Focus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding

• URL: http://arxiv.org/abs/2603.22815v1
• Date: Tue, 24 Mar 2026 05:37:01 GMT
• Title: Focus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding
• Abstract summary: PinPoint is a framework that first identifies instruction-relevant image regions and then refines them to extract fine-grained visual features.<n>New annotations provide richer ground-truth supervision for instruction-relevant regions across challenging VQA benchmarks.
• Score: 15.310650411597727
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Vision-Language Models (LVLMs) have shown strong performance across various multimodal tasks by leveraging the reasoning capabilities of Large Language Models (LLMs). However, processing visually complex and information-rich images, such as infographics or document layouts, requires these models to generate a large number of visual tokens, leading to significant computational overhead. To address this, we propose PinPoint, a novel two-stage framework that first identifies instruction-relevant image regions and then refines them to extract fine-grained visual features for improved reasoning and efficiency. Central to our approach is the Instruction-Region Alignment, which localizes relevant regions using both visual input and textual instructions. We further introduce new annotations that provide richer ground-truth supervision for instruction-relevant regions across challenging VQA benchmarks: InfographicVQA, MultiPageDocVQA, and SinglePageDocVQA. Experimental results show that PinPoint not only achieves superior accuracy compared to existing methods but also reduces computational overhead by minimizing irrelevant visual tokens.

Related papers

• Learning to See What You Need: Gaze Attention for Multimodal Large Language Models [96.20985292033465]
  We introduce Gaze Attention, a novel mechanism that enables MLLMs to selectively attend to task-relevant visual regions during generation.<n>We show that Gaze Attention matches or surpasses dense-attention baselines, while using up to 90% fewer visual KV entries in the attention computation.
  arXiv  Detail & Related papers  (2026-05-13T06:54:09Z)
• Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment [66.80402022104074]
  We propose a Text Refinement and Alignment (TRA) framework that effectively utilizes textual features from visual descriptions to complement the visual features as they are semantically rich.<n>This is achieved by designing two new modules for the original point-supervised framework: a Point-based Text Refinement module (PTR) and a Point-based Multimodal Alignment module (PMA)
  arXiv  Detail & Related papers  (2026-02-01T14:35:46Z)
• When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought [118.71264263478083]
  We propose MIRA, a new benchmark designed to evaluate models in scenarios where generating intermediate visual images is essential for successful reasoning.<n>We include 546 multimodal problems, annotated with intermediate visual images and final answers.
  arXiv  Detail & Related papers  (2025-11-04T18:00:51Z)
• Pyramid Token Pruning for High-Resolution Large Vision-Language Models via Region, Token, and Instruction-Guided Importance [60.028070589466445]
  Pyramid Token Pruning (PTP) is a training-free strategy that hierarchically integrates bottom-up visual saliency at both region and token levels with top-down instruction-guided relevance.<n>We show that PTP substantially reduces computational cost, memory usage, and inference latency, with negligible performance degradation.
  arXiv  Detail & Related papers  (2025-09-19T07:28:17Z)
• CROP: Contextual Region-Oriented Visual Token Pruning [9.099029419132775]
  Contextual Region-Oriented Visual Token Pruning (CROP) is a novel framework to compress visual tokens.<n>Two distinct strategies are introduced for pruning: (1) Pre-LLM Compression (PLC), which adaptively compresses different image regions with varying ratios, and (2) Inner-LLM Pruning (ILP), a training-free method that prunes tokens within early layers guided by the identified contextual region.
  arXiv  Detail & Related papers  (2025-05-27T14:16:52Z)
• Enhancing Visual Representation for Text-based Person Searching [9.601697802095119]
  VFE-TPS is a Visual Feature Enhanced Text-based Person Search model.<n>It introduces a pre-trained backbone CLIP to learn basic multimodal features.<n>It constructs Text Guided Masked Image Modeling task to enhance the model's ability of learning local visual details.
  arXiv  Detail & Related papers  (2024-12-30T01:38:14Z)
• Attention Prompting on Image for Large Vision-Language Models [63.794304207664176]
  We propose a new prompting technique named Attention Prompting on Image. We generate an attention heatmap for the input image dependent on the text query with an auxiliary model like CLIP. Experiments on various vison-language benchmarks verify the effectiveness of our technique.
  arXiv  Detail & Related papers  (2024-09-25T17:59:13Z)
• Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning [40.972648044298374]
  Multi-Modal Large Language Models (MLLMs) have demonstrated impressive performance in various VQA tasks. They often lack interpretability and struggle with complex visual inputs. We introduce the large-scale Visual CoT dataset comprising 438k question-answer pairs. We propose a multi-turn processing pipeline that dynamically focuses on visual inputs and provides interpretable thoughts.
  arXiv  Detail & Related papers  (2024-03-25T17:59:23Z)
• Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models [81.71651422951074]
  Chain-of-Spot (CoS) method is a novel approach that enhances feature extraction by focusing on key regions of interest. This technique allows LVLMs to access more detailed visual information without altering the original image resolution. Our empirical findings demonstrate a significant improvement in LVLMs' ability to understand and reason about visual content.
  arXiv  Detail & Related papers  (2024-03-19T17:59:52Z)
• GeoVLN: Learning Geometry-Enhanced Visual Representation with Slot Attention for Vision-and-Language Navigation [52.65506307440127]
  We propose GeoVLN, which learns Geometry-enhanced visual representation based on slot attention for robust Visual-and-Language Navigation. We employ V&L BERT to learn a cross-modal representation that incorporate both language and vision informations.
  arXiv  Detail & Related papers  (2023-05-26T17:15:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.