Back to Search
Start Over
Reciprocal normalization for domain adaptation.
- Source :
-
Pattern Recognition . Aug2023, Vol. 140, pN.PAG-N.PAG. 1p. - Publication Year :
- 2023
-
Abstract
- Batch normalization (BN) is widely used in modern deep neural networks, which has been shown to represent the domain-related knowledge, and thus is ineffective for cross-domain tasks like unsupervised domain adaptation (UDA). Existing BN variant methods aggregate source and target domain knowledge in the same channel in normalization module. However, the misalignment between the features of corresponding channels across domains often leads to a sub-optimal transferability. In this paper, we exploit the cross-domain relation and propose a novel normalization method, Reciprocal Normalization (RN). Specifically, RN first presents a Reciprocal Compensation (RC) module to acquire the compensatory for each channel in both domains based on the cross-domain channel-wise correlation. Then RN develops a Reciprocal Aggregation (RA) module to adaptively aggregate the feature with its cross-domain compensatory components. As an alternative to BN, RN is more suitable for UDA problems and can be easily integrated into popular domain adaptation methods. Experiments show that the proposed RN outperforms existing normalization counterparts by a large margin and helps state-of-the-art adaptation approaches achieve better results. The source code is available on https://github.com/Openning07/reciprocal-normalization-for-DA. [ABSTRACT FROM AUTHOR]
- Subjects :
- *ARTIFICIAL neural networks
*SOURCE code
Subjects
Details
- Language :
- English
- ISSN :
- 00313203
- Volume :
- 140
- Database :
- Academic Search Index
- Journal :
- Pattern Recognition
- Publication Type :
- Academic Journal
- Accession number :
- 163267079
- Full Text :
- https://doi.org/10.1016/j.patcog.2023.109533