mlsanityData to 7 Oct 2026

CLIPArTT: Adaptation of CLIP to New Domains at Test Time

arXiv 2405.00754 ↗First posted 1 May 2024cs.CV cs.LGcited by 14

On the map: Multimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP

Abstract (arXiv)

Pre-trained vision-language models (VLMs), exemplified by CLIP, demonstrate remarkable adaptability across zero-shot classification tasks without additional training. However, their performance diminishes in the presence of domain shifts. In this study, we introduce CLIP Adaptation duRing Test-Time (CLIPArTT), a fully test-time adaptation (TTA) approach for CLIP, which involves automatic text prompts construction during inference for their use as text supervision. Our method employs a unique, minimally invasive text prompt tuning process, wherein multiple predicted classes are aggregated into a single new text prompt, used as pseudo label to re-classify inputs in a transductive manner. Additionally, we pioneer the standardization of TTA benchmarks (e.g., TENT) in the realm of VLMs. Our findings demonstrate that, without requiring additional transformations nor new trainable modules, CLIPArTT enhances performance dynamically across non-corrupted datasets such as CIFAR-100, corrupted datasets like CIFAR-100-C and ImageNet-C, alongside synthetic datasets such as VisDA-C. This research underscores the potential for improving VLMs' adaptability through novel test-time strategies, offering insights for robust performance across varied datasets and environments. The code can be found at: https://github.com/dosowiechi/CLIPArTT.git

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 25 of its 33 references that are in the map. First posted on arXiv 1 May 2024.

Builds on

25 of 33 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Efficient Test-Time Adaptation of Vision-Language Models27 Mar
  2. 2023Test-Time Distribution Normalization for Contrastively Learned Vision-language Models22 Feb
  3. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models15 Sep
  4. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling6 Nov

Other references · 21

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023Segment Anythingcited by 8,158
  3. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  4. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  5. 2022Continual Test-Time Domain Adaptationcited by 520
  6. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 376
  7. 2021AudioCLIP: Extending CLIP to Image, Text and Audiocited by 335
  8. 2019Label Propagation for Deep Semi-supervised Learningcited by 287
  9. 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 235
  10. 2023CLIP-Driven Universal Model for Organ Segmentation and Tumor Detectioncited by 224
  11. 2022Test-Time Training with Masked Autoencoderscited by 208
  12. 2022Parameter-free Online Test-time Adaptationcited by 184
9 more
  1. 2022Frozen CLIP Models are Efficient Video Learnerscited by 181
  2. 2022CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attentioncited by 103
  3. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  4. 2020Tent: Fully Test-time Adaptation by Entropy Minimizationcited by 59
  5. 2023Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimizationcited by 39
  6. 2022TTTFlow: Unsupervised Test-Time Training with Normalizing Flowcited by 33
  7. 2023ClusT3: Information Invariant Test-Time Trainingcited by 21
  8. 2023On the Potential of CLIP for Compositional Logical Reasoningcited by 3
  9. 2023Improving Entropy-Based Test-Time Adaptation from a Clustering Viewcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 6.

14 papers.

Sort:

By area:

  1. 2025LoRA-TTT: Low-Rank Test-Time Training for Vision-Language Modelscited by 7
  2. 2025Generalizing vision-language models to novel domains: A comprehensive surveycited by 6
  3. 2025Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptionscited by 5
  4. 2025Purge-Gate: Backpropagation-Free Test-Time Adaptation for Point Clouds Classification via Token Purgingcited by 3
  5. 2025textttAVROBUSTBENCH: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Timecited by 2
  6. 2025Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruptioncited by 1
  7. 2026ProtoDCS: Towards Robust and Efficient Open-Set Test-Time Adaptation for Vision-Language Modelscited by 1
  8. 2025Hierarchical Adaptive networks with Task vectors for Test-Time Adaptationcited by 0
  9. 2025TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traversescited by 0
  10. 2026Ramen: Robust Test-Time Adaptation of Vision-Language Models with Active Sample Selectioncited by 0
  11. 2026LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignmentcited by 0
  12. 2026Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classificationcited by 0
2 more
  1. 2026Towards Continual Test-Time Adaptation of Vision-Language Models in Open-Vocabulary Semantic Segmentationcited by 0
  2. 2026Balanced Prompt Adaptation against Entropy-Induced Collapse for Test-Time Binary Segmentationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024WATT: Weight Average Test-Time Adaptation of CLIP
  2. 2026What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective
  3. 2025ETTA: Efficient Test-Time Adaptation for Vision-Language Models through Dynamic Embedding Updates
  4. 2024Fully Fine-tuned CLIP Models are Efficient Few-Shot Learners
  5. 2025Unleashing the Potential of All Test Samples: Mean-Shift Guided Test-Time Adaptation
  6. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapters
  7. 2025The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models
  8. 2025CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptation