Prototype-Based Test-Time Adaptation of Vision-Language Models

• URL: http://arxiv.org/abs/2604.21360v1
• Date: Thu, 23 Apr 2026 07:20:56 GMT
• Title: Prototype-Based Test-Time Adaptation of Vision-Language Models
• Abstract summary: Prototype-Based Test-Time Adaptation (PTA)<n>PTA uses a set of class-specific knowledge prototypes to accumulate knowledge from test samples.<n>PTA achieves extremely high efficiency while achieving state-of-the-art performance.
• Score: 58.28899599773308
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Test-time adaptation (TTA) has emerged as a promising paradigm for vision-language models (VLMs) to bridge the distribution gap between pre-training and test data. Recent works have focused on backpropagation-free TTA methods that rely on cache-based designs, but these introduce two key limitations. First, inference latency increases as the cache grows with the number of classes, leading to inefficiencies in large-scale settings. Second, suboptimal performance occurs when the cache contains insufficient or incorrect samples. In this paper, we present Prototype-Based Test-Time Adaptation (PTA), an efficient and effective TTA paradigm that uses a set of class-specific knowledge prototypes to accumulate knowledge from test samples. Particularly, knowledge prototypes are adaptively weighted based on the zero-shot class confidence of each test sample, incorporating the sample's visual features into the corresponding class-specific prototype. It is worth highlighting that the knowledge from past test samples is integrated and utilized solely in the prototypes, eliminating the overhead of cache population and retrieval that hinders the efficiency of existing TTA methods. This endows PTA with extremely high efficiency while achieving state-of-the-art performance on 15 image recognition benchmarks and 4 robust point cloud analysis benchmarks. For example, PTA improves CLIP's accuracy from 65.64% to 69.38% on 10 cross-domain benchmarks, while retaining 92% of CLIP's inference speed on large-scale ImageNet-1K. In contrast, the cache-based TDA achieves a lower accuracy of 67.97% and operates at only 50% of CLIP's inference speed.

Related papers

• Test-Time Adaptation with Online Personalized Energy-Based Cache for Fine-Grained Video Expression Recognition [59.83490704563065]
  Facial expression recognition (FER) in videos is challenging because models must identify subtle, temporally evolving affective states that vary across individuals.<n>Existing test-time adaptation (TTA) methods commonly update model parameters during inference, increasing computational cost and latency.<n>We introduce Energy-Based Cache Personalization (EB-CaP), a subject-based online TTA method for video FER that generates class-specific prototypes personalized to each target video.
  arXiv  Detail & Related papers  (2026-08-06T18:02:20Z)
• Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models [7.542207462593201]
  In zero-shot setting, test-time adaptation adjusts pre-trained models using unlabeled data from the test phase to enhance performance on unknown test distributions.<n>This study identifies a positive correlation between cache-enhanced performance and intra-class compactness.<n>We propose a Multi-Cache enhanced Prototype-based Test-Time Adaptation (MCP) featuring three caches.
  arXiv  Detail & Related papers  (2025-08-02T06:43:43Z)
• Words Matter: Leveraging Individual Text Embeddings for Code Generation in CLIP Test-Time Adaptation [21.20806568508201]
  We show how to leverage class text information to mitigate distribution drifts encountered by vision-language models (VLMs) during test-time inference.<n>We propose to generate pseudo-labels for the test-time samples by exploiting generic class text embeddings as fixed centroids of a label assignment problem.<n>Experiments on multiple popular test-time adaptation benchmarks presenting diverse complexity empirically show the superiority of CLIP-OT.
  arXiv  Detail & Related papers  (2024-11-26T00:15:37Z)
• TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models [53.91006249339802]
  We propose a novel defense method called Test-Time Adversarial Prompt Tuning (TAPT) to enhance the inference robustness of CLIP against visual adversarial attacks. TAPT is a test-time defense method that learns defensive bimodal (textual and visual) prompts to robustify the inference process of CLIP. We evaluate the effectiveness of TAPT on 11 benchmark datasets, including ImageNet and 10 other zero-shot datasets.
  arXiv  Detail & Related papers  (2024-11-20T08:58:59Z)
• DOTA: Distributional Test-Time Adaptation of Vision-Language Models [69.41389326333771]
  Vision-language foundation models can be unreliable when significant distribution gaps exist between training and test data.<n>We propose DOTA (DistributiOnal Test-time Adaptation), a simple yet effective method addressing this limitation.<n>This distribution-centric approach enables the model to continually learn and adapt to the deployment environment.
  arXiv  Detail & Related papers  (2024-09-28T15:03:28Z)
• Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models [19.683461002518147]
  Test-Time Prototype Shifting (TPS) is a pioneering approach designed to adapt vision-language models to test datasets using unlabeled test inputs.<n>TPS not only facilitates optimization-free prototype reuse for subsequent predictions but also enables seamless integration with current advancements in prompt engineering.<n>A notable aspect of our framework is its significantly reduced memory and computational demands when compared to conventional text-prompt tuning methods.
  arXiv  Detail & Related papers  (2024-03-19T17:54:34Z)
• Decoupled Prototype Learning for Reliable Test-Time Adaptation [50.779896759106784]
  Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference. One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels. This study reveals that minimizing the classification error of each sample causes the cross-entropy loss's vulnerability to label noise. We propose a novel Decoupled Prototype Learning (DPL) method that features prototype-centric loss computation.
  arXiv  Detail & Related papers  (2024-01-15T03:33:39Z)
• Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement [24.108008515395458]
  We propose APE, an Adaptive Prior rEfinement method for CLIP's pre-trained knowledge, which achieves superior accuracy with high computational efficiency. For the average accuracy over 11 benchmarks, both APE and APE-T attain state-of-the-art and respectively outperform the second-best by +1.59% and +1.99% under 16 shots with x30 less learnable parameters.
  arXiv  Detail & Related papers  (2023-04-03T17:58:54Z)
• TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervision [70.05605071885914]
  We propose a novel modification of the self-supervised training algorithm SwAV that adds the ability to adapt to single test samples. We show the success of our method on the common benchmark dataset CIFAR10-C.
  arXiv  Detail & Related papers  (2022-05-18T05:43:06Z)

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.