2019

Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising

Zhang, Haokui, Li, Ying, Chen, Hao et al.

Understand

Recently, neural architecture search (NAS) methods have attracted much attention and outperformed manually designed architectures on a few high-level vision tasks.

In this paper, we propose HiNAS (Hierarchical NAS), an effort towards employing NAS to automatically design effective neural network architectures for image denoising.
HiNAS adopts gradient based search strategies and employs operations with adaptive receptive field to build an flexible hierarchical search space.
During the search stage, HiNAS shares cells across different feature levels to save memory and employ an early stopping strategy to avoid the collapse issue in NAS, and considerably accelerate the search speed.

Built on

A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
David Martin, Charless Fowlkes, Doron Tal, Jitendra Malik, et al · 2001
Earlier work this paper cites.
Image quality assessment: from error visibility to structural similarity
Zhou Wang, Alan Bovik, Hamid Sheikh, and Eero Simoncelli · 2004
Earlier work this paper cites.
Efficient belief propagation with learned higher-order markov random fields
Xiangyang Lan, Stefan Roth, Daniel Huttenlocher, and Michael J Black · 2006
Earlier work this paper cites.
Image denoising by sparse 3-d transform-domain collaborative filtering
K Dabov, A Foi, V Katkovnik, and K Egiazarian · 2007
Earlier work this paper cites.
Is denoising dead?
Priyam Chatterjee and Peyman Milanfar · 2009
Earlier work this paper cites.
Non-local sparse models for image restoration
Julien Mairal, Francis R Bach, Jean Ponce, Guillermo Sapiro, and Andrew Zisserman · 2009
Earlier work this paper cites.
Learning photographic global tonal adjustment with a database of input/output image pairs
Vladimir Bychkovsky, Sylvain Paris, Eric Chan, and Frédo Durand · 2011
Earlier work this paper cites.
Nonlocally centralized sparse representation for image restoration
Weisheng Dong, Lei Zhang, Guangming Shi, and Xin Li · 2012
Earlier work this paper cites.
Weighted nuclear norm minimization with application to image denoising
Shuhang Gu, Lei Zhang, Wangmeng Zuo, and Xiangchu Feng · 2014
Earlier work this paper cites.
Removing rain from a single image via discriminative sparse coding
Yu Luo, Yong Xu, and Hui Ji · 2015
Earlier work this paper cites.
Identity mappings in deep residual networks
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun · 2016
Earlier work this paper cites.
Rain streak removal using layer priors
Yu Li, Robby T Tan, Xiaojie Guo, Jiangbo Lu, and Michael S Brown · 2016
Earlier work this paper cites.
Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections
Xiaojiao Mao, Chunhua Shen, and Yu-Bin Yang · 2016
Earlier work this paper cites.
Neural architecture search with reinforcement learning
Original
Barret Zoph and Quoc V Le · 2016
Earlier work this paper cites.
Removing rain from single images via a deep detail network
Xueyang Fu, Jiabin Huang, Delu Zeng, Yue Huang, Xinghao Ding, and John Paisley · 2017
Earlier work this paper cites.
Hierarchical representations for efficient architecture search
Original
Hanxiao Liu, Karen Simonyan, Oriol Vinyals, Chrisantha Fernando, and Koray Kavukcuoglu · 2017
Earlier work this paper cites.

