GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning

• URL: http://arxiv.org/abs/2403.14410v1
• Date: Thu, 21 Mar 2024 13:57:45 GMT
• Title: GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning
• Authors: Sanqing Qu, Tianpei Zou, Florian Röhrbein, Cewu Lu, Guang Chen, Dacheng Tao, Changjun Jiang,
• Abstract summary: Source-Free Universal Domain Adaptation (SF-UniDA) aims to accurately classify "known" data belonging to common categories. We propose a novel Global and Local Clustering (GLC) technique, which comprises an adaptive one-vs-all global clustering algorithm. We evolve GLC to GLC++, integrating a contrastive affinity learning strategy.
• Score: 84.54244771470012
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks often exhibit sub-optimal performance under covariate and category shifts. Source-Free Domain Adaptation (SFDA) presents a promising solution to this dilemma, yet most SFDA approaches are restricted to closed-set scenarios. In this paper, we explore Source-Free Universal Domain Adaptation (SF-UniDA) aiming to accurately classify "known" data belonging to common categories and segregate them from target-private "unknown" data. We propose a novel Global and Local Clustering (GLC) technique, which comprises an adaptive one-vs-all global clustering algorithm to discern between target classes, complemented by a local k-NN clustering strategy to mitigate negative transfer. Despite the effectiveness, the inherent closed-set source architecture leads to uniform treatment of "unknown" data, impeding the identification of distinct "unknown" categories. To address this, we evolve GLC to GLC++, integrating a contrastive affinity learning strategy. We examine the superiority of GLC and GLC++ across multiple benchmarks and category shift scenarios. Remarkably, in the most challenging open-partial-set scenarios, GLC and GLC++ surpass GATE by 16.7% and 18.6% in H-score on VisDA, respectively. GLC++ enhances the novel category clustering accuracy of GLC by 4.3% in open-set scenarios on Office-Home. Furthermore, the introduced contrastive learning strategy not only enhances GLC but also significantly facilitates existing methodologies.

Related papers

• Federated Learning with Bilateral Curation for Partially Class-Disjoint Data [47.55180390473258]
  Partially class-disjoint data (PCDD), a common yet under-explored data formation, severely challenges the performance of federated algorithms. We propose a novel approach called FedGELA where the ETF is globally fixed as a simplex ETF while locally adapted to the personal distributions. We conduct extensive experiments on a range of datasets to demonstrate that our FedGELA achieves promising performance.
  arXiv  Detail & Related papers  (2024-05-29T10:34:44Z)
• Federated Generalized Category Discovery [68.35420359523329]
  Generalized category discovery (GCD) aims at grouping unlabeled samples from known and unknown classes. To meet the recent decentralization trend in the community, we introduce a practical yet challenging task, namely Federated GCD (Fed-GCD) The goal of Fed-GCD is to train a generic GCD model by client collaboration under the privacy-protected constraint.
  arXiv  Detail & Related papers  (2023-05-23T14:27:41Z)
• Upcycling Models under Domain and Category Shift [95.22147885947732]
  We introduce an innovative global and local clustering learning technique (GLC) We design a novel, adaptive one-vs-all global clustering algorithm to achieve the distinction across different target classes. Remarkably, in the most challenging open-partial-set DA scenario, GLC outperforms UMAD by 14.8% on the VisDA benchmark.
  arXiv  Detail & Related papers  (2023-03-13T13:44:04Z)
• Chaos to Order: A Label Propagation Perspective on Source-Free Domain Adaptation [8.27771856472078]
  We present Chaos to Order (CtO), a novel approach for source-free domain adaptation (SFDA) CtO strives to constrain semantic credibility and propagate label information among target subpopulations. Empirical evidence demonstrates that CtO outperforms the state of the arts on three public benchmarks.
  arXiv  Detail & Related papers  (2023-01-20T03:39:35Z)
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [122.62311703151215]
  Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations. DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
  arXiv  Detail & Related papers  (2022-11-12T09:21:49Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation [74.71931918541748]
  We propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA. We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process. We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-03T01:33:14Z)

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.