PROPERTY NEURONS IN SELF-SUPERVISED SPEECH TRANSFORMERS

被引：0
|
作者：
Lin, Tzu-Quan [1 ]
Lin, Guan-Ting [1 ]
Lee, Hung-Yi [1 ]
Tang, Hao [2 ]
机构：
[1] Graduate Institute of Communication Engineering, National Taiwan University, Taiwan
[2] University of Edinburgh, United Kingdom
来源：
arXiv |
关键词：
Compendex;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Neurons
引用
收藏
相关论文
共 50 条
  • [1] Self-Supervised Transformers for fMRI representation
    Malkiel, Itzik
    Rosenman, Gony
    Wolf, Lior
    Hendler, Talma
    INTERNATIONAL CONFERENCE ON MEDICAL IMAGING WITH DEEP LEARNING, VOL 172, 2022, 172 : 895 - 913
  • [2] On Separate Normalization in Self-supervised Transformers
    Chen, Xiaohui
    Wang, Yinkai
    Du, Yuanqi
    Hassoun, Soha
    Liu, Li-Ping
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [3] Emerging Properties in Self-Supervised Vision Transformers
    Caron, Mathilde
    Touvron, Hugo
    Misra, Ishan
    Jegou, Herve
    Mairal, Julien
    Bojanowski, Piotr
    Joulin, Armand
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 9630 - 9640
  • [4] Self-supervised vision transformers for semantic segmentation
    Gu, Xianfan
    Hu, Yingdong
    Wen, Chuan
    Gao, Yang
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2025, 251
  • [5] Guiding Attention for Self-Supervised Learning with Transformers
    Deshpande, Ameet
    Narasimhan, Karthik
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, 2020, : 4676 - 4686
  • [6] Self-supervised Vision Transformers for Writer Retrieval
    Raven, Tim
    Matei, Arthur
    Fink, Gernot A.
    DOCUMENT ANALYSIS AND RECOGNITION-ICDAR 2024, PT II, 2024, 14805 : 380 - 396
  • [7] Self-Supervised Vision Transformers for Malware Detection
    Seneviratne, Sachith
    Shariffdeen, Ridwan
    Rasnayaka, Sanka
    Kasthuriarachchi, Nuran
    IEEE ACCESS, 2022, 10 : 103121 - 103135
  • [8] Understanding Self-Attention of Self-Supervised Audio Transformers
    Yang, Shu-wen
    Liu, Andy T.
    Lee, Hung-yi
    INTERSPEECH 2020, 2020, : 3785 - 3789
  • [9] Civil Rephrases Of Toxic Texts With Self-Supervised Transformers
    Laugier, Leo
    Pavlopoulos, John
    Sorensen, Jeffrey
    Dixon, Lucas
    16TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EACL 2021), 2021, : 1442 - 1461
  • [10] Self-supervised Video Hashing via Bidirectional Transformers
    Li, Shuyan
    Li, Xiu
    Lu, Jiwen
    Zhou, Jie
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 13544 - 13553
12345