Multi-Label Test-Time Adaptation with Bayesian Conditional Priors
Multi-label recognition with frozen Vision-Language Models (VLMs) is brittle under distribution shift: standard zero-shot inference scores labels independently, ignoring co-occurrence structure and producing incoherent label sets where dominant concepts suppress weaker but compatible labels. We introduce Bayesian Conditional Priors (BCP) Estimation, a gradient-free test-time adaptation method that injects label dependency without tuning the backbone. BCP views zero-shot logits as a proxy for marginal posteriors under a fixed image-text likelihood and attributes shift-induced errors mainly to a mismatched label prior. For each test image, it selects a high-confidence anchor label and applies an anchor-conditioned Bayesian refinement. This update is closed-form in logit space and admits a pointwise mutual information (PMI) interpretation, explicitly promoting compatible labels and suppressing incompatible ones. BCP operates without target annotations by estimating anchor-conditioned priors online from the unlabeled test stream via lightweight second-order co-occurrence statistics, adding negligible overhead beyond a single forward pass. Across standard multi-label benchmarks and multiple CLIP backbones, BCP consistently outperforms strong TTA baselines, e.g., improving RN50 average mAP from 57.31 to 69.22 and ViT-B/16 from 62.61 to 71.79.
Code (0)
등록된 구현이 없습니다.
Tasks
Test-time AdaptationSimilar Papers 제목 키워드 기반
Training on Test Data with Bayesian Adaptation for Covariate Shift
When faced with distribution shift at test time, deep neural networks often make inaccurate predictions with unreliable uncertainty estimates. While improving the robustness of neural networks is one promising approach t…
Domain Adaptationimage-classificationImage ClassificationBayesian Adaptation for Covariate Shift
When faced with distribution shift at test time, deep neural networks often make inaccurate predictions with unreliable uncertainty estimates.While improving the robustness of neural networks is one promising approach to…
Domain Adaptationimage-classificationImage ClassificationVariational Continual Test-Time Adaptation
The prior drift is crucial in Continual Test-Time Adaptation (CTTA) methods that only use unlabeled test data, as it can cause significant error propagation. In this paper, we introduce VCoTTA, a variational Bayesian app…
Test-time AdaptationVariational InferenceOrder-Aware Test-Time Adaptation: Leveraging Temporal Dynamics for Robust Streaming Inference
Test-Time Adaptation (TTA) enables pre-trained models to adjust to distribution shift by learning from unlabeled test-time streams. However, existing methods typically treat these streams as independent samples, overlook…
Test-time AdaptationImage ClassificationSentiment AnalysisiLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis
Parameter-efficient adaptation has made LLMs practical for domain prediction, but standard LoRA still relies on a static low-rank update and does not expose the latent interactions that often drive scientific labels. We …