Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation

Abstract

We study a practical domain adaptation task, called source-free unsupervised domain adaptation (UDA) problem, in which we cannot access source domain data due to data privacy issues but only a pre-trained source model and unlabeled target data are available. This task, however, is very difficult due to one key challenge: the lack of source data and target domain labels makes model adaptation very challenging. To address this, we propose to mine the hidden knowledge in the source model and exploit it to generate source avatar prototypes (i.e. representative features for each source class) as well as target pseudo labels for domain alignment. To this end, we propose a Contrastive Prototype Generation and Adaptation (CPGA) method. Specifically, CPGA consists of two stages: (1) prototype generation: by exploring the classification boundary information of the source model, we train a prototype generator to generate avatar prototypes via contrastive learning. (2) prototype adaptation: based on the generated source prototypes and target pseudo labels, we develop a new robust contrastive prototype adaptation strategy to align each pseudo-labeled target data to the corresponding source prototypes. Extensive experiments on three UDA benchmark datasets demonstrate the effectiveness and superiority of the proposed method.

ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation

“…In recent years, pioneering works [12], [13] discover that the well-trained source model conceals sufficient source knowledge for the following target adaptation stage, and [12] provides a clear definition of this problem. The last two years have witnessed an increasing number of SFDA approaches [15], [16], [17], [18], most of which are generation based [13], [14], [15] or self-training [12], [44] based methods. Generation based methods [14], [15], [13], [45], [20] generate virtual highlevel features of the source domain to bridge the unseen source and target distribution.…”

“…The last two years have witnessed an increasing number of SFDA approaches [15], [16], [17], [18], most of which are generation based [13], [14], [15] or self-training [12], [44] based methods. Generation based methods [14], [15], [13], [45], [20] generate virtual highlevel features of the source domain to bridge the unseen source and target distribution. Self-training based methods seek to refine the source model by using self-supervised techniques, with the pseudo label technique [12], [44] being the most extensively employed.…”

“…Baselines. We compare ProxyMix with the state-of-the-art source-free domain adaptation methods: SHOT [12], CPGA [15], A 2 Net [17], HCL [18], NRC [44], SSFT-SSD [45], PS [20]. Moreover, to illustrate the effectiveness of Prox-yMix, we further compare our method with the state-of-the-art UDA methods: SymNets [60], TADA [62], BNM [11], BDG [63], SRDC [64], RSDA-MSTN [65], ADR [69], CDAN [5], CDAN+BSP [70], SAFN [59], SWD [71], MDD [61], DMRL [38], MCC [34], STAR [72], RWOT [67], ATDOC [35], MMD [75], DANN [4], ADDA [9], MCD [58], PointDAN [74].…”

“…The booming efforts in the SFDA community are either generation-based or pseudo label-based. The generationbased methods [13], [14], [15] introduce extra generative modules to recover the unseen source domain at imagelevel or feature-level, and then address this problem from a UDA perspective. Nevertheless, generative modules introduce additional parameters, and the recovered virtual source domain usually suffers from a mode collapse problem, which results in low-quality images or features.…”

“…Nevertheless, generative modules introduce additional parameters, and the recovered virtual source domain usually suffers from a mode collapse problem, which results in low-quality images or features. The pseudo label-based methods [15], [16], [17], [18] label the target samples based on the present model's prediction or feature structure. However, due to the extreme domain shift, the noises are inescapable, result in inaccurate decision boundary.…”