When a person solves the multi-choice problem, she considers not only what is the answer but also what is not the answer. Knowing what choice is not the answer and utilizing the relationships between choices, she can improve the prediction accuracy. Inspired by this human reasoning process, we propose a new training strategy to fully utilize inter-class relationships, namely LogitMix. Our strategy is combined with recent data augmentation techniques, e.g., Mixup, Manifold Mixup, CutMix, and PuzzleMix. Then, we suggest using a mixed logit, i.e., a mixture of two logits, as an auxiliary training objective. Since the logit can preserve both positive and negative inter-class relationships, it can impose a network to learn the probability of wrong answers correctly. Our extensive experimental results on the image- and language-based tasks demonstrate that LogitMix achieves state-of-the-art performance among recent data augmentation techniques regarding calibration error and prediction accuracy.
|Title of host publication||Proceedings of the 31st International Joint Conference on Artificial Intelligence, IJCAI 2022|
|Editors||Luc De Raedt, Luc De Raedt|
|Publisher||International Joint Conferences on Artificial Intelligence|
|Number of pages||8|
|Publication status||Published - 2022|
|Event||31st International Joint Conference on Artificial Intelligence, IJCAI 2022 - Vienna, Austria|
Duration: 2022 Jul 23 → 2022 Jul 29
|Name||IJCAI International Joint Conference on Artificial Intelligence|
|Conference||31st International Joint Conference on Artificial Intelligence, IJCAI 2022|
|Period||22/7/23 → 22/7/29|
Bibliographical noteFunding Information:
This research was partially supported by the Basic Science Research Program through NRF funded by the MSIP (NRF-2022R1A2C3011154), IITP grant funded by the Korea government(MSIT) and KEIT grant funded by the Korea government(MOTIE) (No. 2022-0-00680), and Korea Medical Device Development Fund grant funded by the Korea government (Project Number: 202011D06).
© 2022 International Joint Conferences on Artificial Intelligence. All rights reserved.
All Science Journal Classification (ASJC) codes
- Artificial Intelligence