Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations

• URL: http://arxiv.org/abs/2507.09500v1
• Date: Sun, 13 Jul 2025 05:37:33 GMT
• Title: Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations
• Authors: Yiwen Liang, Hui Chen, Yizhe Xiong, Zihan Zhou, Mengyao Lyu, Zijia Lin, Shuaicheng Niu, Sicheng Zhao, Jungong Han, Guiguang Ding,
• Abstract summary: Vision-language models (VLMs) exhibit remarkable zero-shot capabilities but struggle with distribution shifts in downstream tasks when labeled data is unavailable.<n>We propose a Reliable Test-time Adaptation (ReTA) method that enhances reliability from two perspectives.
• Score: 67.35596444651037
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language models (VLMs) exhibit remarkable zero-shot capabilities but struggle with distribution shifts in downstream tasks when labeled data is unavailable, which has motivated the development of Test-Time Adaptation (TTA) to improve VLMs' performance during inference without annotations. Among various TTA approaches, cache-based methods show promise by preserving historical knowledge from low-entropy samples in a dynamic cache and fostering efficient adaptation. However, these methods face two critical reliability challenges: (1) entropy often becomes unreliable under distribution shifts, causing error accumulation in the cache and degradation in adaptation performance; (2) the final predictions may be unreliable due to inflexible decision boundaries that fail to accommodate large downstream shifts. To address these challenges, we propose a Reliable Test-time Adaptation (ReTA) method that integrates two complementary strategies to enhance reliability from two perspectives. First, to mitigate the unreliability of entropy as a sample selection criterion for cache construction, we introduce Consistency-aware Entropy Reweighting (CER), which incorporates consistency constraints to weight entropy during cache updating. While conventional approaches rely solely on low entropy for cache prioritization and risk introducing noise, our method leverages predictive consistency to maintain a high-quality cache and facilitate more robust adaptation. Second, we present Diversity-driven Distribution Calibration (DDC), which models class-wise text embeddings as multivariate Gaussian distributions, enabling adaptive decision boundaries for more accurate predictions across visually diverse content. Extensive experiments demonstrate that ReTA consistently outperforms state-of-the-art methods, particularly under challenging real-world distribution shifts.

Related papers

• Learning from Heterogeneity: Generalizing Dynamic Facial Expression Recognition via Distributionally Robust Optimization [23.328511708942045]
  Heterogeneity-aware Distributional Framework (HDF) designed to enhance time-frequency modeling and mitigate imbalance caused by hard samples.<n>Time-Frequency Distributional Attention Module (DAM) captures both temporal consistency and frequency robustness.<n> adaptive optimization module Distribution-aware Scaling Module (DSM) introduced to dynamically balance classification and contrastive losses.
  arXiv  Detail & Related papers  (2025-07-21T16:21:47Z)
• BayesTTA: Continual-Temporal Test-Time Adaptation for Vision-Language Models via Gaussian Discriminant Analysis [41.09181390655176]
  Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but degrade significantly under textittemporally evolving distribution shifts common in real-world scenarios.<n>We formalize this practical problem as textitContinual-Temporal Test-Time Adaptation (CT-TTA), where test distributions evolve gradually over time.<n>We propose textitBayesTTA, a Bayesian adaptation framework that enforces temporally consistent predictions and dynamically aligns visual representations.
  arXiv  Detail & Related papers  (2025-07-11T14:02:54Z)
• Solving Inverse Problems with FLAIR [59.02385492199431]
  Flow-based latent generative models are able to generate images with remarkable quality, even enabling text-to-image generation.<n>We present FLAIR, a novel training free variational framework that leverages flow-based generative models as a prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Mitigating Cache Noise in Test-Time Adaptation for Large Vision-Language Models [13.157596316463621]
  Test-time adaptation (TTA) of visual language models has attracted significant attention as a solution to the performance degradation caused by distribution shifts in downstream tasks.<n>We introduce a comprehensive and reliable caching mechanism and propose a novel zero-shot TTA method called "Cache, Residual, Gaussian" (CRG)<n> Experimental results on 13 benchmarks demonstrate that CRG outperforms state-of-the-art TTA methods, showcasing exceptional robustness and adaptability.
  arXiv  Detail & Related papers  (2025-03-24T04:32:35Z)
• Confidence-calibrated covariate shift correction for few-shot classification in Vision-Language Models [2.6061534894032907]
  We introduce textbfConfidence-Calibrated Covariate Shift Correction (CalShift) -- a unified approach that combines a Fisher information penalty to mitigate covariate shift and a Confidence Misalignment Penalty (CMP) to reduce overconfidence in misclassified examples.<n>CalShift significantly improves model calibration, achieving up to a 5.82% reduction in Expected Error (ECE)<n>Our results highlight CalShift as a promising strategy for building robust and reliable low-shot vision-language systems for real-world applications.
  arXiv  Detail & Related papers  (2025-02-11T10:10:15Z)
• DRIVE: Dual-Robustness via Information Variability and Entropic Consistency in Source-Free Unsupervised Domain Adaptation [10.127634263641877]
  Adapting machine learning models to new domains without labeled data is a critical challenge in applications like medical imaging, autonomous driving, and remote sensing.<n>This task, known as Source-Free Unsupervised Domain Adaptation (SFUDA), involves adapting a pre-trained model to a target domain using only unlabeled target data.<n>Existing SFUDA methods often rely on single-model architectures, struggling with uncertainty and variability in the target domain.<n>We propose DRIVE, a novel SFUDA framework leveraging a dual-model architecture. The two models, with identical weights, work in parallel to capture diverse target domain characteristics.
  arXiv  Detail & Related papers  (2024-11-24T20:35:04Z)
• DOTA: Distributional Test-Time Adaptation of Vision-Language Models [52.98590762456236]
  Training-free test-time dynamic adapter (TDA) is a promising approach to address this issue. We propose a simple yet effective method for DistributiOnal Test-time Adaptation (Dota) Dota continually estimates the distributions of test samples, allowing the model to continually adapt to the deployment environment.
  arXiv  Detail & Related papers  (2024-09-28T15:03:28Z)
• Digital Twin-Assisted Data-Driven Optimization for Reliable Edge Caching in Wireless Networks [60.54852710216738]
  We introduce a novel digital twin-assisted optimization framework, called D-REC, to ensure reliable caching in nextG wireless networks. By incorporating reliability modules into a constrained decision process, D-REC can adaptively adjust actions, rewards, and states to comply with advantageous constraints.
  arXiv  Detail & Related papers  (2024-06-29T02:40:28Z)
• Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting [55.17761802332469]
  Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and test data by adapting a given model w.r.t. any test sample. Prior methods perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications. We propose an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples.
  arXiv  Detail & Related papers  (2024-03-18T05:49:45Z)
• Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness [61.827054365139645]
  Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. We propose an alternative model, DU-VAE, for learning a more Diverse and less Uncertain latent space.
  arXiv  Detail & Related papers  (2021-10-24T07:58:13Z)

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.