期刊論文
| 學年 | 114 |
|---|---|
| 學期 | 1 |
| 出版（發表）日期 | 2025-10-30 |
| 作品名稱 | Replacing Batch Normalization with Memory-Based Affine Transformation for Test-Time Adaptation |
| 作品名稱（其他語言） | |
| 著者 | Jih Pin Yeh; Joe-Mei Feng; Hwei Jen Lin; Yoshimasa Tokuyama |
| 單位 | |
| 出版者 | |
| 著錄名稱、卷期、頁數 | Electronics 14(21), p.4251 |
| 摘要 | Batch normalization (BN) has become a foundational component in modern deep neural networks. However, one of its disadvantages is its reliance on batch statistics that may be unreliable or unavailable during inference, particularly under test-time domain shifts. While batch-statistics-free affine transformation methods alleviate this by learning per-sample scale and shift parameters, most treat samples independently, overlooking temporal or sequential correlations in streaming or episodic test-time settings. We propose LSTM-Affine, a memory-based normalization module that replaces BN with a recurrent parameter generator. By leveraging an LSTM, the module produces channel-wise affine parameters conditioned on both the current input and its historical context, enabling gradual adaptation to evolving feature distributions. Unlike conventional batch-statistics-free designs, LSTM-Affine captures dependencies across consecutive samples, improving stability and convergence in scenarios with gradual distribution shifts. Extensive experiments on few-shot learning and source-free domain adaptation benchmarks demonstrate that LSTM-Affine consistently outperforms BN and prior batch-statistics-free baselines, particularly when adaptation data are scarce or non-stationary. |
| 關鍵字 | batch normalization;affine transformation;LSTM;test-time adaptation;memory-based learning;domain adaptation;few-shot learning;normalization-free networks;deep neural networks;feature distribution shift |
| 語言 | en |
| ISSN | |
| 期刊性質 | 國外 |
| 收錄於 | SCI |
| 產學合作 | |
| 通訊作者 | |
| 審稿制度 | 是 |
| 國別 | CHE |
| 公開徵稿 | |
| 出版型式 | ,電子版 |
| 相關連結 |
機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/128257 ) |