Stacked BNAS: Rethinking Broad Convolutional Neural Network for Neural Architecture Search

被引:2
|
作者
Ding, Zixiang [1 ,2 ]
Chen, Yaran [1 ,2 ]
Li, Nannan [1 ,2 ]
Zhao, Dongbin [1 ,2 ]
Chen, C. L. Philip [3 ,4 ]
机构
[1] Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
[2] Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
[3] South China Univ Technol, Sch Comp Sci & Engn, Guangzhou 510641, Peoples R China
[4] Pazhou Lab, Ctr Affect Comp & Gen Models, Guangzhou 510335, Peoples R China
基金
中国国家自然科学基金;
关键词
Broad neural architecture search (BNAS); knowledge embedding search (KES); stacked broad convolutional neural network (BCNN); LEARNING-SYSTEM; APPROXIMATION;
D O I
10.1109/TSMC.2023.3275128
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Different from other deep scalable architecture-based NAS approaches, Broad Neural Architecture Search (BNAS) proposes a broad scalable architecture which consists of convolution and enhancement blocks, dubbed Broad Convolutional Neural Network (BCNN), as the search space for amazing efficiency improvement. BCNN reuses the topologies of cells in the convolution block so that BNAS can employ few cells for efficient search. Moreover, multi-scale feature fusion and knowledge embedding are proposed to improve the performance of BCNN with shallow topology. However, BNAS suffers some drawbacks: 1) insufficient representation diversity for feature fusion and enhancement and 2) time consumption of knowledge embedding design by human experts. This paper proposes Stacked BNAS, whose search space is a developed broad scalable architecture named Stacked BCNN, with better performance than BNAS. On the one hand, Stacked BCNN treats mini BCNN as a basic block to preserve comprehensive representation and deliver powerful feature extraction ability. For multi-scale feature enhancement, each mini BCNN feeds the outputs of deep and broad cells to the enhancement cell. For multi-scale feature fusion, each mini BCNN feeds the outputs of deep, broad and enhancement cells to the output node. On the other hand, Knowledge Embedding Search (KES) is proposed to learn appropriate knowledge embeddings in a differentiable way. Moreover, the basic unit of KES is an over-parameterized knowledge embedding module that consists of all possible candidate knowledge embeddings. Experimental results show that 1) Stacked BNAS obtains better performance than BNAS-v2 on both CIFAR-10 and ImageNet, 2) the proposed KES algorithm contributes to reducing the parameters of the learned architecture with satisfactory performance, and 3) Stacked BNAS delivers a state-of-the-art efficiency of 0.02 GPU days.
引用
收藏
页码:5679 / 5690
页数:12
相关论文
共 50 条
  • [1] BNAS: Efficient Neural Architecture Search Using Broad Scalable Architecture
    Ding, Zixiang
    Chen, Yaran
    Li, Nannan
    Zhao, Dongbin
    Sun, Zhiquan
    Chen, C. L. Philip
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (09) : 5004 - 5018
  • [2] Steganalysis of convolutional neural network based on neural architecture search
    Hongbo Wang
    Xingyu Pan
    Lingyan Fan
    Shuofeng Zhao
    [J]. Multimedia Systems, 2021, 27 : 379 - 387
  • [3] Steganalysis of convolutional neural network based on neural architecture search
    Wang, Hongbo
    Pan, Xingyu
    Fan, Lingyan
    Zhao, Shuofeng
    [J]. MULTIMEDIA SYSTEMS, 2021, 27 (03) : 379 - 387
  • [4] Neural Architecture Search for Convolutional Neural Networks with Attention
    Nakai, Kohei
    Matsubara, Takashi
    Uehara, Kuniaki
    [J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2021, E104D (02) : 312 - 321
  • [5] A reinforcement neural architecture search convolutional neural network for rolling bearing fault diagnosis
    Li, Lintao
    Jiang, Hongkai
    Wang, Ruixin
    Yang, Qiao
    [J]. MEASUREMENT SCIENCE AND TECHNOLOGY, 2023, 34 (11)
  • [6] BNAS-v2: Memory-Efficient and Performance-Collapse-Prevented Broad Neural Architecture Search
    Ding, Zixiang
    Chen, Yaran
    Li, Nannan
    Zhao, Dongbin
    [J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2022, 52 (10): : 6259 - 6272
  • [7] NASB: Neural Architecture Search for Binary Convolutional Neural Networks
    Zhu, Baozhou
    Al-Ars, Zaid
    Hofstee, H. Peter
    [J]. 2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [8] Rethinking the Pruning Criteria for Convolutional Neural Network
    Huang, Zhongzhan
    Shao, Wenqi
    Wang, Xinjiang
    Lin, Liang
    Luo, Ping
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [9] Efficient and lightweight convolutional neural network architecture search methods for object classification
    Lin, Chuen-Horng
    Chen, Tsung-Yi
    Chen, Huan-Yu
    Chan, Yung-Kuan
    [J]. PATTERN RECOGNITION, 2024, 156
  • [10] Convolutional neural network architecture search based on fractal decomposition optimization algorithm
    Souquet, Leo
    Shvai, Nadiya
    Llanza, Arcadi
    Nakib, Amir
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2023, 213