Visual domain bridge: A source-free domain adaptation for cross-domain few-shot learning

M Yazdanpanah, P Moradi - Proceedings of the IEEE/CVF …, 2022 - openaccess.thecvf.com
Proceedings of the IEEE/CVF Conference on Computer Vision and …, 2022openaccess.thecvf.com
Due to the covariate shift, deep neural networks performance always degrades when
applied to novel domains. In order to mitigate this problem, domain adaptation techniques
require samples from target data during the feature extraction training, which is not always
applicable in realworld scenarios. Batch Normalization is a known component of computer
vision models, aiming at reducing the training-time covariate shift. However, facing
distribution shift results in an internal state mismatch inside the BatchNorm layers during the …
Abstract
Due to the covariate shift, deep neural networks performance always degrades when applied to novel domains. In order to mitigate this problem, domain adaptation techniques require samples from target data during the feature extraction training, which is not always applicable in realworld scenarios. Batch Normalization is a known component of computer vision models, aiming at reducing the training-time covariate shift. However, facing distribution shift results in an internal state mismatch inside the BatchNorm layers during the inference time. In favor of alleviating the induced mismatch, this paper proposes a sourcefree, lightweight and straightforward approach by introducing the" Visual Domain Bridge" concept reducing the BatchNorm's internal mismatch in the cross-domain settings. Compared to the other BatchNorm-based sourcefree domain adaptation techniques such as AdaBN and Prediction-BN, our method formed a new state-of-the-art cross-domain few-shot fine-tuning method neglecting extra augmentations; while improving the performance in neardomain settings too. The proposed method can integrate with other domain adaptation methods and enhance their performance requiring just a few lines of modification in the BatchNorm's implementation. Implementations are available in https://github. com/MosyMosy/VDB.
openaccess.thecvf.com
以上显示的是最相近的搜索结果。 查看全部搜索结果