Papers › Probabilistic Contrastive Learning for Domain Adaptation

Probabilistic Contrastive Learning for Domain Adaptation

11 Nov 2021arXiv:2111.06021archive 2025-07-28

Junjie Li, Yixin Zhang, Zilei Wang, Keyu Tu, Saihui Hou

Contrastive learning can largely enhance the feature discriminability in a self-supervised manner and has achieved remarkable success for various visual tasks. However, it is undesirably observed that the standard contrastive paradigm (features+ℓ₂ normalization) only brings little help for domain adaptation. In this work, we delve into this phenomenon and find that the main reason is due to the class weights (weights of the final fully connected layer) which are vital for the recognition yet ignored in the optimization. To tackle this issue, we propose a simple yet powerful Probabilistic Contrastive Learning (PCL), which does not only assist in extracting discriminative features but also enforces them to be clustered around the class weights. Specifically, we break the standard contrastive paradigm by removing ℓ₂ normalization and replacing the features with probabilities. In this way, PCL can enforce the probability to approximate the one-hot form, thereby reducing the deviation between the features and class weights. Benefiting from the conciseness, PCL can be well generalized to different settings. In this work, we conduct extensive experiments on five tasks and observe consistent performance gains, i.e., Unsupervised Domain Adaptation (UDA), Semi-Supervised Domain Adaptation (SSDA), Semi-Supervised Learning (SSL), UDA Detection, and UDA Semantic Segmentation. Notably, for UDA Semantic Segmentation on SYNTHIA, PCL surpasses the sophisticated CPSL-D by >2% in terms of mean IoU with a much smaller training cost (PCL: 1*3090, 5 days v.s. CPSL-D: 4*V100, 11 days). Code is available at https://github.com/ljjcoder/Probabilistic-Contrastive-Learning.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ljjcoder/probabilistic-contrastive-learning officialmentioned in papermentioned on GitHubpytorch report
ljjcoder/PCL officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningDomain AdaptationImage ClassificationRepresentation LearningSemantic SegmentationSemi-Supervised Image ClassificationSemi-supervised Domain AdaptationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation Office-Home PCL Accuracy 74.5 #12 of 29 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 40 Labels PCL Percentage error 5.88±1.19 #11 of 21 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-100, 400 Labels PCL (Flexmatch) Percentage error 35.75±0.53 #7 of 21 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-100, 400 Labels PCL (Fixmatch) Percentage error 42.38±2.52 #15 of 21 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive LearningSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections