategy that dynamically highlights relevant image regions, a spatial-preserving orchestration schema that maintains object integrity, and a budget-aware prompting method that balances global context with crucial visual details. Comprehensive evaluations across multiple datasets demonstrate that \SysName consistently outperforms baseline methods, achieving up to a $26.9\%$ improvement in accuracy while significantly reducing token consumption.

arXiv:2505.01050

Transferable Adversarial Attacks on Black-Box Vision-Language Models

Vision Large Language Models (VLLMs) are increasingly deployed to offer advanced capabilities on inputs comprising both text and images. While prior research has shown that adversarial attacks can transfer from open-source to proprietary black-box models in text-only and vision-only contexts, the extent and effectiveness of such vulnerabilities remain underexplored for VLLMs. We present a comprehensive analysis demonstrating that targeted adversarial examples are highly transferable to widely-used proprietary VLLMs such as GPT-4o, Claude, and Gemini. We show that attackers can craft perturbations to induce specific attacker-chosen interpretations of visual information, such as misinterpreting hazardous content as safe, overlooking sensitive or restricted material, or generating detailed incorrect responses aligned with the attacker's intent. Furthermore, we discover that universal perturbations -- modifications applicable to a wide set of images -- can consistently induce these misinterpretations across multiple proprietary VLLMs. Our experimental results on object recognition, visual question answering, and image captioning show that this vulnerability is common across current state-of-the-art models, and underscore an urgent need for robust mitigations to ensure the safe and secure deployment of VLLMs.

arXiv:2505.02278

Compositional Image-Text Matching and Retrieval by Grounding Entities

Vision-language pretraining on large datasets of images-text pairs is one of the main building blocks of current Vision-Language Models. While with additional training, these models excel in various downstream tasks, including visual question answering, image captioning, and visual commonsense reasoning. However, a notable weakness of pretrained models like CLIP, is their inability to perform entity grounding and compositional image and text matching~\cite{Jiang2024ComCLIP, yang2023amc, Rajabi2023GroundedVSR, learninglocalizeCVPR24}. In this work we propose a novel learning-free zero-shot augmentation of CLIP embeddings that has favorable compositional properties. We compute separate embeddings of sub-images of object entities and relations that are localized by the state of the art open vocabulary detectors and dynamically adjust the baseline global image embedding. % The final embedding is obtained by computing a weighted combination of the sub-image embeddings. The resulting embedding is then utilized for similarity computation with text embedding, resulting in a average 1.5\% improvement in image-text matching accuracy on the Visual Genome and SVO Probes datasets~\cite{krishna2017visualgenome, svo}. Notably, the enhanced embeddings demonstrate superior retrieval performance, thus achieving significant gains on the Flickr30K and MS-COCO retrieval benchmarks~\cite{flickr30ke, mscoco}, improving the state-of-the-art Recall@1 by 12\% and 0.4\%, respectively. Our code is available at https://github.com/madhukarreddyvongala/GroundingCLIP.

arXiv:2505.03420

Mitigating Image Captioning Hallucinations in Vision-Language Models

Hallucinations in vision-language models (VLMs) hinder reliability and real-world applicability, usually stemming from distribution shifts between pretraining data and test samples. Existing solutions, such as retraining or fine-tuning on additional data, demand significant computational resources and labor-intensive data collection, while ensemble-based methods incur additional costs by introducing auxiliary VLMs. To address these challenges, we propose a novel test-time adaptation framework using reinforcement learning to mitigate hallucinations during inference without retraining or any auxiliary VLMs. By updating only the learnable parameters in the layer normalization of the language model (approximately 0.003% of the model parameters), our method reduces distribution shifts between test samples and pretraining samples. A CLIP-based hallucination evaluation model is proposed to provide dual rewards to VLMs. Experimental results demonstrate a 15.4% and 17.3% reduction in hallucination rates on LLaVA and InstructBLIP, respectively. Our approach outperforms state-of-the-art baselines with a 68.3% improvement in hallucination mitigation, demonstrating its effectiveness.

