Revisiting CLIP for SF-OSDA: Unleashing Zero-Shot Potential with Adaptive Threshold and Training-Free Feature Filtering

• URL: http://arxiv.org/abs/2504.14224v1
• Date: Sat, 19 Apr 2025 08:12:19 GMT
• Title: Revisiting CLIP for SF-OSDA: Unleashing Zero-Shot Potential with Adaptive Threshold and Training-Free Feature Filtering
• Authors: Yongguang Li, Jindong Li, Qi Wang, Qianli Xing, Runliang Niu, Shengsheng Wang, Menglin Yang,
• Abstract summary: We propose CLIPXpert, a novel SF-OSDA approach that integrates two key components: an adaptive thresholding strategy and an unknown class feature filtering module.<n> Experiments show that our source-free and training-free method outperforms state-of-the-art trained approach UOTA by 1.92% on the DomainNet dataset.
• Score: 8.875465803682808
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Source-Free Unsupervised Open-Set Domain Adaptation (SF-OSDA) methods using CLIP face significant issues: (1) while heavily dependent on domain-specific threshold selection, existing methods employ simple fixed thresholds, underutilizing CLIP's zero-shot potential in SF-OSDA scenarios; and (2) overlook intrinsic class tendencies while employing complex training to enforce feature separation, incurring deployment costs and feature shifts that compromise CLIP's generalization ability. To address these issues, we propose CLIPXpert, a novel SF-OSDA approach that integrates two key components: an adaptive thresholding strategy and an unknown class feature filtering module. Specifically, the Box-Cox GMM-Based Adaptive Thresholding (BGAT) module dynamically determines the optimal threshold by estimating sample score distributions, balancing known class recognition and unknown class sample detection. Additionally, the Singular Value Decomposition (SVD)-Based Unknown-Class Feature Filtering (SUFF) module reduces the tendency of unknown class samples towards known classes, improving the separation between known and unknown classes. Experiments show that our source-free and training-free method outperforms state-of-the-art trained approach UOTA by 1.92% on the DomainNet dataset, achieves SOTA-comparable performance on datasets such as Office-Home, and surpasses other SF-OSDA methods. This not only validates the effectiveness of our proposed method but also highlights CLIP's strong zero-shot potential for SF-OSDA tasks.

Related papers

• Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation Framework [9.03028904066824]
  Open-set Domain Adaptation (OSDA) aims to adapt a model from a labeled source domain to an unlabeled target domain. We propose Recall and Refine (RRDA), a novel SF-OSDA framework designed to address limitations by explicitly learning features for target-private unknown classes.
  arXiv  Detail & Related papers  (2024-11-19T15:18:50Z)
• Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation [22.474866164542302]
  UDA approaches commonly assume that source and target domains share the same labels space. This paper considers the more challenging Source-Free Open-set Domain Adaptation (SF-OSDA) setting. We propose a novel approach for SF-OSDA that exploits the granularity of target-private categories by segregating their samples into multiple unknown classes.
  arXiv  Detail & Related papers  (2024-04-16T13:52:00Z)
• A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation [121.0693322732454]
  Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods to enhance CLIP's performance in downstream tasks. We revisit a classical algorithm, Gaussian Discriminant Analysis (GDA), and apply it to the downstream classification of CLIP.
  arXiv  Detail & Related papers  (2024-02-06T15:45:27Z)
• Activate and Reject: Towards Safe Domain Generalization under Category Shift [71.95548187205736]
  We study a practical problem of Domain Generalization under Category Shift (DGCS) It aims to simultaneously detect unknown-class samples and classify known-class samples in the target domains. Compared to prior DG works, we face two new challenges: 1) how to learn the concept of unknown'' during training with only source known-class samples, and 2) how to adapt the source-trained model to unseen environments.
  arXiv  Detail & Related papers  (2023-10-07T07:53:12Z)
• Self-Paced Learning for Open-Set Domain Adaptation [50.620824701934]
  Traditional domain adaptation methods presume that the classes in the source and target domains are identical. Open-set domain adaptation (OSDA) addresses this limitation by allowing previously unseen classes in the target domain. We propose a novel framework based on self-paced learning to distinguish common and unknown class samples.
  arXiv  Detail & Related papers  (2023-03-10T14:11:09Z)
• 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)
• Towards Accurate Open-Set Recognition via Background-Class Regularization [36.96359929574601]
  In open-set recognition (OSR), classifiers should be able to reject unknown-class samples while maintaining high closed-set classification accuracy. Previous studies attempted to limit latent feature space and reject data located outside the limited space via offline analyses. We propose a simple inference process (without offline analyses) to conduct OSR in standard classifier architectures. We show that the proposed method provides robust OSR results, while maintaining high closed-set classification accuracy.
  arXiv  Detail & Related papers  (2022-07-21T03:55:36Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data [78.69828864672978]
  A central challenge in training classification models in the real-world federated system is learning with non-IID data. We propose a novel and simple algorithm called Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated ssian mixture model. Experimental results demonstrate that CCVR state-of-the-art performance on popular federated learning benchmarks including CIFAR-10, CIFAR-100, and CINIC-10.
  arXiv  Detail & Related papers  (2021-06-09T12:02:29Z)
• Source-Free Open Compound Domain Adaptation in Semantic Segmentation [99.82890571842603]
  In SF-OCDA, only the source pre-trained model and the target data are available to learn the target model. We propose the Cross-Patch Style Swap (CPSS) to diversify samples with various patch styles in the feature-level. Our method produces state-of-the-art results on the C-Driving dataset.
  arXiv  Detail & Related papers  (2021-06-07T08:38:41Z)

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.