Reducing Source-Private Bias in Extreme Universal Domain Adaptation

• URL: http://arxiv.org/abs/2410.11271v1
• Date: Tue, 15 Oct 2024 04:51:37 GMT
• Title: Reducing Source-Private Bias in Extreme Universal Domain Adaptation
• Authors: Hung-Chieh Fang, Po-Yi Lu, Hsuan-Tien Lin,
• Abstract summary: Universal Domain Adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. We show that state-of-the-art methods struggle when the source domain has significantly more non-overlapping classes than overlapping ones. We propose using self-supervised learning to preserve the structure of the target data.
• Score: 11.875619863954238
• License:
• Abstract: Universal Domain Adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain without assuming how much the label-sets of the two domains intersect. The goal of UniDA is to achieve robust performance on the target domain across different intersection levels. However, existing literature has not sufficiently explored performance under extreme intersection levels. Our experiments reveal that state-of-the-art methods struggle when the source domain has significantly more non-overlapping classes than overlapping ones, a setting we refer to as Extreme UniDA. In this paper, we demonstrate that classical partial domain alignment, which focuses on aligning only overlapping-class data between domains, is limited in mitigating the bias of feature extractors toward source-private classes in extreme UniDA scenarios. We argue that feature extractors trained with source supervised loss distort the intrinsic structure of the target data due to the inherent differences between source-private classes and the target data. To mitigate this bias, we propose using self-supervised learning to preserve the structure of the target data. Our approach can be easily integrated into existing frameworks. We apply the proposed approach to two distinct training paradigms-adversarial-based and optimal-transport-based-and show consistent improvements across various intersection levels, with significant gains in extreme UniDA settings.

Related papers

• Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias [16.4249819402209]
  We introduce Universal Semi-Supervised Domain Adaptation (UniSSDA) UniSSDA is at the intersection of Universal Domain Adaptation (UniDA) and Semi-Supervised Domain Adaptation (SSDA) We propose a new prior-guided pseudo-label refinement strategy to reduce the reinforcement of common-class bias due to pseudo-labeling.
  arXiv  Detail & Related papers  (2024-03-17T14:43:47Z)
• 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 Adaptation for Semantic Segmentation [3.946367634483361]
  We propose a novel two-step semi-supervised dual-domain adaptation (SSDDA) approach to address both cross- and intra-domain gaps in semantic segmentation. We demonstrate that the proposed approach outperforms state-of-the-art methods on two common synthetic-to-real semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-10-20T16:13:00Z)
• Domain Adaptive Semantic Segmentation without Source Data [50.18389578589789]
  We investigate domain adaptive semantic segmentation without source data, which assumes that the model is pre-trained on the source domain. We propose an effective framework for this challenging problem with two components: positive learning and negative learning. Our framework can be easily implemented and incorporated with other methods to further enhance the performance.
  arXiv  Detail & Related papers  (2021-10-13T04:12:27Z)
• Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection [11.262560426527818]
  Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data. Recently, mainstream approaches perform this task through adversarial learning, yet still suffer from two limitations. We propose a joint adaptive detection framework (JADF) to address the above challenges.
  arXiv  Detail & Related papers  (2021-09-19T00:27:08Z)
• CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation [1.2691047660244335]
  Unsupervised Domain Adaptation (UDA) aims to align the labeled source distribution with the unlabeled target distribution to obtain domain invariant predictive models. We propose Contrastive Learning framework for semi-supervised Domain Adaptation (CLDA) that attempts to bridge the intra-domain gap. CLDA achieves state-of-the-art results on all the above datasets.
  arXiv  Detail & Related papers  (2021-06-30T20:23:19Z)
• 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)
• Inferring Latent Domains for Unsupervised Deep Domain Adaptation [54.963823285456925]
  Unsupervised Domain Adaptation (UDA) refers to the problem of learning a model in a target domain where labeled data are not available. This paper introduces a novel deep architecture which addresses the problem of UDA by automatically discovering latent domains in visual datasets. We evaluate our approach on publicly available benchmarks, showing that it outperforms state-of-the-art domain adaptation methods.
  arXiv  Detail & Related papers  (2021-03-25T14:33:33Z)
• Discriminative Cross-Domain Feature Learning for Partial Domain Adaptation [70.45936509510528]
  Partial domain adaptation aims to adapt knowledge from a larger and more diverse source domain to a smaller target domain with less number of classes. Recent practice on domain adaptation manages to extract effective features by incorporating the pseudo labels for the target domain. It is essential to align target data with only a small set of source data.
  arXiv  Detail & Related papers  (2020-08-26T03:18:53Z)
• Towards Fair Cross-Domain Adaptation via Generative Learning [50.76694500782927]
  Domain Adaptation (DA) targets at adapting a model trained over the well-labeled source domain to the unlabeled target domain lying in different distributions. We develop a novel Generative Few-shot Cross-domain Adaptation (GFCA) algorithm for fair cross-domain classification.
  arXiv  Detail & Related papers  (2020-03-04T23:25:09Z)

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.