Exploring Structural Sparsity in Neural Image Compression

• URL: http://arxiv.org/abs/2202.04595v2
• Date: Thu, 10 Feb 2022 07:46:42 GMT
• Title: Exploring Structural Sparsity in Neural Image Compression
• Authors: Shanzhi Yin, Fanyang Meng, Wen Tan, Chao Li, Youneng Bao, Yongsheng Liang, Wei Liu
• Abstract summary: We propose a plug-in adaptive binary channel masking(ABCM) to judge the importance of each convolution channel and introduce sparsity during training. During inference, the unimportant channels are pruned to obtain slimmer network and less computation. Experiment results show that up to 7x computation reduction and 3x acceleration can be achieved with negligible performance drop.
• Score: 14.106763725475469
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Neural image compression have reached or out-performed traditional methods (such as JPEG, BPG, WebP). However,their sophisticated network structures with cascaded convolution layers bring heavy computational burden for practical deployment. In this paper, we explore the structural sparsity in neural image compression network to obtain real-time acceleration without any specialized hardware design or algorithm. We propose a simple plug-in adaptive binary channel masking(ABCM) to judge the importance of each convolution channel and introduce sparsity during training. During inference, the unimportant channels are pruned to obtain slimmer network and less computation. We implement our method into three neural image compression networks with different entropy models to verify its effectiveness and generalization, the experiment results show that up to 7x computation reduction and 3x acceleration can be achieved with negligible performance drop.

Related papers

• Streaming Lossless Volumetric Compression of Medical Images Using Gated Recurrent Convolutional Neural Network [0.0]
  This paper introduces a hardware-friendly streaming lossless volumetric compression framework. We propose a gated recurrent convolutional neural network that combines diverse convolutional structures and fusion gate mechanisms. Our method exhibits robust generalization ability and competitive compression speed.
  arXiv  Detail & Related papers  (2023-11-27T07:19:09Z)
• Deep Multi-Threshold Spiking-UNet for Image Processing [51.88730892920031]
  This paper introduces the novel concept of Spiking-UNet for image processing, which combines the power of Spiking Neural Networks (SNNs) with the U-Net architecture. To achieve an efficient Spiking-UNet, we face two primary challenges: ensuring high-fidelity information propagation through the network via spikes and formulating an effective training strategy. Experimental results show that, on image segmentation and denoising, our Spiking-UNet achieves comparable performance to its non-spiking counterpart.
  arXiv  Detail & Related papers  (2023-07-20T16:00:19Z)
• Modality-Agnostic Variational Compression of Implicit Neural Representations [96.35492043867104]
  We introduce a modality-agnostic neural compression algorithm based on a functional view of data and parameterised as an Implicit Neural Representation (INR) Bridging the gap between latent coding and sparsity, we obtain compact latent representations non-linearly mapped to a soft gating mechanism. After obtaining a dataset of such latent representations, we directly optimise the rate/distortion trade-off in a modality-agnostic space using neural compression.
  arXiv  Detail & Related papers  (2023-01-23T15:22:42Z)
• Wavelet Feature Maps Compression for Image-to-Image CNNs [3.1542695050861544]
  We propose a novel approach for high-resolution activation maps compression integrated with point-wise convolutions. We achieve compression rates equivalent to 1-4bit activation quantization with relatively small and much more graceful degradation in performance.
  arXiv  Detail & Related papers  (2022-05-24T20:29:19Z)
• Reducing Redundancy in the Bottleneck Representation of the Autoencoders [98.78384185493624]
  Autoencoders are a type of unsupervised neural networks, which can be used to solve various tasks. We propose a scheme to explicitly penalize feature redundancies in the bottleneck representation. We tested our approach across different tasks: dimensionality reduction using three different dataset, image compression using the MNIST dataset, and image denoising using fashion MNIST.
  arXiv  Detail & Related papers  (2022-02-09T18:48:02Z)
• Self-supervised Neural Networks for Spectral Snapshot Compressive Imaging [15.616674529295366]
  We consider using untrained neural networks to solve the reconstruction problem of snapshot compressive imaging (SCI) In this paper, inspired by the untrained neural networks such as deep image priors (DIP) and deep decoders, we develop a framework by integrating DIP into the plug-and-play regime, leading to a self-supervised network for spectral SCI reconstruction.
  arXiv  Detail & Related papers  (2021-08-28T14:17:38Z)
• Group Fisher Pruning for Practical Network Compression [58.25776612812883]
  We present a general channel pruning approach that can be applied to various complicated structures. We derive a unified metric based on Fisher information to evaluate the importance of a single channel and coupled channels. Our method can be used to prune any structures including those with coupled channels.
  arXiv  Detail & Related papers  (2021-08-02T08:21:44Z)
• Image Complexity Guided Network Compression for Biomedical Image Segmentation [5.926887379656135]
  We propose an image complexity-guided network compression technique for biomedical image segmentation. We map the dataset complexity to the target network accuracy degradation caused by compression. The mapping is used to determine the convolutional layer-wise multiplicative factor for generating a compressed network.
  arXiv  Detail & Related papers  (2021-07-06T22:28:10Z)
• On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures [17.349420462716886]
  This study investigates the impact of commonplace image and video compression techniques on the performance of deep learning architectures. We examine the impact on performance across five discrete tasks: human pose estimation, semantic segmentation, object detection, action recognition, and monocular depth estimation. Results show a non-linear and non-uniform relationship between network performance and the level of lossy compression applied.
  arXiv  Detail & Related papers  (2020-07-28T15:37:37Z)
• Channel-Level Variable Quantization Network for Deep Image Compression [50.3174629451739]
  We propose a channel-level variable quantization network to dynamically allocate more convolutions for significant channels and withdraws for negligible channels. Our method achieves superior performance and can produce much better visual reconstructions.
  arXiv  Detail & Related papers  (2020-07-15T07:20:39Z)
• Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle [117.95823660228537]
  We propose a novel structured sparsification method for efficient network compression. The proposed method automatically induces structured sparsity on the convolutional weights. We also address the problem of inter-group communication with a learnable channel shuffle mechanism.
  arXiv  Detail & Related papers  (2020-02-19T12:03:10Z)

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.