Source-Free Domain Adaptation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

7 leaderboard tables shown for this task, 7 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

6 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

2 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 103 papers with code (188 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Upcycling Models under Domain and Category Shift
  13 Mar 2023 3 repositories listed
  We examine the superiority of our GLC on multiple benchmarks with different category shift scenarios, including partial-set, open-set, and open-partial-set DA.
• Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation
  27 Jul 2022 3 repositories listed Syntology ran 6 of 13 samples · 7 unverified
  The prime challenge in unsupervised domain adaptation (DA) is to mitigate the domain shift between the source and target domains.
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
  20 Feb 2020 3 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain.
• Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-Prompting
  13 May 2025 2 repositories listed
  Source-free domain adaptation (SFDA) for segmentation aims at adapting a model trained in the source domain to perform well in the target domain with only the source model and unlabeled target data.
• GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning
  21 Mar 2024 2 repositories listed
  GLC++ enhances the novel category clustering accuracy of GLC by 4.
• Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning
  2 Jun 2023 2 repositories listed
  It utilizes a well-trained source model and unlabeled target data to achieve adaptation in the target domain.
• Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation
  7 Mar 2023 2 repositories listed Syntology ran 1 of 3 samples · 2 unverified · 3 pointer-only (licence)
  We propose a novel approach for the SF-UDA setting based on a loss reweighting strategy that brings robustness against the noise that inevitably affects the pseudo-labels.
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning
  12 Nov 2022 2 repositories listed Syntology ran 7 of 18 samples · 11 unverified · 15 pointer-only (licence)
  We investigate a practical domain adaptation task, called source-free domain adaptation (SFUDA), where the source-pretrained model is adapted to the target domain without access to the source data.
• ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation
  29 May 2022 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  First of all, to avoid additional parameters and explore the information in the source model, ProxyMix defines the weights of the classifier as the class prototypes and then constructs a class-balanced proxy source…
• Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
  8 Oct 2021 2 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  In this paper, we address the challenging source-free domain adaptation (SFDA) problem, where the source pretrained model is adapted to the target domain in the absence of source data.
• Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
  14 Dec 2020 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 2 pointer-only (licence)
  Furthermore, we propose a new labeling transfer strategy, which separates the target data into two splits based on the confidence of predictions (labeling information), and then employ semi-supervised learning to…
• SS-SFDA : Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous Environments
  27 Nov 2020 2 repositories listed
  We present a novel approach for unsupervised road segmentation in adverse weather conditions such as rain or fog.
• Casting a BAIT for Offline and Online Source-free Domain Adaptation
  23 Oct 2020 2 repositories listed
  When adapting to the target domain, the additional classifier initialized from source classifier is expected to find misclassified features.
• Tent: Fully Test-time Adaptation by Entropy Minimization
  18 Jun 2020 2 repositories listed Syntology ran 8 of 9 samples · 1 unverified · 3 pointer-only (licence)
  A model must adapt itself to generalize to new and different data during testing.
• SRPL-SFDA: SAM-Guided Reliable Pseudo-Labels for Source-Free Domain Adaptation in Medical Image Segmentation
  11 Jun 2025 1 repository listed
  Domain Adaptation (DA) is crucial for robust deployment of medical image segmentation models when applied to new clinical centers with significant domain shifts.
• Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation
  30 May 2025 1 repository listed
  A new augmentation technique, Shuffle PatchMix (SPM), and a novel reweighting strategy are introduced to enhance performance.
• DDFP: Data-dependent Frequency Prompt for Source Free Domain Adaptation of Medical Image Segmentation
  15 May 2025 1 repository listed
  To further enhance adaptation, we employ a style-related layer fine-tuning strategy, specifically designed for SFDA, to train the target model using the prompted target domain images and pseudo-labels.
• Effective Dual-Region Augmentation for Reduced Reliance on Large Amounts of Labeled Data
  17 Apr 2025 1 repository listed
  This paper introduces a novel dual-region augmentation approach designed to reduce reliance on large-scale labeled datasets while improving model robustness and adaptability across diverse computer vision tasks,…
• Disentangled Source-Free Personalization for Facial Expression Recognition with Neutral Target Data
  26 Mar 2025 1 repository listed
  This paper introduces the Disentangled Source-Free Domain Adaptation (DSFDA) method to address the SFDA challenge posed by missing target expression data.
• Source-free domain adaptation based on label reliability for cross-domain bearing fault diagnosis
  11 Mar 2025 1 repository listed
  We argue that every target sample can contribute to model adaptation, and accordingly propose in this paper a novel SFDA-based approach for bearing fault diagnosis that exploits both reliable and unreliable…
• AIF-SFDA: Autonomous Information Filter-driven Source-Free Domain Adaptation for Medical Image Segmentation
  6 Jan 2025 1 repository listed
  Decoupling domain-variant information (DVI) from domain-invariant information (DII) serves as a prominent strategy for mitigating domain shifts in the practical implementation of deep learning algorithms.
• Bridge then Begin Anew: Generating Target-relevant Intermediate Model for Source-free Visual Emotion Adaptation
  18 Dec 2024 1 repository listed
  For reducing reliance on data labeling, domain adaptation offers an alternative solution by adapting models trained on labeled source data to unlabeled target data.
• What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood Context
  18 Dec 2024 1 repository listed Syntology ran 4 of 4 samples · 0 unverified · 4 pointer-only (licence)
  The absence of access to source data during adaptation makes it challenging to analytically estimate the domain gap.
• Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation Framework
  19 Nov 2024 1 repository listed Syntology ran 3 of 5 samples · 2 unverified · 2 pointer-only (licence)
  Open-set Domain Adaptation (OSDA) aims to adapt a model from a labeled source domain to an unlabeled target domain, where novel classes - also referred to as target-private unknown classes - are present.
• GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation
  22 Oct 2024 1 repository listed
  To achieve domain alignment, GALA employs a graph diffusion model to reconstruct source-style graphs from target data.
• A3: Active Adversarial Alignment for Source-Free Domain Adaptation
  27 Sep 2024 1 repository listed
  A3 advances source-free UDA through its synergistic integration of active and adversarial learning for effective domain alignment and noise reduction.
• Source-Free Domain Adaptation for YOLO Object Detection
  25 Sep 2024 1 repository listed
  Source-free domain adaptation (SFDA) is a challenging problem in object detection, where a pre-trained source model is adapted to a new target domain without using any source domain data for privacy and efficiency…
• Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation
  6 Sep 2024 1 repository listed Syntology ran 10 of 19 samples · 9 unverified · 19 pointer-only (licence)
  We tackle the challenging problem of source-free unsupervised domain adaptation (SFUDA) for 3D semantic segmentation.
• Dynamic Retraining-Updating Mean Teacher for Source-Free Object Detection
  23 Jul 2024 1 repository listed
  In object detection, unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain.
• EIANet: A Novel Domain Adaptation Approach to Maximize Class Distinction with Neural Collapse Principles
  23 Jul 2024 1 repository listed
  A major challenge in SFDA is deriving accurate categorical information for the target domain, especially when sample embeddings from different classes appear similar.

Syntology lines on 11 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.