2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDMLR-APPL-IP-4.13
Paper Title TASK-AGNOSTIC CONTINUAL LEARNING USING BASE-CHILD CLASSIFIERS
Authors Pranshu Ranjan Singh, Saisubramaniam Gopalakrishnan, Institute for Infocomm Research (I2R), A*STAR, Singapore; Qiao ZhongZheng, Ponnuthurai N. Suganthan, Nanyang Technological University (NTU), Singapore; Savitha Ramasamy, ArulMurugan Ambikapathi, Institute for Infocomm Research (I2R), A*STAR, Singapore
SessionMLR-APPL-IP-4: Machine learning for image processing 4
LocationArea D
Session Time:Tuesday, 21 September, 13:30 - 15:00
Presentation Time:Tuesday, 21 September, 13:30 - 15:00
Presentation Poster
Topic Applications of Machine Learning: Machine learning for image processing
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Continual learning (CL) aims to learn new tasks by forward transfer of information learnt from previous tasks and without forgetting them. In task incremental CL, task information is vital during both strategy development and inference. Providing such partial knowledge about the test sample demands additional complexity and may become intractable, especially when the sample source is ambiguous. In this work, we design a task-agnostic approach that uses {\em base-child} hybrid setup to incrementally learn tasks while mitigating forgetting. Multiple base classifiers guided by reference points learn new tasks and this information is {\em distilled} via feature space induced sampling strategy. A central child classifier consolidates information across tasks and infers the task identifier automatically. Experimental results on standard datasets show that the proposed approach outperforms the various state-of-the-art regularization and replay CL algorithms in terms of accuracy, by 50\% and 7\% with homogeneous and heterogeneous tasks, respectively, in task-agnostic scenarios.