Gradual Geometry-Guided Knowledge Distillation for Source-Data-Free Domain Adaptation
Due to access to the source data during the transfer phase, conventional domain adaptation works have recently raised safety and privacy concerns. More research attention thus shifts to a more practical setting known as source-data-free domain adaptation (SFDA). The new challenge is how to obtain re...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/9/1491 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Due to access to the source data during the transfer phase, conventional domain adaptation works have recently raised safety and privacy concerns. More research attention thus shifts to a more practical setting known as source-data-free domain adaptation (SFDA). The new challenge is how to obtain reliable semantic supervision in the absence of source domain training data and the labels on the target domain. To that end, in this work, we introduce a novel <i>Gradual Geometry-Guided Knowledge Distillation</i> (G2KD) approach for SFDA. Specifically, to address the lack of supervision, we used local geometry of data to construct a more credible probability distribution over the potential categories, termed geometry-guided knowledge. Then, knowledge distillation was adopted to integrate this extra information for boosting the adaptation. More specifically, first, we constructed a neighborhood geometry for any target data using a similarity comparison on the whole target dataset. Second, based on pre-obtained semantic estimation by clustering, we mined soft semantic representations expressing the geometry-guided knowledge by semantic fusion. Third, using the soften labels, we performed knowledge distillation regulated by the new objective. Considering the unsupervised setting of SFDA, in addition to the distillation loss and student loss, we introduced a mixed entropy regulator that minimized the entropy of individual data as well as maximized the mutual entropy with augmentation data to utilize neighbor relation. Our contribution is that, through local geometry discovery with semantic representation and self-knowledge distillation, the semantic information hidden in the local structures is transformed to effective semantic self-supervision. Also, our knowledge distillation works in a gradual way that is helpful to capture the dynamic variations in the local geometry, mitigating the previous guidance degradation and deviation at the same time. Extensive experiments on five challenging benchmarks confirmed the state-of-the-art performance of our method. |
|---|---|
| ISSN: | 2227-7390 |