Semi-supervised Domain Adaptation via Sample-to-Sample Self-Distillation

• URL: http://arxiv.org/abs/2111.14353v1
• Date: Mon, 29 Nov 2021 07:13:36 GMT
• Title: Semi-supervised Domain Adaptation via Sample-to-Sample Self-Distillation
• Authors: Jeongbeen Yoon, Dahyun Kang, Minsu Cho
• Abstract summary: Semi-supervised domain adaptation (SSDA) is to adapt a learner to a new domain with only a small set of labeled samples when a large labeled dataset is given on a source domain. We propose a pair-based SSDA method that adapts a model to the target domain using self-distillation with sample pairs.
• Score: 30.556465364799948
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Semi-supervised domain adaptation (SSDA) is to adapt a learner to a new domain with only a small set of labeled samples when a large labeled dataset is given on a source domain. In this paper, we propose a pair-based SSDA method that adapts a model to the target domain using self-distillation with sample pairs. Each sample pair is composed of a teacher sample from a labeled dataset (i.e., source or labeled target) and its student sample from an unlabeled dataset (i.e., unlabeled target). Our method generates an assistant feature by transferring an intermediate style between the teacher and the student, and then train the model by minimizing the output discrepancy between the student and the assistant. During training, the assistants gradually bridge the discrepancy between the two domains, thus allowing the student to easily learn from the teacher. Experimental evaluation on standard benchmarks shows that our method effectively minimizes both the inter-domain and intra-domain discrepancies, thus achieving significant improvements over recent methods.

Related papers

• Semi-supervised Domain Adaptation via Prototype-based Multi-level Learning [4.232614032390374]
  In semi-supervised domain adaptation (SSDA), a few labeled target samples of each class help the model to transfer knowledge representation from the fully labeled source domain to the target domain. We propose a Prototype-based Multi-level Learning (ProML) framework to better tap the potential of labeled target samples.
  arXiv  Detail & Related papers  (2023-05-04T10:09:30Z)
• 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)
• Adapting the Mean Teacher for keypoint-based lung registration under geometric domain shifts [75.51482952586773]
  deep neural networks generally require plenty of labeled training data and are vulnerable to domain shifts between training and test data. We present a novel approach to geometric domain adaptation for image registration, adapting a model from a labeled source to an unlabeled target domain. Our method consistently improves on the baseline model by 50%/47% while even matching the accuracy of models trained on target data.
  arXiv  Detail & Related papers  (2022-07-01T12:16:42Z)
• Low-confidence Samples Matter for Domain Adaptation [47.552605279925736]
  Domain adaptation (DA) aims to transfer knowledge from a label-rich source domain to a related but label-scarce target domain. We propose a novel contrastive learning method by processing low-confidence samples. We evaluate the proposed method in both unsupervised and semi-supervised DA settings.
  arXiv  Detail & Related papers  (2022-02-06T15:45:45Z)
• Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection [107.52026281057343]
  We introduce a Frequency Spectrum Augmentation Consistency (FSAC) framework with four different low-frequency filter operations. In the first stage, we utilize all the original and augmented source data to train an object detector. In the second stage, augmented source and target data with pseudo labels are adopted to perform the self-training for prediction consistency.
  arXiv  Detail & Related papers  (2021-12-16T04:07:01Z)
• Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation [22.852237073492894]
  Unsupervised Domain Adaptation (UDA) aims to generalize the knowledge learned from a well-labeled source domain to an unlabeled target domain. We propose a cross-domain discrepancy minimization (CGDM) method which explicitly minimizes the discrepancy of gradients generated by source samples and target samples. In order to compute the gradient signal of target samples, we further obtain target pseudo labels through a clustering-based self-supervised learning.
  arXiv  Detail & Related papers  (2021-06-08T07:35:40Z)
• Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning [86.6929930921905]
  This paper studies how much it can help address domain shifts if we further have a few target samples labeled. To explore the full potential of landmarks, we incorporate a prototypical alignment (PA) module which calculates a target prototype for each class from the landmarks. Specifically, we severely perturb the labeled images, making PA non-trivial to achieve and thus promoting model generalizability.
  arXiv  Detail & Related papers  (2021-04-19T08:46:08Z)
• On Universal Black-Box Domain Adaptation [53.7611757926922]
  We study an arguably least restrictive setting of domain adaptation in a sense of practical deployment. Only the interface of source model is available to the target domain, and where the label-space relations between the two domains are allowed to be different and unknown. We propose to unify them into a self-training framework, regularized by consistency of predictions in local neighborhoods of target samples.
  arXiv  Detail & Related papers  (2021-04-10T02:21:09Z)
• OVANet: One-vs-All Network for Universal Domain Adaptation [78.86047802107025]
  Existing methods manually set a threshold to reject unknown samples based on validation or a pre-defined ratio of unknown samples. We propose a method to learn the threshold using source samples and to adapt it to the target domain. Our idea is that a minimum inter-class distance in the source domain should be a good threshold to decide between known or unknown in the target.
  arXiv  Detail & Related papers  (2021-04-07T18:36:31Z)
• Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation [34.790169990156684]
  We focus on a more practical setting of semi-supervised domain adaptation (SSDA) where both a small set of labeled target data and large amounts of labeled source data are available. Two kinds of data mixing methods are proposed to reduce domain gap in both region-level and sample-level respectively. We can obtain two complementary domain-mixed teachers based on dual-level mixed data from holistic and partial views respectively.
  arXiv  Detail & Related papers  (2021-03-08T12:33:17Z)
• MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation [29.43532067090422]
  We propose an easy-to-implement method dubbed MiniMax Entropy Networks (MMEN) based on adversarial learning. Unlike most existing approaches which employ a generator to deal with domain difference, MMEN focuses on learning the categorical information from unlabeled target samples.
  arXiv  Detail & Related papers  (2019-04-21T13:39:29Z)

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.