• Home
  • Search
  • Semi-supervised Domain Adaptation by Similarity Based Pseudo-Label Injection
  • Cite Icon2
  • https://doi.org/10.1007/978-3-031-25063-7_10Copy DOI Icon

Semi-supervised Domain Adaptation by Similarity Based Pseudo-Label Injection

  • Jan 1, 2023
  • Abhay Rawat +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

One of the primary challenges in Semi-supervised Domain Adaptation (SSDA) is the skewed ratio between the number of labeled source and target samples, causing the model to be biased towards the source domain. Recent works in SSDA show that aligning only the labeled target samples with the source samples potentially leads to incomplete domain alignment of the target domain to the source domain. In our approach, to align the two domains, we leverage contrastive losses to learn a semantically meaningful and a domain agnostic feature space using the supervised samples from both domains. To mitigate challenges caused by the skewed label ratio, we pseudo-label the unlabeled target samples by comparing their feature representation to those of the labeled samples from both the source and target domains. Furthermore, to increase the support of the target domain, these potentially noisy pseudo-labels are gradually injected into the labeled target dataset over the course of training. Specifically, we use a temperature scaled cosine similarity measure to assign a soft pseudo-label to the unlabeled target samples. Additionally, we compute an exponential moving average of the soft pseudo-labels for each unlabeled sample. These pseudo-labels are progressively injected (or removed) into the (from) the labeled target dataset based on a confidence threshold to supplement the alignment of the source and target distributions. Finally, we use a supervised contrastive loss on the labeled and pseudo-labeled datasets to align the source and target distributions. Using our proposed approach, we showcase state-of-the-art performance on SSDA benchmarks - Office-Home, DomainNet and Office-31. The inference code is available at https://github.com/abhayraw1/SPI

Similar Papers
  • Conference Article
  • Citations137

Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation

  • Jun 01, 2021
  • Jichang Li +3
  • Conference Article
  • Citations2

Towards Realizing the Value of Labeled Target Samples: A Two-Stage Approach for Semi-Supervised Domain Adaptation

  • Jun 04, 2023
  • Mengqun Jin +4
  • Conference Article
  • Citations2

Semi-supervised Adversarial Domain Adaptation Based on Maximum Mean Discrepancy

  • Oct 22, 2021
  • Chang'An Yi +4
  • Conference Article
  • Citations31

Improving Semi-Supervised Domain Adaptation Using Effective Target Selection and Semantics

  • Jun 01, 2021
  • Anurag Singh +8
  • PDF
  • Research Article
  • Citations33

Multi-View Collaborative Learning for Semi-Supervised Domain Adaptation

  • Jan 01, 2021
  • IEEE Access
  • Ba Hung Ngo +3
  • Research Article
  • Citations25

ACT: Semi-supervised Domain-adaptive Medical Image Segmentation with Asymmetric Co-Training.

  • Jan 01, 2022
  • Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
  • Xiaofeng Liu +6
  • Conference Article
  • Citations58

ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation

  • Oct 01, 2021
  • Kai Li +4
  • Conference Article
  • Citations14

Semi-supervised Domain Adaptation via Prototype-based Multi-level Learning

  • Aug 01, 2023
  • Xinyang Huang +2
  • Research Article

Fully semisupervised framework for visual domain adaptation

  • Feb 18, 2019
  • Journal of Electronic Imaging
  • Depeng Gao +3
  • Research Article
  • Citations19

Semi-Supervised Domain Adaptation Using Explicit Class-Wise Matching for Domain-Invariant and Class-Discriminative Feature Learning

  • Jan 01, 2021
  • IEEE Access
  • Ba Hung Ngo +3
  • Conference Article
  • Citations1

Classification of Remote Sensing scenes using Semi-Supervised Domain Adaptation based on Entropy Adversarial Optimization

  • Apr 01, 2021
  • Tariq Lasloum +2
  • Research Article
  • Citations4

Robust transfer joint matching distributions in semi-supervised domain adaptation for hyperspectral images classification

  • Oct 06, 2020
  • International Journal of Remote Sensing
  • Arash Saboori +1
  • PDF
  • Research Article
  • Citations6

DEEP DOMAIN ADAPTATION BY WEIGHTED ENTROPY MINIMIZATION FOR THE CLASSIFICATION OF AERIAL IMAGES

  • Aug 03, 2020
  • ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
  • D Wittich
  • Research Article
  • Citations24

Unsupervised domain-adaptive scene-specific pedestrian detection for static video surveillance

  • May 19, 2021
  • Pattern Recognition
  • Quanzheng Mou +8
  • Research Article
  • Citations36

Multidomain Adaptation With Sample and Source Distillation.

  • Apr 01, 2024
  • IEEE Transactions on Cybernetics
  • Keqiuyin Li +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.