big.LITTLE Vision Transformer for Efficient Visual Recognition

• URL: http://arxiv.org/abs/2410.10267v1
• Date: Mon, 14 Oct 2024 08:21:00 GMT
• Title: big.LITTLE Vision Transformer for Efficient Visual Recognition
• Authors: He Guo, Yulong Wang, Zixuan Ye, Jifeng Dai, Yuwen Xiong,
• Abstract summary: big.LITTLE Vision Transformer is an innovative architecture aimed at achieving efficient visual recognition. System is composed of two distinct blocks: the big performance block and the LITTLE efficiency block. When processing an image, our system determines the importance of each token and allocates them accordingly.
• Score: 34.015778625984055
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we introduce the big.LITTLE Vision Transformer, an innovative architecture aimed at achieving efficient visual recognition. This dual-transformer system is composed of two distinct blocks: the big performance block, characterized by its high capacity and substantial computational demands, and the LITTLE efficiency block, designed for speed with lower capacity. The key innovation of our approach lies in its dynamic inference mechanism. When processing an image, our system determines the importance of each token and allocates them accordingly: essential tokens are processed by the high-performance big model, while less critical tokens are handled by the more efficient little model. This selective processing significantly reduces computational load without sacrificing the overall performance of the model, as it ensures that detailed analysis is reserved for the most important information. To validate the effectiveness of our big.LITTLE Vision Transformer, we conducted comprehensive experiments on image classification and segment anything task. Our results demonstrate that the big.LITTLE architecture not only maintains high accuracy but also achieves substantial computational savings. Specifically, our approach enables the efficient handling of large-scale visual recognition tasks by dynamically balancing the trade-offs between performance and efficiency. The success of our method underscores the potential of hybrid models in optimizing both computation and performance in visual recognition tasks, paving the way for more practical and scalable deployment of advanced neural networks in real-world applications.

Related papers

• CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction [77.8576094863446]
  We propose a new detextbfCoupled dutextbfAl-interactive lineatextbfR atttextbfEntion (CARE) mechanism. We first propose an asymmetrical feature decoupling strategy that asymmetrically decouples the learning process for local inductive bias and long-range dependencies. By adopting a decoupled learning way and fully exploiting complementarity across features, our method can achieve both high efficiency and accuracy.
  arXiv  Detail & Related papers  (2024-11-25T07:56:13Z)
• FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression [45.37530855889661]
  High-resolution images lead to a quadratic increase in the number of visual tokens input into Multi-modal Large Language Models. Current work develop visual token compression methods to achieve efficiency improvements, often at the expense of performance. We build a coarse-to-fine visual token compression method, with a vision-guided sampler for compressing redundant regions with low information density, and a text-guided sampler for selecting visual tokens that are strongly correlated with the user instructions.
  arXiv  Detail & Related papers  (2024-11-21T15:37:52Z)
• Shuffle Vision Transformer: Lightweight, Fast and Efficient Recognition of Driver Facial Expression [4.034679618136641]
  Existing methods for driver facial expression recognition (DFER) are often computationally intensive, rendering them unsuitable for real-time applications. We introduce a novel transfer learning-based dual architecture, named ShuffViT-DFER, which elegantly combines computational efficiency and accuracy.
  arXiv  Detail & Related papers  (2024-09-05T11:39:43Z)
• Dyn-Adapter: Towards Disentangled Representation for Efficient Visual Recognition [22.615830919860777]
  This paper presents an efficient visual recognition paradigm, called Dynamic Adapter (Dyn-Adapter) We devise a dynamic architecture with balanced early heads for multi-level feature extraction, along with adaptive training strategy. We reduce FLOPs during inference by 50%, while maintaining or even yielding higher recognition accuracy.
  arXiv  Detail & Related papers  (2024-07-19T13:33:38Z)
• A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking [19.65897437342896]
  Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. This paper mathematically defines the strategies used to make Vision Transformer efficient, describes and discusses state-of-the-art methodologies, and analyzes their performances over different application scenarios.
  arXiv  Detail & Related papers  (2023-09-05T08:21:16Z)
• E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning [55.50908600818483]
  Fine-tuning large-scale pretrained vision models for new tasks has become increasingly parameter-intensive. We propose an Effective and Efficient Visual Prompt Tuning (E2VPT) approach for large-scale transformer-based model adaptation. Our approach outperforms several state-of-the-art baselines on two benchmarks.
  arXiv  Detail & Related papers  (2023-07-25T19:03:21Z)
• Skip-Attention: Improving Vision Transformers by Paying Less Attention [55.47058516775423]
  Vision computation transformers (ViTs) use expensive self-attention operations in every layer. We propose SkipAt, a method to reuse self-attention from preceding layers to approximate attention at one or more subsequent layers. We show the effectiveness of our method in image classification and self-supervised learning on ImageNet-1K, semantic segmentation on ADE20K, image denoising on SIDD, and video denoising on DAVIS.
  arXiv  Detail & Related papers  (2023-01-05T18:59:52Z)
• Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks [88.77951448313486]
  We present a new approach for model acceleration by exploiting spatial sparsity in visual data. We propose a dynamic token sparsification framework to prune redundant tokens. We extend our method to hierarchical models including CNNs and hierarchical vision Transformers.
  arXiv  Detail & Related papers  (2022-07-04T17:00:51Z)
• Activating More Pixels in Image Super-Resolution Transformer [53.87533738125943]
  Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. We propose a novel Hybrid Attention Transformer (HAT) to activate more input pixels for better reconstruction. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB.
  arXiv  Detail & Related papers  (2022-05-09T17:36:58Z)
• AdaViT: Adaptive Vision Transformers for Efficient Image Recognition [78.07924262215181]
  We introduce AdaViT, an adaptive framework that learns to derive usage policies on which patches, self-attention heads and transformer blocks to use. Our method obtains more than 2x improvement on efficiency compared to state-of-the-art vision transformers with only 0.8% drop of accuracy.
  arXiv  Detail & Related papers  (2021-11-30T18:57:02Z)
• Hierarchical Residual Attention Network for Single Image Super-Resolution [2.0571256241341924]
  This paper introduces a new lightweight super-resolution model based on an efficient method for residual feature and attention aggregation. Our proposed architecture surpasses state-of-the-art performance in several datasets, while maintaining relatively low computation and memory footprint.
  arXiv  Detail & Related papers  (2020-12-08T17:24:28Z)

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.