arXiv:2504.14526공식 코드 · Papers with Code

Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding

Vision Large Language Models (VLLMs) have demonstrated impressive capabilities in general visual tasks such as image captioning and visual question answering. However, their effectiveness in specialized, safety-critical domains like autonomous driving remains largely unexplored. Autonomous driving systems require sophisticated scene understanding in complex environments, yet existing multimodal benchmarks primarily focus on normal driving conditions, failing to adequately assess VLLMs' performance in safety-critical scenarios. To address this, we introduce DVBench, a pioneering benchmark designed to evaluate the performance of VLLMs in understanding safety-critical driving videos. Built around a hierarchical ability taxonomy that aligns with widely adopted frameworks for describing driving scenarios used in assessing highly automated driving systems, DVBench features 10,000 multiple-choice questions with human-annotated ground-truth answers, enabling a comprehensive evaluation of VLLMs' capabilities in perception and reasoning. Experiments on 14 SOTA VLLMs, ranging from 0.5B to 72B parameters, reveal significant performance gaps, with no model achieving over 40% accuracy, highlighting critical limitations in understanding complex driving scenarios. To probe adaptability, we fine-tuned selected models using domain-specific data from DVBench, achieving accuracy gains ranging from 5.24 to 10.94 percentage points, with relative improvements of up to 43.59%. This improvement underscores the necessity of targeted adaptation to bridge the gap between general-purpose VLLMs and mission-critical driving applications. DVBench establishes an essential evaluation framework and research roadmap for developing VLLMs that meet the safety and robustness requirements for real-world autonomous systems. We released the benchmark toolbox and the fine-tuned model at: https://github.com/tong-zeng/DVBench.git.

arXiv:2504.15199

Zero-Shot, But at What Cost? Unveiling the Hidden Overhead of MILS's LLM-CLIP Framework for Image Captioning

MILS (Multimodal Iterative LLM Solver) is a recently published framework that claims "LLMs can see and hear without any training" by leveraging an iterative, LLM-CLIP based approach for zero-shot image captioning. While this MILS approach demonstrates good performance, our investigation reveals that this success comes at a hidden, substantial computational cost due to its expensive multi-step refinement process. In contrast, alternative models such as BLIP-2 and GPT-4V achieve competitive results through a streamlined, single-pass approach. We hypothesize that the significant overhead inherent in MILS's iterative process may undermine its practical benefits, thereby challenging the narrative that zero-shot performance can be attained without incurring heavy resource demands. This work is the first to expose and quantify the trade-offs between output quality and computational cost in MILS, providing critical insights for the design of more efficient multimodal models.

arXiv:2504.12100

Generalized Visual Relation Detection with Diffusion Models

Visual relation detection (VRD) aims to identify relationships (or interactions) between object pairs in an image. Although recent VRD models have achieved impressive performance, they are all restricted to pre-defined relation categories, while failing to consider the semantic ambiguity characteristic of visual relations. Unlike objects, the appearance of visual relations is always subtle and can be described by multiple predicate words from different perspectives, e.g., ``ride'' can be depicted as ``race'' and ``sit on'', from the sports and spatial position views, respectively. To this end, we propose to model visual relations as continuous embeddings, and design diffusion models to achieve generalized VRD in a conditional generative manner, termed Diff-VRD. We model the diffusion process in a latent space and generate all possible relations in the image as an embedding sequence. During the generation, the visual and text embeddings of subject-object pairs serve as conditional signals and are injected via cross-attention. After the generation, we design a subsequent matching stage to assign the relation words to subject-object pairs by considering their semantic similarities. Benefiting from the diffusion-based generative process, our Diff-VRD is able to generate visual relations beyond the pre-defined category labels of datasets. To properly evaluate this generalized VRD task, we introduce two evaluation metrics, i.e., text-to-image retrieval and SPICE PR Curve inspired by image captioning. Extensive experiments in both human-object interaction (HOI) detection and scene graph generation (SGG) benchmarks attest to the superiority and effectiveness of Diff-VRD.

arXiv:2504.13199

Building Trustworthy Multimodal AI: A Review of Fairness, Transparency, and Ethics in Vision-Language Tasks

