Abstract / Description of output
We present a “learning to learn” approach for discovering white-box classification loss functions that are robust to label noise in the training data. We parameterise a flexible family of loss functions using Taylor polynomials, and apply evolutionary strategies to search for noise-robust losses in this space. To learn re-usable loss functions that can apply to new tasks, our fitness function scores their performance in aggregate across a range of training datasets and architectures. The resulting white-box loss provides a simple and fast “plug-and-play” module that enables effective labelnoise-robust learning in diverse downstream tasks, without requiring a special training procedure or network architecture. The efficacy of our loss is demonstrated on a variety of datasets with both synthetic and real label noise, where we compare favourably to prior work.
Original language | English |
---|---|
Title of host publication | Proceedings of 2021 IEEE/CVF International Conference on Computer Vision ICCV 2021 |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 6650-6659 |
Number of pages | 10 |
ISBN (Electronic) | 978-1-6654-2812-5 |
ISBN (Print) | 978-1-6654-2813-2 |
DOIs | |
Publication status | Published - 28 Feb 2022 |
Event | International Conference on Computer Vision 2021 - Online Duration: 11 Oct 2021 → 17 Oct 2021 https://iccv2021.thecvf.com/home |
Publication series
Name | 2021 IEEE/CVF International Conference on Computer Vision (ICCV) |
---|---|
Publisher | IEEE |
ISSN (Print) | 1550-5499 |
ISSN (Electronic) | 2380-7504 |
Conference
Conference | International Conference on Computer Vision 2021 |
---|---|
Abbreviated title | ICCV 2021 |
Period | 11/10/21 → 17/10/21 |
Internet address |