Dynamic Slimmable Denoising Network

• URL: http://arxiv.org/abs/2110.08940v1
• Date: Sun, 17 Oct 2021 22:45:33 GMT
• Title: Dynamic Slimmable Denoising Network
• Authors: Zutao Jiang and Changlin Li and Xiaojun Chang and Jihua Zhu and Yi Yang
• Abstract summary: Dynamic slimmable denoising network (DDSNet) is a general method to achieve good denoising quality with less computational complexity. OurNet is empowered with the ability of dynamic inference by a dynamic gate. Our experiments demonstrate our-Net consistently outperforms the state-of-the-art individually trained static denoising networks.
• Score: 64.77565006158895
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, tremendous human-designed and automatically searched neural networks have been applied to image denoising. However, previous works intend to handle all noisy images in a pre-defined static network architecture, which inevitably leads to high computational complexity for good denoising quality. Here, we present dynamic slimmable denoising network (DDS-Net), a general method to achieve good denoising quality with less computational complexity, via dynamically adjusting the channel configurations of networks at test time with respect to different noisy images. Our DDS-Net is empowered with the ability of dynamic inference by a dynamic gate, which can predictively adjust the channel configuration of networks with negligible extra computation cost. To ensure the performance of each candidate sub-network and the fairness of the dynamic gate, we propose a three-stage optimization scheme. In the first stage, we train a weight-shared slimmable super network. In the second stage, we evaluate the trained slimmable super network in an iterative way and progressively tailor the channel numbers of each layer with minimal denoising quality drop. By a single pass, we can obtain several sub-networks with good performance under different channel configurations. In the last stage, we identify easy and hard samples in an online way and train a dynamic gate to predictively select the corresponding sub-network with respect to different noisy images. Extensive experiments demonstrate our DDS-Net consistently outperforms the state-of-the-art individually trained static denoising networks.

Related papers

• Image Blind Denoising Using Dual Convolutional Neural Network with Skip Connection [2.9689285167236603]
  We propose a novel dual convolutional blind denoising network with skip connection (DCBDNet) The proposed DCBDNet consists of a noise estimation network and a dual convolutional neural network (CNN)
  arXiv  Detail & Related papers  (2023-04-04T08:21:46Z)
• Real-time Controllable Denoising for Image and Video [44.68523669975698]
  Controllable image denoising aims to generate clean samples with human priors and balance sharpness and smoothness. We introduce Real-time Controllable Denoising (RCD), the first deep image and video denoising pipeline. RCD provides a fully controllable user interface to edit arbitrary denoising levels in real-time with only one-time network inference.
  arXiv  Detail & Related papers  (2023-03-29T03:10:28Z)
• Multi-stage image denoising with the wavelet transform [125.2251438120701]
  Deep convolutional neural networks (CNNs) are used for image denoising via automatically mining accurate structure information. We propose a multi-stage image denoising CNN with the wavelet transform (MWDCNN) via three stages, i.e., a dynamic convolutional block (DCB), two cascaded wavelet transform and enhancement blocks (WEBs) and residual block (RB)
  arXiv  Detail & Related papers  (2022-09-26T03:28:23Z)
• Interference Cancellation GAN Framework for Dynamic Channels [74.22393885274728]
  We introduce an online training framework that can adapt to any changes in the channel. Our framework significantly outperforms recent neural network models on highly dynamic channels.
  arXiv  Detail & Related papers  (2022-08-17T02:01:18Z)
• A Study of Designing Compact Audio-Visual Wake Word Spotting System Based on Iterative Fine-Tuning in Neural Network Pruning [57.28467469709369]
  We investigate on designing a compact audio-visual wake word spotting (WWS) system by utilizing visual information. We introduce a neural network pruning strategy via the lottery ticket hypothesis in an iterative fine-tuning manner (LTH-IF) The proposed audio-visual system achieves significant performance improvements over the single-modality (audio-only or video-only) system under different noisy conditions.
  arXiv  Detail & Related papers  (2022-02-17T08:26:25Z)
• Dynamic Slimmable Network [105.74546828182834]
  We develop a dynamic network slimming regime named Dynamic Slimmable Network (DS-Net) Our DS-Net is empowered with the ability of dynamic inference by the proposed double-headed dynamic gate. It consistently outperforms its static counterparts as well as state-of-the-art static and dynamic model compression methods.
  arXiv  Detail & Related papers  (2021-03-24T15:25:20Z)
• Learning Frequency-aware Dynamic Network for Efficient Super-Resolution [56.98668484450857]
  This paper explores a novel frequency-aware dynamic network for dividing the input into multiple parts according to its coefficients in the discrete cosine transform (DCT) domain. In practice, the high-frequency part will be processed using expensive operations and the lower-frequency part is assigned with cheap operations to relieve the computation burden. Experiments conducted on benchmark SISR models and datasets show that the frequency-aware dynamic network can be employed for various SISR neural architectures.
  arXiv  Detail & Related papers  (2021-03-15T12:54:26Z)
• Exploring ensembles and uncertainty minimization in denoising networks [0.522145960878624]
  We propose a fusion model consisting of two attention modules, which focus on assigning the proper weights to pixels and channels. The experimental results show that our model achieves better performance on top of the baseline of regular pre-trained denoising networks.
  arXiv  Detail & Related papers  (2021-01-24T20:48:18Z)

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.