Dual-Teacher Distillation with Subnetwork Rectification for Black-Box Domain Adaptation

• URL: http://arxiv.org/abs/2603.22908v2
• Date: Wed, 25 Mar 2026 03:47:44 GMT
• Title: Dual-Teacher Distillation with Subnetwork Rectification for Black-Box Domain Adaptation
• Abstract summary: Black box domain adaptation represents a highly practical yet extremely challenging setting.<n>We propose a dual teacher distillation with subnetwork rectification (DDSR) model that exploits specific knowledge embedded in black box source models.<n>Our approach demonstrates consistent improvements over state of the art methods, including those using source data or models.
• Score: 69.7036779439312
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Assuming that neither source data nor the source model is accessible, black box domain adaptation represents a highly practical yet extremely challenging setting, as transferable information is restricted to the predictions of the black box source model, which can only be queried using target samples. Existing approaches attempt to extract transferable knowledge through pseudo label refinement or by leveraging external vision language models (ViLs), but they often suffer from noisy supervision or insufficient utilization of the semantic priors provided by ViLs, which ultimately hinder adaptation performance. To overcome these limitations, we propose a dual teacher distillation with subnetwork rectification (DDSR) model that jointly exploits the specific knowledge embedded in black box source models and the general semantic information of a ViL. DDSR adaptively integrates their complementary predictions to generate reliable pseudo labels for the target domain and introduces a subnetwork driven regularization strategy to mitigate overfitting caused by noisy supervision. Furthermore, the refined target predictions iteratively enhance both the pseudo labels and ViL prompts, enabling more accurate and semantically consistent adaptation. Finally, the target model is further optimized through self training with classwise prototypes. Extensive experiments on multiple benchmark datasets validate the effectiveness of our approach, demonstrating consistent improvements over state of the art methods, including those using source data or models.

Related papers

• Did Models Sufficient Learn? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation [61.248535801314375]
  Subset-Selected Counterfactual Augmentation (SS-CA)<n>We develop Counterfactual LIMA to identify minimal spatial region sets whose removal can selectively alter model predictions.<n>Experiments show that SS-CA improves generalization on in-distribution (ID) test data and achieves superior performance on out-of-distribution (OOD) benchmarks.
  arXiv  Detail & Related papers  (2025-11-15T08:39:22Z)
• Conformal Prediction for Zero-Shot Models [20.94974284175104]
  We investigate the capabilities of CLIP models under the split conformal prediction paradigm.<n>We propose Conf-OT, a transfer learning setting that operates transductive over the combined calibration and query sets.
  arXiv  Detail & Related papers  (2025-05-30T15:16:19Z)
• Source-free Semantic Regularization Learning for Semi-supervised Domain Adaptation [25.51051224329922]
  Semi-supervised domain adaptation (SSDA) has been extensively researched due to its ability to improve classification performance and generalization ability of models.<n>We propose a novel SSDA learning framework called semantic regularization learning (SERL)<n>SERL captures the target semantic information from multiple perspectives of regularization learning to achieve adaptive fine-tuning of the source pre-trained model on the target domain.
  arXiv  Detail & Related papers  (2025-01-02T07:53:02Z)
• Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence [60.37934652213881]
  Domain Adaptation (DA) facilitates knowledge transfer from a source domain to a related target domain. This paper investigates a practical DA paradigm, namely Source data-Free Active Domain Adaptation (SFADA), where source data becomes inaccessible during adaptation. We present learn from the learnt (LFTL), a novel paradigm for SFADA to leverage the learnt knowledge from the source pretrained model and actively iterated models without extra overhead.
  arXiv  Detail & Related papers  (2024-07-26T17:51:58Z)
• Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer [54.32283739486781]
  We present a textbfForgery-aware textbfAdaptive textbfVision textbfTransformer (FA-ViT) under the adaptive learning paradigm. FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation.
  arXiv  Detail & Related papers  (2023-09-20T06:51:11Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• Curriculum Guided Domain Adaptation in the Dark [0.0]
  Domain adaptation in the dark aims to adapt a black-box source trained model to an unlabeled target domain without access to source data or source model parameters. We present Curriculum Adaptation for Black-Box (CABB) which provides a curriculum guided adaptation approach to gradually train the target model. Our method utilizes co-training of a dual-branch network to suppress error accumulation resulting from confirmation bias.
  arXiv  Detail & Related papers  (2023-08-02T05:47:56Z)
• ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation [48.039156140237615]
  A Continual Test-Time Adaptation task is proposed to adapt the pre-trained model to continually changing target domains. We design a Visual Domain Adapter (ViDA) for CTTA, explicitly handling both domain-specific and domain-shared knowledge. Our proposed method achieves state-of-the-art performance in both classification and segmentation CTTA tasks.
  arXiv  Detail & Related papers  (2023-06-07T11:18:53Z)
• Confidence Attention and Generalization Enhanced Distillation for Continuous Video Domain Adaptation [62.458968086881555]
  Continuous Video Domain Adaptation (CVDA) is a scenario where a source model is required to adapt to a series of individually available changing target domains. We propose a Confidence-Attentive network with geneRalization enhanced self-knowledge disTillation (CART) to address the challenge in CVDA.
  arXiv  Detail & Related papers  (2023-03-18T16:40:10Z)
• RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation [80.03883315743715]
  Source-free domain adaptation transits the source-trained model towards target domain without exposing the source data. This paradigm is still at risk of data leakage due to adversarial attacks on the source model. We propose a novel approach named RAIN (RegulArization on Input and Network) for Black-Box domain adaptation from both input-level and network-level regularization.
  arXiv  Detail & Related papers  (2022-08-22T18:18:47Z)

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.