GeT: Generative Target Structure Debiasing for Domain Adaptation

• URL: http://arxiv.org/abs/2308.10205v1
• Date: Sun, 20 Aug 2023 08:52:43 GMT
• Title: GeT: Generative Target Structure Debiasing for Domain Adaptation
• Authors: Can Zhang and Gim Hee Lee
• Abstract summary: Domain adaptation (DA) aims to transfer knowledge from a fully labeled source to a scarcely labeled or totally unlabeled target under domain shift. Recently, semi-supervised learning-based (SSL) techniques that leverage pseudo labeling have been increasingly used in DA. In this paper, we propose GeT that learns a non-bias target embedding distribution with high quality pseudo labels.
• Score: 67.17025068995835
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Domain adaptation (DA) aims to transfer knowledge from a fully labeled source to a scarcely labeled or totally unlabeled target under domain shift. Recently, semi-supervised learning-based (SSL) techniques that leverage pseudo labeling have been increasingly used in DA. Despite the competitive performance, these pseudo labeling methods rely heavily on the source domain to generate pseudo labels for the target domain and therefore still suffer considerably from source data bias. Moreover, class distribution bias in the target domain is also often ignored in the pseudo label generation and thus leading to further deterioration of performance. In this paper, we propose GeT that learns a non-bias target embedding distribution with high quality pseudo labels. Specifically, we formulate an online target generative classifier to induce the target distribution into distinctive Gaussian components weighted by their class priors to mitigate source data bias and enhance target class discriminability. We further propose a structure similarity regularization framework to alleviate target class distribution bias and further improve target class discriminability. Experimental results show that our proposed GeT is effective and achieves consistent improvements under various DA settings with and without class distribution bias. Our code is available at: https://lulusindazc.github.io/getproject/.

Related papers

• Evidential Graph Contrastive Alignment for Source-Free Blending-Target Domain Adaptation [3.0134158269410207]
  We propose a new method called Evidential Contrastive Alignment (ECA) to decouple the blending target domain and alleviate the effect from noisy target pseudo labels. ECA outperforms other methods with considerable gains and achieves comparable results compared with those that have domain labels or source data in prior.
  arXiv  Detail & Related papers  (2024-08-14T13:02:20Z)
• 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)
• Cycle Label-Consistent Networks for Unsupervised Domain Adaptation [57.29464116557734]
  Domain adaptation aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution. We propose a simple yet efficient domain adaptation method, i.e. Cycle Label-Consistent Network (CLCN), by exploiting the cycle consistency of classification label. We demonstrate the effectiveness of our approach on MNIST-USPS-SVHN, Office-31, Office-Home and Image CLEF-DA benchmarks.
  arXiv  Detail & Related papers  (2022-05-27T13:09:08Z)
• Source-Free Domain Adaptation via Distribution Estimation [106.48277721860036]
  Domain Adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain whose data distributions are different. Recently, Source-Free Domain Adaptation (SFDA) has drawn much attention, which tries to tackle domain adaptation problem without using source data. In this work, we propose a novel framework called SFDA-DE to address SFDA task via source Distribution Estimation.
  arXiv  Detail & Related papers  (2022-04-24T12:22:19Z)
• Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation [31.50802009879241]
  Domain adaptive semantic segmentation aims to learn a model with the supervision of source domain data, and produce dense predictions on unlabeled target domain. One popular solution to this challenging task is self-training, which selects high-scoring predictions on target samples as pseudo labels for training. We propose to directly explore the intrinsic pixel distributions of target domain data, instead of heavily relying on the source domain.
  arXiv  Detail & Related papers  (2022-03-18T04:56:20Z)
• 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)
• Learning Target Domain Specific Classifier for Partial Domain Adaptation [85.71584004185031]
  Unsupervised domain adaptation (UDA) aims at reducing the distribution discrepancy when transferring knowledge from a labeled source domain to an unlabeled target domain. This paper focuses on a more realistic UDA scenario, where the target label space is subsumed to the source label space.
  arXiv  Detail & Related papers  (2020-08-25T02:28:24Z)

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.