상세 보기
Mitigating Class Imbalance in Neural Network Quantization via Rank-Based Variance Regularization
- Kim, Suk Hyun;
- Youn, Jongsu;
- Yoon, Yeonghun;
- Choi, Jongwon
WEB OF SCIENCE
0SCOPUS
0초록
While Quantization Aware Training (QAT) improves inference efficiency, it struggles with performance degradation on class-imbalanced datasets due to limited representation of tail classes and an overemphasis on head class optimization. To address the issue, we propose a Rank-based variance regularization method, which introduces a regularization term for variance consistency across classes and applies a rank-based statistical test for outlier robustness. Our method also uses a class-inverse scaling strategy to enhance tail class representation. Experimental results show that our approach outperforms existing methods up to 6.3% and achieves stable performance across head and tail classes under severe class imbalance and high compression rates.
키워드
- 제목
- Mitigating Class Imbalance in Neural Network Quantization via Rank-Based Variance Regularization
- 저자
- Kim, Suk Hyun; Youn, Jongsu; Yoon, Yeonghun; Choi, Jongwon
- 발행일
- 2027
- 유형
- Proceedings Paper
- 권
- 16825
- 페이지
- 593 ~ 607
- 언어
- ENG
- 출판사
- Springer Science and Business Media Deutschland GmbH
- 발행국가
- 미국
- 분량
- 15 페이지
- ISSN
- E 1611-3349
P 0302-9743