Objective: This review explores the trustworthiness of multimodal artificial intelligence (AI) systems, specifically focusing on vision-language tasks. It addresses critical challenges related to fairness, transparency, and ethical implications in these systems, providing a comparative analysis of key tasks such as Visual Question Answering (VQA), image captioning, and visual dialogue. Background: Multimodal models, particularly vision-language models, enhance artificial intelligence (AI) capabilities by integrating visual and textual data, mimicking human learning processes. Despite significant advancements, the trustworthiness of these models remains a crucial concern, particularly as AI systems increasingly confront issues regarding fairness, transparency, and ethics. Methods: This review examines research conducted from 2017 to 2024 focusing on forenamed core vision-language tasks. It employs a comparative approach to analyze these tasks through the lens of trustworthiness, underlining fairness, explainability, and ethics. This study synthesizes findings from recent literature to identify trends, challenges, and state-of-the-art solutions. Results: Several key findings were highlighted. Transparency: Explainability of vision language tasks is important for user trust. Techniques, such as attention maps and gradient-based methods, have successfully addressed this issue. Fairness: Bias mitigation in VQA and visual dialogue systems is essential for ensuring unbiased outcomes across diverse demographic groups. Ethical Implications: Addressing biases in multilingual models and ensuring ethical data handling is critical for the responsible deployment of vision-language systems. Conclusion: This study underscores the importance of integrating fairness, transparency, and ethical considerations in developing vision-language models within a unified framework.

arXiv:2504.09724공식 코드 · Papers with Code

A Survey on Efficient Vision-Language Models

Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high computational demands pose challenges for real-time applications. This has led to a growing focus on developing efficient vision language models. In this survey, we review key techniques for optimizing VLMs on edge and resource-constrained devices. We also explore compact VLM architectures, frameworks and provide detailed insights into the performance-memory trade-offs of efficient VLMs. Furthermore, we establish a GitHub repository at https://github.com/MPSCUMBC/Efficient-Vision-Language-Models-A-Survey to compile all surveyed papers, which we will actively update. Our objective is to foster deeper research in this area.

arXiv:2504.10854

LVLM_CSP: Accelerating Large Vision Language Models via Clustering, Scattering, and Pruning for Reasoning Segmentation

Large Vision Language Models (LVLMs) have been widely adopted to guide vision foundation models in performing reasoning segmentation tasks, achieving impressive performance. However, the substantial computational overhead associated with LVLMs presents a new challenge. The primary source of this computational cost arises from processing hundreds of image tokens. Therefore, an effective strategy to mitigate such overhead is to reduce the number of image tokens, a process known as image token pruning. Previous studies on image token pruning for LVLMs have primarily focused on high level visual understanding tasks, such as visual question answering and image captioning. In contrast, guiding vision foundation models to generate accurate visual masks based on textual queries demands precise semantic and spatial reasoning capabilities. Consequently, pruning methods must carefully control individual image tokens throughout the LVLM reasoning process. Our empirical analysis reveals that existing methods struggle to adequately balance reductions in computational overhead with the necessity to maintain high segmentation accuracy. In this work, we propose LVLM_CSP, a novel training free visual token pruning method specifically designed for LVLM based reasoning segmentation tasks. LVLM_CSP consists of three stages: clustering, scattering, and pruning. Initially, the LVLM performs coarse-grained visual reasoning using a subset of selected image tokens. Next, fine grained reasoning is conducted, and finally, most visual tokens are pruned in the last stage. Extensive experiments demonstrate that LVLM_CSP achieves a 65% reduction in image token inference FLOPs with virtually no accuracy degradation, and a 70% reduction with only a minor 1% drop in accuracy on the 7B LVLM.

arXiv:2504.10727

Foundation Models for Remote Sensing: An Analysis of MLLMs for Object Localization

Multimodal large language models (MLLMs) have altered the landscape of computer vision, obtaining impressive results across a wide range of tasks, especially in zero-shot settings. Unfortunately, their strong performance does not always transfer to out-of-distribution domains, such as earth observation (EO) imagery. Prior work has demonstrated that MLLMs excel at some EO tasks, such as image captioning and scene understanding, while failing at tasks that require more fine-grained spatial reasoning, such as object localization. However, MLLMs are advancing rapidly and insights quickly become out-dated. In this work, we analyze more recent MLLMs that have been explicitly trained to include fine-grained spatial reasoning capabilities, benchmarking them on EO object localization tasks. We demonstrate that these models are performant in certain settings, making them well suited for zero-shot scenarios. Additionally, we provide a detailed discussion focused on prompt selection, ground sample distance (GSD) optimization, and analyzing failure cases. We hope that this work will prove valuable as others evaluate whether an MLLM is well suited for a given EO localization task and how to optimize it.