Similar

Sgdr: Stochastic gradient descent with warm restarts
Ilya Loshchilov and Frank Hutter · 2017
Cited alongside, same era.
Memnet: A persistent memory network for image restoration
Ying Tai, Jian Yang, Xiaoming Liu, and Chunyan Xu · 2017
Cited alongside, same era.
Deep joint rain detection and removal from a single image
Wenhan Yang, Robby T Tan, Jiashi Feng, Jiaying Liu, Zongming Guo, and Shuicheng Yan · 2017
Cited alongside, same era.
Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising
Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang · 2017
Cited alongside, same era.
Learning deep cnn denoiser prior for image restoration
Kai Zhang, Wangmeng Zuo, Shuhang Gu, and Lei Zhang · 2017
Cited alongside, same era.
Proxylessnas: Direct neural architecture search on target task and hardware
Original
Han Cai, Ligeng Zhu, and Song Han · 2018
Cited alongside, same era.
Efficient multi-objective neural architecture search via lamarckian evolution
Original
Thomas Elsken, Jan Hendrik Metzen, and Frank Hutter · 2018
Cited alongside, same era.
Recurrent squeeze-and-excitation context aggregation net for single image deraining
Xia Li, Jianlong Wu, Zhouchen Lin, Hong Liu, and Hongbin Zha · 2018
Cited alongside, same era.
Non-local recurrent network for image restoration
Ding Liu, Bihan Wen, Yuchen Fan, Chen Change Loy, and Thomas S Huang · 2018
Cited alongside, same era.
Darts: Differentiable architecture search
Original
Hanxiao Liu, Karen Simonyan, and Yiming Yang · 2018
Cited alongside, same era.
Shufflenet v2: Practical guidelines for efficient cnn architecture design
Ningning Ma, Xiangyu Zhang, Hai-Tao Zheng, and Jian Sun · 2018
Cited alongside, same era.
Efficient neural architecture search via parameter sharing
Original
Hieu Pham, Melody Y Guan, Barret Zoph, Quoc V Le, and Jeff Dean · 2018
Cited alongside, same era.

Then

Ffdnet: Toward a fast and flexible solution for cnn-based image denoising
Kai Zhang, Wangmeng Zuo, and Lei Zhang · 2018
Later among the works it cites.
Practical block-wise neural network architecture generation
Zhao Zhong, Junjie Yan, Wei Wu, Jing Shao, and Cheng-Lin Liu · 2018
Later among the works it cites.
Learning transferable architectures for scalable image recognition
Barret Zoph, Vijay Vasudevan, Jonathon Shlens, and Quoc V Le · 2018
Later among the works it cites.
Fast, accurate and lightweight super-resolution with neural architecture search
Original
Xiangxiang Chu, Bo Zhang, Hailong Ma, Ruijun Xu, Jixiang Li, and Qingyuan Li · 2019
Closest in time.
Nas-fpn: Learning scalable feature pyramid architecture for object detection
Golnaz Ghiasi, Tsung-Yi Lin, and Quoc V Le · 2019
Closest in time.
Toward convolutional blind denoising of real photographs
Shi Guo, Zifei Yan, Kai Zhang, Wangmeng Zuo, and Lei Zhang · 2019
Closest in time.
Generating training data for denoising real rgb images via camera pipeline simulation
Original
Ronnachai Jaroensri, Camille Biscarrat, Miika Aittala, and Frédo Durand · 2019
Closest in time.
Darts+: Improved differentiable architecture search with early stopping
Original
Hanwen Liang, Shifeng Zhang, Jiacheng Sun, Xingqiu He, Weiran Huang, Kechen Zhuang, and Zhenguo Li · 2019
Closest in time.
Auto-deeplab: Hierarchical neural architecture search for semantic image segmentation
Chenxi Liu, Liang-Chieh Chen, Florian Schroff, Hartwig Adam, Wei Hua, Alan L Yuille, and Li Fei-Fei · 2019
Closest in time.
Deep evolutionary networks with expedited genetic algorithms for medical image denoising
Peng Liu, Mohammad D El Basha, Yangjunyi Li, Yao Xiao, Pina C Sanelli, and Ruogu Fang · 2019
Closest in time.
Dual residual networks leveraging the potential of paired operations for image restoration
Xing Liu, Masanori Suganuma, Zhun Sun, and Takayuki Okatani · 2019
Closest in time.
Fast neural architecture search of compact semantic segmentation models via auxiliary cells
Vladimir Nekrasov, Hao Chen, Chunhua Shen, and Ian Reid · 2019
Closest in time.
Mnasnet: Platform-aware neural architecture search for mobile
Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Mark Sandler, Andrew Howard, and Quoc V Le · 2019
Closest in time.
NAS-FCOS: Fast neural architecture search for object detection
Original
Ning Wang, Yang Gao, Hao Chen, Peng Wang, Zhi Tian, and Chunhua Shen · 2019
Closest in time.
Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search
Bichen Wu, Xiaoliang Dai, Peizhao Zhang, Yanghan Wang, Fei Sun, Yiming Wu, Yuandong Tian, Peter Vajda, Yangqing Jia, and Kurt Keutzer · 2019
Closest in time.
Deformable convnets v2: More deformable, better results
Xizhou Zhu, Han Hu, Stephen Lin, and Jifeng Dai · 2019
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…