Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation

• URL: http://arxiv.org/abs/2106.15326v1
• Date: Fri, 18 Jun 2021 08:30:54 GMT
• Title: Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
• Authors: Zhen Qiu, Yifan Zhang, Hongbin Lin, Shuaicheng Niu, Yanxia Liu, Qing Du, Mingkui Tan
• Abstract summary: We study a practical domain adaptation task in which we cannot access source domain data due to data privacy issues. The lack of source data and target domain labels makes model adaptation very challenging. We propose a Contrastive Prototype Generation and Adaptation (CPGA) method to exploit hidden knowledge in the source model.
• Score: 34.45208248728318
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning [57.43322536718131]
  We present a two-stage source-free domain adaptation (SFDA) framework for medical image segmentation. In the prototype-anchored feature alignment stage, we first utilize the weights of the pre-trained pixel-wise classifier as source prototypes. Then, we introduce the bi-directional transport to align the target features with class prototypes by minimizing its expected cost.
  arXiv  Detail & Related papers  (2023-07-19T06:07:12Z)
• Imbalance-Agnostic Source-Free Domain Adaptation via Avatar Prototype Alignment [45.356399249491545]
  Source-free Unsupervised Domain Adaptation (SF-UDA) aims to adapt a well-trained source model to an unlabeled target domain without access to the source data. We propose a Contrastive Prototype Generation and Adaptation (CPGA) method to generate source avatar prototypes. We empirically show that T-CPGA significantly outperforms other SF-UDA methods in imbalance-agnostic SF-UDA.
  arXiv  Detail & Related papers  (2023-05-22T02:46:34Z)
• A Prototype-Oriented Clustering for Domain Shift with Source Privacy [66.67700676888629]
  We introduce Prototype-oriented Clustering with Distillation (PCD) to improve the performance and applicability of existing methods. PCD first constructs a source clustering model by aligning the distributions of prototypes and data. It then distills the knowledge to the target model through cluster labels provided by the source model while simultaneously clustering the target data.
  arXiv  Detail & Related papers  (2023-02-08T00:15:35Z)
• BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation [74.93176783541332]
  Source-free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to the unlabeled target domain without accessing the well-labeled source data. To make up for the absence of source data, most existing methods introduced feature prototype based pseudo-labeling strategies. We propose a general class-Balanced Multicentric Dynamic prototype strategy for the SFDA task.
  arXiv  Detail & Related papers  (2022-04-06T13:23:02Z)
• Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection [85.11649974840758]
  3D object detection networks tend to be biased towards the data they are trained on. We propose a single-frame approach for source-free, unsupervised domain adaptation of lidar-based 3D object detectors.
  arXiv  Detail & Related papers  (2021-11-30T18:42:42Z)
• Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data [32.77436219094282]
  Unsupervised domain adaptation aims to align a labeled source domain and an unlabeled target domain without accessing source data. We design an innovative historical contrastive learning (HCL) technique that exploits historical source hypothesis to make up for the absence of source data in UMA. HCL outperforms and complements state-of-the-art methods consistently across a variety of visual tasks.
  arXiv  Detail & Related papers  (2021-10-07T12:13:00Z)
• Distill and Fine-tune: Effective Adaptation from a Black-box Source Model [138.12678159620248]
  Unsupervised domain adaptation (UDA) aims to transfer knowledge in previous related labeled datasets (source) to a new unlabeled dataset (target) We propose a novel two-step adaptation framework called Distill and Fine-tune (Dis-tune)
  arXiv  Detail & Related papers  (2021-04-04T05:29:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.