arXiv:2504.10642공식 코드 · Papers with Code

SilVar-Med: A Speech-Driven Visual Language Model for Explainable Abnormality Detection in Medical Imaging

Medical Visual Language Models have shown great potential in various healthcare applications, including medical image captioning and diagnostic assistance. However, most existing models rely on text-based instructions, limiting their usability in real-world clinical environments especially in scenarios such as surgery, text-based interaction is often impractical for physicians. In addition, current medical image analysis models typically lack comprehensive reasoning behind their predictions, which reduces their reliability for clinical decision-making. Given that medical diagnosis errors can have life-changing consequences, there is a critical need for interpretable and rational medical assistance. To address these challenges, we introduce an end-to-end speech-driven medical VLM, SilVar-Med, a multimodal medical image assistant that integrates speech interaction with VLMs, pioneering the task of voice-based communication for medical image analysis. In addition, we focus on the interpretation of the reasoning behind each prediction of medical abnormalities with a proposed reasoning dataset. Through extensive experiments, we demonstrate a proof-of-concept study for reasoning-driven medical image interpretation with end-to-end speech interaction. We believe this work will advance the field of medical AI by fostering more transparent, interactive, and clinically viable diagnostic support systems. Our code and dataset are publicly available at SiVar-Med.

arXiv:2504.11441

TADACap: Time-series Adaptive Domain-Aware Captioning

While image captioning has gained significant attention, the potential of captioning time-series images, prevalent in areas like finance and healthcare, remains largely untapped. Existing time-series captioning methods typically offer generic, domain-agnostic descriptions of time-series shapes and struggle to adapt to new domains without substantial retraining. To address these limitations, we introduce TADACap, a retrieval-based framework to generate domain-aware captions for time-series images, capable of adapting to new domains without retraining. Building on TADACap, we propose a novel retrieval strategy that retrieves diverse image-caption pairs from a target domain database, namely TADACap-diverse. We benchmarked TADACap-diverse against state-of-the-art methods and ablation variants. TADACap-diverse demonstrates comparable semantic accuracy while requiring significantly less annotation effort.

arXiv:2502.14914

What Is a Good Caption? A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness

Visual captioning benchmarks have become outdated with the emergence of modern multimodal large language models (MLLMs), as the brief ground-truth sentences and traditional metrics fail to assess detailed captions effectively. While recent benchmarks attempt to address this by focusing on keyword extraction or object-centric evaluation, they remain limited to vague-view or object-view analyses and incomplete visual element coverage. In this paper, we introduce CAPability, a comprehensive multi-view benchmark for evaluating visual captioning across 12 dimensions spanning six critical views. We curate nearly 11K human-annotated images and videos with visual element annotations to evaluate the generated captions. CAPability stably assesses both the correctness and thoroughness of captions using F1-score. By converting annotations to QA pairs, we further introduce a heuristic metric, \textit{know but cannot tell} ($K\bar{T}$), indicating a significant performance gap between QA and caption capabilities. Our work provides the first holistic analysis of MLLMs' captioning abilities, as we identify their strengths and weaknesses across various dimensions, guiding future research to enhance specific aspects of capabilities.

arXiv:2504.09620

Metropolis-Hastings Captioning Game: Knowledge Fusion of Vision Language Models via Decentralized Bayesian Inference

We propose the Metropolis-Hastings Captioning Game (MHCG), a method to fuse knowledge of multiple vision-language models (VLMs) by learning from each other. Although existing methods that combine multiple models suffer from inference costs and architectural constraints, MHCG avoids these problems by performing decentralized Bayesian inference through a process resembling a language game. The knowledge fusion process establishes communication between two VLM agents alternately captioning images and learning from each other. We conduct two image-captioning experiments with two VLMs, each pre-trained on a different dataset. The first experiment demonstrates that MHCG achieves consistent improvement in reference-free evaluation metrics. The second experiment investigates how MHCG contributes to sharing VLMs' category-level vocabulary by observing the occurrence of the vocabulary in the generated captions.

