Compress image to patches for Vision Transformer

• URL: http://arxiv.org/abs/2502.10120v2
• Date: Mon, 17 Feb 2025 07:35:28 GMT
• Title: Compress image to patches for Vision Transformer
• Authors: Xinfeng Zhao, Yaoru Sun,
• Abstract summary: This paper proposes a hybrid model based on CNN and Vision Transformer, named CI2P-ViT. The model incorporates a module called CI2P, which utilizes the CompressAI encoder to compress images and subsequently generates a sequence of patches through a series of convolutions. When trained from the ground up on the Animals-10 dataset, CI2P-ViT achieved an accuracy rate of 92.37%, representing a 3.3% improvement over the ViT-B/16 baseline.
• Score: 0.0
• License:
• Abstract: The Vision Transformer (ViT) has made significant strides in the field of computer vision. However, as the depth of the model and the resolution of the input images increase, the computational cost associated with training and running ViT models has surged dramatically. This paper proposes a hybrid model based on CNN and Vision Transformer, named CI2P-ViT. The model incorporates a module called CI2P, which utilizes the CompressAI encoder to compress images and subsequently generates a sequence of patches through a series of convolutions. CI2P can replace the Patch Embedding component in the ViT model, enabling seamless integration into existing ViT models. Compared to ViT-B/16, CI2P-ViT has the number of patches input to the self-attention layer reduced to a quarter of the original. This design not only significantly reduces the computational cost of the ViT model but also effectively enhances the model's accuracy by introducing the inductive bias properties of CNN. The ViT model's precision is markedly enhanced. When trained from the ground up on the Animals-10 dataset, CI2P-ViT achieved an accuracy rate of 92.37%, representing a 3.3% improvement over the ViT-B/16 baseline. Additionally, the model's computational operations, measured in floating-point operations per second (FLOPs), were diminished by 63.35%, and it exhibited a 2-fold increase in training velocity on identical hardware configurations.

Related papers

• DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices [42.89175608336226]
  Vision transformer (ViT) has achieved state-of-the-art performance on multiple computer vision benchmarks. ViT models suffer from vast amounts of parameters and high computation cost, leading to difficult deployment on resource-constrained edge devices. We propose a collaborative inference framework termed DeViT to facilitate edge deployment by decomposing large ViTs.
  arXiv  Detail & Related papers  (2023-09-10T12:26:17Z)
• Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design [84.34416126115732]
  Scaling laws have been recently employed to derive compute-optimal model size (number of parameters) for a given compute duration. We advance and refine such methods to infer compute-optimal model shapes, such as width and depth, and successfully implement this in vision transformers. Our shape-optimized vision transformer, SoViT, achieves results competitive with models that exceed twice its size, despite being pre-trained with an equivalent amount of compute.
  arXiv  Detail & Related papers  (2023-05-22T13:39:28Z)
• MiniViT: Compressing Vision Transformers with Weight Multiplexing [88.54212027516755]
  Vision Transformer (ViT) models have recently drawn much attention in computer vision due to their high model capability. MiniViT is a new compression framework, which achieves parameter reduction in vision transformers while retaining the same performance.
  arXiv  Detail & Related papers  (2022-04-14T17:59:05Z)
• Improving Vision Transformers by Revisiting High-frequency Components [106.7140968644414]
  We show that Vision Transformer (ViT) models are less effective in capturing the high-frequency components of images than CNN models. To compensate, we propose HAT, which directly augments high-frequency components of images via adversarial training. We show that HAT can consistently boost the performance of various ViT models.
  arXiv  Detail & Related papers  (2022-04-03T05:16:51Z)
• Coarse-to-Fine Vision Transformer [83.45020063642235]
  We propose a coarse-to-fine vision transformer (CF-ViT) to relieve computational burden while retaining performance. Our proposed CF-ViT is motivated by two important observations in modern ViT models. Our CF-ViT reduces 53% FLOPs of LV-ViT, and also achieves 2.01x throughput.
  arXiv  Detail & Related papers  (2022-03-08T02:57:49Z)
• A Unified Pruning Framework for Vision Transformers [40.7622551128182]
  Vision transformer (ViT) and its variants have achieved promising performances in various computer vision tasks. We propose a unified framework for structural pruning of both ViTs and its variants, namely UP-ViTs. Our method focuses on pruning all ViTs components while maintaining the consistency of the model structure.
  arXiv  Detail & Related papers  (2021-11-30T05:01:02Z)
• Early Convolutions Help Transformers See Better [63.21712652156238]
  Vision transformer (ViT) models exhibit substandard optimizability. Modern convolutional neural networks are far easier to optimize. Using a convolutional stem in ViT dramatically increases optimization stability and also improves peak performance.
  arXiv  Detail & Related papers  (2021-06-28T17:59:33Z)
• DeepViT: Towards Deeper Vision Transformer [92.04063170357426]
  Vision transformers (ViTs) have been successfully applied in image classification tasks recently. We show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the performance of ViTs saturate fast when scaled to be deeper. We propose a simple yet effective method, named Re-attention, to re-generate the attention maps to increase their diversity.
  arXiv  Detail & Related papers  (2021-03-22T14:32:07Z)

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.