Channel-Level Variable Quantization Network for Deep Image Compression

• URL: http://arxiv.org/abs/2007.12619v1
• Date: Wed, 15 Jul 2020 07:20:39 GMT
• Title: Channel-Level Variable Quantization Network for Deep Image Compression
• Authors: Zhisheng Zhong, Hiroaki Akutsu and Kiyoharu Aizawa
• Abstract summary: 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.
• Score: 50.3174629451739
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep image compression systems mainly contain four components: encoder, quantizer, entropy model, and decoder. To optimize these four components, a joint rate-distortion framework was proposed, and many deep neural network-based methods achieved great success in image compression. However, almost all convolutional neural network-based methods treat channel-wise feature maps equally, reducing the flexibility in handling different types of information. In this paper, we propose a channel-level variable quantization network to dynamically allocate more bitrates for significant channels and withdraw bitrates for negligible channels. Specifically, we propose a variable quantization controller. It consists of two key components: the channel importance module, which can dynamically learn the importance of channels during training, and the splitting-merging module, which can allocate different bitrates for different channels. We also formulate the quantizer into a Gaussian mixture model manner. Quantitative and qualitative experiments verify the effectiveness of the proposed model and demonstrate that our method achieves superior performance and can produce much better visual reconstructions.

Related papers

• Exploring Effective Mask Sampling Modeling for Neural Image Compression [171.35596121939238]
  Most existing neural image compression methods rely on side information from hyperprior or context models to eliminate spatial redundancy. Inspired by the mask sampling modeling in recent self-supervised learning methods for natural language processing and high-level vision, we propose a novel pretraining strategy for neural image compression. Our method achieves competitive performance with lower computational complexity compared to state-of-the-art image compression methods.
  arXiv  Detail & Related papers  (2023-06-09T06:50:20Z)
• Joint Channel Estimation and Feedback with Masked Token Transformers in Massive MIMO Systems [74.52117784544758]
  This paper proposes an encoder-decoder based network that unveils the intrinsic frequency-domain correlation within the CSI matrix. The entire encoder-decoder network is utilized for channel compression. Our method outperforms state-of-the-art channel estimation and feedback techniques in joint tasks.
  arXiv  Detail & Related papers  (2023-06-08T06:15:17Z)
• Convolutional Neural Network with Convolutional Block Attention Module for Finger Vein Recognition [4.035753155957698]
  We propose a lightweight convolutional neural network with a convolutional block attention module (CBAM) for finger vein recognition. The experiments are carried out on two publicly available databases and the results demonstrate that the proposed method achieves a stable, highly accurate, and robust performance in multimodal finger recognition.
  arXiv  Detail & Related papers  (2022-02-14T12:59:23Z)
• Exploring Structural Sparsity in Neural Image Compression [14.106763725475469]
  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.
  arXiv  Detail & Related papers  (2022-02-09T17:46:49Z)
• 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)
• MWQ: Multiscale Wavelet Quantized Neural Networks [45.22093693422084]
  We propose a novel multiscale wavelet quantization (MWQ) method inspired by the characteristics of images in the frequency domain. It exploits the multiscale frequency and spatial information to alleviate the information loss caused by quantization in the spatial domain. Because of the flexibility of MWQ, we demonstrate three applications on the ImageNet and COCO datasets.
  arXiv  Detail & Related papers  (2021-03-09T11:21:59Z)
• Learned Multi-Resolution Variable-Rate Image Compression with Octave-based Residual Blocks [15.308823742699039]
  We propose a new variable-rate image compression framework, which employs generalized octave convolutions (GoConv) and generalized octave transposed-convolutions (GoTConv) To enable a single model to operate with different bit rates and to learn multi-rate image features, a new objective function is introduced. Experimental results show that the proposed framework trained with variable-rate objective function outperforms the standard codecs such as H.265/HEVC-based BPG and state-of-the-art learning-based variable-rate methods.
  arXiv  Detail & Related papers  (2020-12-31T06:26:56Z)
• Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks [73.29587731448345]
  This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations. First, to obtain low bit-width weights, most existing methods obtain the quantized weights by performing quantization on the full-precision network weights. Second, to obtain low bit-width activations, existing works consider all channels equally.
  arXiv  Detail & Related papers  (2020-12-26T15:21:18Z)
• Operation-Aware Soft Channel Pruning using Differentiable Masks [51.04085547997066]
  We propose a data-driven algorithm, which compresses deep neural networks in a differentiable way by exploiting the characteristics of operations. We perform extensive experiments and achieve outstanding performance in terms of the accuracy of output networks.
  arXiv  Detail & Related papers  (2020-07-08T07:44:00Z)

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.