arXiv:2504.09528

AeroLite: Tag-Guided Lightweight Generation of Aerial Image Captions

Accurate and automated captioning of aerial imagery is crucial for applications like environmental monitoring, urban planning, and disaster management. However, this task remains challenging due to complex spatial semantics and domain variability. To address these issues, we introduce \textbf{AeroLite}, a lightweight, tag-guided captioning framework designed to equip small-scale language models (1--3B parameters) with robust and interpretable captioning capabilities specifically for remote sensing images. \textbf{AeroLite} leverages GPT-4o to generate a large-scale, semantically rich pseudo-caption dataset by integrating multiple remote sensing benchmarks, including DLRSD, iSAID, LoveDA, WHU, and RSSCN7. To explicitly capture key semantic elements such as orientation and land-use types, AeroLite employs natural language processing techniques to extract relevant semantic tags. These tags are then learned by a dedicated multi-label CLIP encoder, ensuring precise semantic predictions. To effectively fuse visual and semantic information, we propose a novel bridging multilayer perceptron (MLP) architecture, aligning semantic tags with visual embeddings while maintaining minimal computational overhead. AeroLite's flexible design also enables seamless integration with various pretrained large language models. We adopt a two-stage LoRA-based training approach: the initial stage leverages our pseudo-caption dataset to capture broad remote sensing semantics, followed by fine-tuning on smaller, curated datasets like UCM and Sydney Captions to refine domain-specific alignment. Experimental evaluations demonstrate that AeroLite surpasses significantly larger models (e.g., 13B parameters) in standard captioning metrics, including BLEU and METEOR, while maintaining substantially lower computational costs.

arXiv:2504.08140

Impact of Language Guidance: A Reproducibility Study

Modern deep-learning architectures need large amounts of data to produce state-of-the-art results. Annotating such huge datasets is time-consuming, expensive, and prone to human error. Recent advances in self-supervised learning allow us to train huge models without explicit annotation. Contrastive learning is a popular paradigm in self-supervised learning. Recent works like SimCLR and CLIP rely on image augmentations or directly minimizing cross-modal loss between image and text. Banani et al. (2023) propose to use language guidance to sample view pairs. They claim that language enables better conceptual similarity, eliminating the effects of visual variability. We reproduce their experiments to verify their claims and find that their dataset, RedCaps, contains low-quality captions. We use an off-the-shelf image captioning model, BLIP-2, to replace the captions and improve performance, and we also devise a new metric to evaluate the semantic capabilities of self-supervised models based on interpretability methods.

arXiv:2504.08583

AstroLLaVA: towards the unification of astronomical data and natural language

We present AstroLLaVA, a vision language model for astronomy that enables interaction with astronomical imagery through natural dialogue. By fine-tuning the LLaVA model on a diverse dataset of $\sim$30k images with captions and question-answer pairs sourced from NASA's `Astronomy Picture of the Day', the European Southern Observatory, and the NASA/ESA Hubble Space Telescope, we create a model capable of answering open-ended questions about astronomical concepts depicted visually. Our two-stage fine-tuning process adapts the model to both image captioning and visual question answering in the astronomy domain. We demonstrate AstroLLaVA's performance on an astronomical visual question answering benchmark and release the model weights, code, and training set to encourage further open source work in this space. Finally, we suggest a roadmap towards general astronomical data alignment with pre-trained language models, and provide an open space for collaboration towards this end for interested researchers.

arXiv:2504.08531

Embodied Image Captioning: Self-supervised Learning Agents for Spatially Coherent Image Descriptions

We present a self-supervised method to improve an agent's abilities in describing arbitrary objects while actively exploring a generic environment. This is a challenging problem, as current models struggle to obtain coherent image captions due to different camera viewpoints and clutter. We propose a three-phase framework to fine-tune existing captioning models that enhances caption accuracy and consistency across views via a consensus mechanism. First, an agent explores the environment, collecting noisy image-caption pairs. Then, a consistent pseudo-caption for each object instance is distilled via consensus using a large language model. Finally, these pseudo-captions are used to fine-tune an off-the-shelf captioning model, with the addition of contrastive learning. We analyse the performance of the combination of captioning models, exploration policies, pseudo-labeling methods, and fine-tuning strategies, on our manually labeled test set. Results show that a policy can be trained to mine samples with higher disagreement compared to classical baselines. Our pseudo-captioning method, in combination with all policies, has a higher semantic similarity compared to other existing methods, and fine-tuning improves caption accuracy and consistency by a significant margin. Code and test set annotations available at https://hsp-iit.github.io/embodied-captioning/