Abstract
The imbalanced distribution of long-tailed data presents a considerable challenge for deep learning models, as it causes them to prioritize the accurate classification of head classes but largely disregard tail classes. The biased decision boundary caused by inadequate semantic information in tail classes is one of the key factors contributing to their low recognition accuracy. To rectify this issue, we propose to augment tail classes by grafting the diverse semantic information from head classes, referred to as head-to-tail fusion (H2T). We replace a portion of feature maps from tail classes with those belonging to head classes. These fused features substantially enhance the diversity of tail classes. Both theoretical analysis and practical experimentation demonstrate that H2T can contribute to a more optimized solution for the decision boundary. We seamlessly integrate H2T in the classifier adjustment stage, making it a plug-and-play module. Its simplicity and ease of implementation allow for smooth integration with existing long-tailed recognition methods, facilitating a further performance boost. Extensive experiments on various long-tailed benchmarks demonstrate the effectiveness of the proposed H2T. The source code is available at https://github.com/Keke921/H2T.
Original language | English |
---|---|
Title of host publication | Proceedings of the 38th AAAI Conference on Artificial Intelligence |
Editors | Michael Wooldridge, Jennifer Dy, Sriraam Natarajan |
Publisher | AAAI press |
Pages | 13581-13589 |
Number of pages | 9 |
ISBN (Print) | 1577358872, 9781577358879 |
DOIs | |
Publication status | Published - 25 Mar 2024 |
Event | 38th AAAI Conference on Artificial Intelligence, AAAI 2024 - Vancouver, Canada Duration: 20 Feb 2024 → 27 Feb 2024 https://ojs.aaai.org/index.php/AAAI/issue/archive (Conference proceeding) |
Publication series
Name | Proceedings of the AAAI Conference on Artificial Intelligence |
---|---|
Publisher | AAAI Press |
Number | 12 |
Volume | 38 |
ISSN (Print) | 2159-5399 |
ISSN (Electronic) | 2374-3468 |
Conference
Conference | 38th AAAI Conference on Artificial Intelligence, AAAI 2024 |
---|---|
Country/Territory | Canada |
City | Vancouver |
Period | 20/02/24 → 27/02/24 |
Internet address |
|
Scopus Subject Areas
- Artificial Intelligence
User-Defined Keywords
- ML: Classification and Regression
- CV: Object Detection & Categorization
- ML: Multi-class/Multi-label Learning & Extreme Classification