Adaptive Contrastive Learning with Label Consistency for Source Data Free Unsupervised Domain Adaptation
Open Access
Abstract
Unsupervised domain adaptation, which aims to alleviate the domain shift between source domain and target domain, has attracted extensive research interest; however, this is unlikely in practical application scenarios, which may be due to privacy issues and intellectual rights. In this paper, we discuss a more challenging and practical source-free unsupervised domain adaptation, which needs to adapt the source domain model to the target domain without the aid of source domain data. We propose label consistent contrastive learning (LCCL), an adaptive contrastive learning framework for source-free unsupervised domain adaptation, which encourages target domain samples to learn class-level discriminative features. Considering that the data in the source domain are unavailable, we introduce the memory bank to store the samples with the same pseudo label output and the samples obtained by clustering, and the trusted historical samples are involved in contrastive learning. In addition, we demonstrate that LCCL is a general framework that can be applied to unsupervised domain adaptation. Extensive experiments on digit recognition and image classification benchmark datasets demonstrate the effectiveness of the proposed method.Keywords
Funding Information
- Narodowe Centrum Nauki (2020/37/K/ST8/02748)
This publication has 27 references indexed in Scilit:
- Deep Residual Correction Network for Partial Domain AdaptationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- Discriminative Transfer Feature and Label Consistency for Cross-Domain Image ClassificationIEEE Transactions on Neural Networks and Learning Systems, 2020
- Joint Adversarial Domain Adaptation2019
- A Graph Embedding Framework for Maximum Mean Discrepancy-Based Domain Adaptation AlgorithmsIEEE Transactions on Image Processing, 2019
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation2018
- Domain Invariant and Class Discriminative Feature Learning for Visual Domain AdaptationIEEE Transactions on Image Processing, 2018
- Adversarial Discriminative Domain Adaptation2017
- You Only Look Once: Unified, Real-Time Object Detection2016
- Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998