HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models

• URL: http://arxiv.org/abs/2407.08706v1
• Date: Thu, 11 Jul 2024 17:42:17 GMT
• Title: HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models
• Authors: Runhui Huang, Xinpeng Ding, Chunwei Wang, Jianhua Han, Yulong Liu, Hengshuang Zhao, Hang Xu, Lu Hou, Wei Zhang, Xiaodan Liang,
• Abstract summary: HiRes-LLaVA is a novel framework designed to process any size of high-resolution input without altering the original contextual and geometric information. HiRes-LLaVA comprises two innovative components: (i) a SliceRestore adapter that reconstructs sliced patches into their original form, efficiently extracting both global and local features via down-up-sampling and convolution layers, and (ii) a Self-Mining Sampler to compress the vision tokens based on themselves.
• Score: 96.76995840807615
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-resolution inputs enable Large Vision-Language Models (LVLMs) to discern finer visual details, enhancing their comprehension capabilities. To reduce the training and computation costs caused by high-resolution input, one promising direction is to use sliding windows to slice the input into uniform patches, each matching the input size of the well-trained vision encoder. Although efficient, this slicing strategy leads to the fragmentation of original input, i.e., the continuity of contextual information and spatial geometry is lost across patches, adversely affecting performance in cross-patch context perception and position-specific tasks. To overcome these shortcomings, we introduce HiRes-LLaVA, a novel framework designed to efficiently process any size of high-resolution input without altering the original contextual and geometric information. HiRes-LLaVA comprises two innovative components: (i) a SliceRestore adapter that reconstructs sliced patches into their original form, efficiently extracting both global and local features via down-up-sampling and convolution layers, and (ii) a Self-Mining Sampler to compresses the vision tokens based on themselves, preserving the original context and positional information while reducing training overhead. To assess the ability of handling context fragmentation, we construct a new benchmark, EntityGrid-QA, consisting of edge-related and position-related tasks. Our comprehensive experiments demonstrate the superiority of HiRes-LLaVA on both existing public benchmarks and on EntityGrid-QA, particularly on document-oriented tasks, establishing new standards for handling high-resolution inputs.

Related papers

• Dynamic Integration of Task-Specific Adapters for Class Incremental Learning [31.67570086108542]
  Non-exemplar class Incremental Learning (NECIL) enables models to continuously acquire new classes without retraining from scratch and storing old task exemplars. We propose a novel framework called Dynamic Integration of task-specific Adapters (DIA), which comprises two key components: Task-Specific Adapter Integration (TSAI) and Patch-Level Model Alignment.
  arXiv  Detail & Related papers  (2024-09-23T13:01:33Z)
• Any Image Restoration with Efficient Automatic Degradation Adaptation [132.81912195537433]
  We propose a unified manner to achieve joint embedding by leveraging the inherent similarities across various degradations for efficient and comprehensive restoration. Our network sets new SOTA records while reducing model complexity by approximately -82% in trainable parameters and -85% in FLOPs.
  arXiv  Detail & Related papers  (2024-07-18T10:26:53Z)
• Looking for Tiny Defects via Forward-Backward Feature Transfer [12.442574943138794]
  We introduce a novel benchmark that evaluates methods on the original, high-resolution image and ground-truth masks. Our benchmark includes a metric that captures robustness with respect to defect size. Our proposal features the highest robustness to defect size, runs at the fastest speed and yields state-of-the-art segmentation performance.
  arXiv  Detail & Related papers  (2024-07-04T17:59:26Z)
• UGMAE: A Unified Framework for Graph Masked Autoencoders [67.75493040186859]
  We propose UGMAE, a unified framework for graph masked autoencoders. We first develop an adaptive feature mask generator to account for the unique significance of nodes. We then design a ranking-based structure reconstruction objective joint with feature reconstruction to capture holistic graph information.
  arXiv  Detail & Related papers  (2024-02-12T19:39:26Z)
• Low-Resolution Self-Attention for Semantic Segmentation [96.81482872022237]
  We introduce the Low-Resolution Self-Attention (LRSA) mechanism to capture global context at a significantly reduced computational cost. Our approach involves computing self-attention in a fixed low-resolution space regardless of the input image's resolution. We demonstrate the effectiveness of our LRSA approach by building the LRFormer, a vision transformer with an encoder-decoder structure.
  arXiv  Detail & Related papers  (2023-10-08T06:10:09Z)
• ClusVPR: Efficient Visual Place Recognition with Clustering-based Weighted Transformer [13.0858576267115]
  We present ClusVPR, a novel approach that tackles the specific issues of redundant information in duplicate regions and representations of small objects. ClusVPR introduces a unique paradigm called Clustering-based weighted Transformer Network (CWTNet) We also introduce the optimized-VLAD layer that significantly reduces the number of parameters and enhances model efficiency.
  arXiv  Detail & Related papers  (2023-10-06T09:01:15Z)
• Vision Transformer with Quadrangle Attention [76.35955924137986]
  We propose a novel quadrangle attention (QA) method that extends the window-based attention to a general quadrangle formulation. Our method employs an end-to-end learnable quadrangle regression module that predicts a transformation matrix to transform default windows into target quadrangles. We integrate QA into plain and hierarchical vision transformers to create a new architecture named QFormer, which offers minor code modifications and negligible extra computational cost.
  arXiv  Detail & Related papers  (2023-03-27T11:13:50Z)
• Rethinking Query-Key Pairwise Interactions in Vision Transformers [5.141895475956681]
  We propose key-only attention, which excludes query-key pairwise interactions and uses a compute-efficient saliency-gate to obtain attention weights. We develop a new self-attention model family, LinGlos, which reach state-of-the-art accuracies on the parameter-limited setting of ImageNet classification benchmark.
  arXiv  Detail & Related papers  (2022-07-01T03:36:49Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)

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.