paper-with-me

Papers

When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning

2025-03-10 · Junwei Luo, Yingying Zhang, Xue Yang, Kang Wu, Qi Zhu, Lei Liang, Jingdong Chen, Yansheng Li

Efficient vision-language understanding of large Remote Sensing Images (RSIs) is meaningful but challenging. Current Large Vision-Language Models (LVLMs) typically employ limited pre-defined grids to process images, leading to information loss when handling gigapixel RSIs. Conversely, using unlimited grids significantly increases computational costs. To preserve image details while reducing computational complexity, we propose a text-guided token pruning method with Dynamic Image Pyramid (DIP) integration. Our method introduces: (i) a Region Focus Module (RFM) that leverages text-aware region localization capability to identify critical vision tokens, and (ii) a coarse-to-fine image tile selection and vision token pruning strategy based on DIP, which is guided by RFM outputs and avoids directly processing the entire large imagery. Additionally, existing benchmarks for evaluating LVLMs' perception ability on large RSI suffer from limited question diversity and constrained image sizes. We construct a new benchmark named LRS-VQA, which contains 7,333 QA pairs across 8 categories, with image length up to 27,328 pixels. Our method outperforms existing high-resolution strategies on four datasets using the same data. Moreover, compared to existing token reduction methods, our approach demonstrates higher efficiency under high-resolution settings. Dataset and code are in https://github.com/VisionXLab/LRS-VQA.

📄 PDF Abstract BibTeX arXiv:2503.07588

Code (1)

visionxlab/lrs-vqa 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingToken ReductionVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

Focus 설명 없음
Pruning 설명 없음

Similar Papers 제목 키워드 기반

Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning

2022-07-15 · Shibani Santurkar, Yann Dubois, Rohan Taori, Percy Liang 외

The development of CLIP [Radford et al., 2021] has sparked a debate on whether language supervision can result in vision models with more transferable representations than traditional image-only methods. Our work studies…

DescriptiveRepresentation Learning

Graph Meets LLMs: Towards Large Graph Models

2023-08-28 · Ziwei Zhang, Haoyang Li, Zeyang Zhang, Yijian Qin 외

Large models have emerged as the most recent groundbreaking achievements in artificial intelligence, and particularly machine learning. However, when it comes to graphs, large models have not achieved the same level of s…

When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach

2024-01-01 · CVPR 2024 1 · Tao Ma, Bing Bai, Haozhe Lin, Heyuan Wang 외

Visual grounding refers to the process of associating natural language expressions with corresponding regions within an image. Existing benchmarks for visual grounding primarily operate within small-scale scenes with…

Scene UnderstandingVisual Grounding

Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning

2024-05-31 · Cheng Tan, Jingxuan Wei, Linzhuang Sun, Zhangyang Gao 외

Large language models equipped with retrieval-augmented generation (RAG) represent a burgeoning field aimed at enhancing answering capabilities by leveraging external knowledge bases. Although the application of RAG with…

Answer GenerationMultimodal ReasoningRAGRetrieval+1

Watchdogs and Oracles: Runtime Verification Meets Large Language Models for Autonomous Systems

2025-11-18 · Angelo Ferrando arxiv

Assuring the safety and trustworthiness of autonomous systems is particularly difficult when learning-enabled components and open environments are involved. Formal methods provide strong guarantees but depend on complete…