Online Domain-Incremental Learning Approach to Classify Acoustic Scenes in All Locations

被引:0
|
作者
Mulimani, Manjunath [1 ]
Mesaros, Annamaria [1 ]
机构
[1] Tampere Univ, Signal Proc Res Ctr, Tampere, Finland
关键词
Domain-incremental learning; online learning; acoustic scene classification; Batch Normalization layers; forgetting; deep learning model; NEURAL-NETWORKS;
D O I
10.23919/EUSIPCO63174.2024.10715156
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
In this paper, we propose a method for online domain-incremental learning of acoustic scene classification from a sequence of different locations. Simply training a deep learning model on a sequence of different locations leads to forgetting of previously learned knowledge. In this work, we only correct the statistics of the Batch Normalization layers of a model using a few samples to learn the acoustic scenes from a new location without any excessive training. Experiments are performed on acoustic scenes from 11 different locations, with an initial task containing acoustic scenes from 6 locations and the remaining 5 incremental tasks each representing the acoustic scenes from a different location. The proposed approach outperforms fine-tuning based methods and achieves an average accuracy of 48.8% after learning the last task in sequence without forgetting acoustic scenes from the previously learned locations.
引用
收藏
页码:96 / 100
页数:5
相关论文
共 36 条
  • [1] An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions
    Mirza, M. Jehanzeb
    Masana, Marc
    Possegger, Horst
    Bischof, Horst
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 3000 - 3010
  • [2] Domain-Incremental Semantic Segmentation for Traffic Scenes
    Liu, Yazhou
    Chen, Haoqi
    Lasang, Pongsak
    Wu, Zheng
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2025,
  • [3] Clustering-based Domain-Incremental Learning
    Lamers, Christiaan
    Vidal, Rene
    Belbachir, Nabil
    Van Stein, Niki
    Back, Thomas
    Giampouras, Paris
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS, ICCVW, 2023, : 3376 - 3384
  • [4] Continual Learning for Class- and Domain-Incremental Semantic Segmentation
    Kalb, Tobias
    Roschani, Masoud
    Ruf, Miriam
    Beyerer, Juergen
    2021 32ND IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), 2021, : 1345 - 1351
  • [5] Progressive Adapting and Pruning: Domain-Incremental Learning for Saliency Prediction
    Yang, Kaihui
    Han, Junwei
    Guo, Guangyu
    Fang, Chaowei
    Fan, Yingzi
    Cheng, Lechao
    Zhang, Dingwen
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2024, 20 (08)
  • [6] Quarta: quantum supervised and unsupervised learning for binary classification in domain-incremental learning
    Loglisci, Corrado
    Malerba, Donato
    Pascazio, Saverio
    QUANTUM MACHINE INTELLIGENCE, 2024, 6 (02)
  • [7] Transformed-*: A domain-incremental lifelong learning scenario generation framework
    Zurek, Dominik
    Corizzo, Roberto
    Karwatowski, Michal
    Pietron, Marcin
    Faber, Kamil
    2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [8] Personalized Federated Domain-Incremental Learning Based on Adaptive Knowledge Matching
    Lp, Yichen
    Xu, Wenchao
    Wang, Haozhao
    Qi, Yining
    Li, Ruixuan
    Gu, Jingcai
    COMPUTER VISION-ECCV 2024, PT XLVI, 2025, 15104 : 127 - 144
  • [9] SR-FDIL: Synergistic Replay for Federated Domain-Incremental Learning
    Li, Yichen
    Xu, Wenchao
    Qi, Yining
    Wang, Haozhao
    Li, Ruixuan
    Guo, Song
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2024, 35 (11) : 1879 - 1890
  • [10] Domain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition
    Churamani, Nikhil
    Kara, Ozgur
    Gunes, Hatice
    IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2023, 14 (04) : 3191 - 3206