arXiv Computer Vision
Training-Free Active Test-Time Adaptation for Vision-Language Models
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Sep 30
WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation
arXiv:2609.37687v1 Announce Type: new Abstract: Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively queryin...
arXiv AI
Sep 16
Sparse MLLM Anchors, Dense Adaptation: Breaking the Self-Referential Loop in Wild Test-Time Adaptation
The paper introduces MASA, a method for Wild Test-Time Adaptation that uses a frozen multimodal large language model to provide structured semantic anchors, thereby avoiding the self-referential loop common in existing WTTA techniques. MASA selects a small, diverse set of reliability-ranked anchors, encodes their descriptions, propagates them to nearby test samples, and stores this visual‑semantic information in an online prototype memory. The stored descriptors enable lightweight adaptation of normalization parameters, and MASA is evaluated on the WTTA ImageNet‑C benchmark with ResNet and ViT backbones under limited‑batch, mixed‑domain, and imbalanced‑label‑shift scenarios.
arXiv AI
4d ago
Batch-Conditioned Semantic Anchors for Robust Transductive Adaptation of Vision--Language Models
Batch-Conditioned Semantic Anchors for Robust Transductive Adaptation of Vision–Language Models proposes JPTA, a prior-aware framework that refines vision-language model predictions at test time by estimating batch-conditioned semantic references. Unlike aggressive methods that risk drift on sparse or shifted batches, or conservative methods that may under-adapt, JPTA calibrates the influence of CLIP text prototypes based on batch reliability, yielding consistent performance gains across benchmarks, especially in sparse and prior-shifted scenarios.
arXiv Computer Vision
Sep 3
Test-Time Logit Prompting for Source-Free Missing Modality Adaptation
The paper introduces Test-Time Logit Prompting (TLP), a lightweight framework that adapts vision-language models to missing-modality inputs without accessing source training data. TLP optimizes logit prompts using uncertainty-aware adjustments and modality-complete consistency regularization, thereby maintaining prediction confidence and semantic consistency. Experiments on various benchmarks show that TLP improves recognition performance by up to 8% while requiring only a few hundred tunable parameters and minimal test-time optimization steps.
arXiv Computer Vision
Sep 1
GATE: Reliability-Gated Gaussian Evidence Fusion for Training-Free Test-Time Adaptation of Vision-Language Models
arXiv:2608.29395v1 Announce Type: new Abstract: Vision-language models such as CLIP and SigLIP provide strong zero-shot recognition, but their predictions can degrade when deployed on target data tha...
Hugging Face Trending Papers
Sep 15
Sparse MLLM Anchors, Dense Adaptation: Breaking the Self-Referential Loop in Wild Test-Time Adaptation
Wild test-time adaptation (WTTA) updates a source model online under small test batches, concurrent distribution shifts, and time-varying class imbalance. Most WTTA methods derive their adaptation sig...