Task-Agnostic Vision Transformer for Distributed Learning of Image Processing

被引:6
|
作者
Kim, Boah [1 ]
Kim, Jeongsol [1 ]
Ye, Jong Chul [2 ]
机构
[1] Korea Adv Inst Sci & Technol KAIST, Dept Bio & Brain Engn, Daejeon 34141, South Korea
[2] Korea Adv Inst Sci & Technol KAIST, Kim Jaechul Grad Sch Artificial Intelligence AI, Daejeon 34141, South Korea
关键词
Distributed learning; transformer; image processing; task-agnostic learning; QUALITY ASSESSMENT;
D O I
10.1109/TIP.2022.3226892
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recently, distributed learning approaches have been studied for using data from multiple sources without sharing them, but they are not usually suitable in applications where each client carries out different tasks. Meanwhile, Transformer has been widely explored in computer vision area due to its capability to learn the common representation through global attention. By leveraging the advantages of Transformer, here we present a new distributed learning framework for multiple image processing tasks, allowing clients to learn distinct tasks with their local data. This arises from a disentangled representation of local and non-local features using a task-specific head/tail and a task-agnostic Vision Transformer. Each client learns a translation from its own task to a common representation using the task-specific networks, while the Transformer body on the server learns global attention between the features embedded in the representation. To enable decomposition between the task-specific and common representations, we propose an alternating training strategy between clients and server. Experimental results on distributed learning for various tasks show that our method synergistically improves the performance of each client with its own data.
引用
收藏
页码:203 / 218
页数:16
相关论文
共 50 条
  • [41] Task-Agnostic Evolution of Diverse Repertoires of Swarm Behaviours
    Gomes, Jorge
    Christensen, Anders Lyhne
    SWARM INTELLIGENCE (ANTS 2018), 2018, 11172 : 225 - 238
  • [42] VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty
    Ardywibowo, Randy
    Huo, Zepeng
    Wang, Zhangyang
    Mortazavi, Bobak
    Huang, Shuai
    Qian, Xiaoning
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022, : 865 - 877
  • [43] DexBERT: Effective, Task-Agnostic and Fine-Grained Representation Learning of Android Bytecode
    Sun T.
    Allix K.
    Kim K.
    Zhou X.
    Kim D.
    Lo D.
    Bissyande T.F.
    Klein J.
    IEEE Transactions on Software Engineering, 2023, 49 (10) : 4691 - 4706
  • [44] LEARNING DIVERSE SUB-POLICIES VIA A TASK-AGNOSTIC REGULARIZATION ON ACTION DISTRIBUTIONS
    Huo, Liangyu
    Wang, Zulin
    Xu, Mai
    Song, Yuhang
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 3932 - 3936
  • [45] Task-Agnostic Object Recognition for Mobile Robots through Few-Shot Image Matching
    Chiatti, Agnese
    Bardaro, Gianluca
    Bastianelli, Emanuele
    Tiddi, Ilaria
    Mitra, Prasenjit
    Motta, Enrico
    ELECTRONICS, 2020, 9 (03)
  • [46] Task-Agnostic Amortized Inference of Gaussian Process Hyperparameters
    Liu, Sulin
    Sun, Xingyuan
    Ramadge, Peter J.
    Adams, Ryan P.
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [47] Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training
    Liu, Yuanxin
    Meng, Fandong
    Lin, Zheng
    Fu, Peng
    Cao, Yanan
    Wang, Weiping
    Zhou, Jie
    NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, 2022, : 5840 - 5857
  • [48] TADA: Efficient Task-Agnostic Domain Adaptation for Transformers
    Hung, Chia-Chien
    Lange, Lukas
    Stroetgen, Jannik
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL 2023, 2023, : 487 - 503
  • [49] COSMIC: Mutual Information for Task-Agnostic Summarization Evaluation
    Darrin, Maxime
    Formont, Philippe
    CilEuNG, Jackie Chi Kit
    Piantanida, Pablo
    PROCEEDINGS OF THE 62ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1: LONG PAPERS, 2024, : 12696 - 12717
  • [50] Towards Learning Generalizable Code Embeddings Using Task-agnostic Graph Convolutional Networks
    Ding, Zishuo
    Li, Heng
    Shang, Weiyi
    Chen, Tse-Hsun
    ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY, 2023, 32 (02)