Test-time Adaptation

Benchmarks archive 2025-07-28

1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

2 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 229 papers with code (484 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions
  28 Jan 2022 6 repositories listed Syntology ran 14 of 29 samples · 15 unverified
  Deep neural networks on 3D point cloud data have been widely used in the real world, especially in safety-critical applications.
• Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models
  30 Jan 2025 5 repositories listed
  Besides, the recent advent of large-scale pre-trained multimodal foundation models, such as CLIP, has inspired works leveraging these models to enhance adaptation and generalization performances or adapting them to…
• Continual Test-Time Domain Adaptation
  25 Mar 2022 3 repositories listed Syntology ran 6 of 11 samples · 5 unverified · 4 pointer-only (licence)
  However, real-world machine perception systems are running in non-stationary and continually changing environments where the target domain distribution can change over time.
• Controllable Continual Test-Time Adaptation
  23 May 2024 2 repositories listed
  Continual Test-Time Adaptation (CTTA) is an emerging and challenging task where a model trained in a source domain must adapt to continuously changing conditions during testing, without access to the original source…
• Multi-Stream Cellular Test-Time Adaptation of Real-Time Models Evolving in Dynamic Environments
  27 Apr 2024 2 repositories listed
  In the era of the Internet of Things (IoT), objects connect through a dynamic network, empowered by technologies like 5G, enabling real-time data sharing.
• Test Time Adaptation for Blind Image Quality Assessment
  27 Jul 2023 2 repositories listed
  In this work, we introduce two novel quality-relevant auxiliary tasks at the batch and sample levels to enable TTA for blind IQA.
• ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
  7 Jun 2023 2 repositories listed Syntology ran 8 of 9 samples · 1 unverified
  Note that, our method can be regarded as a novel transfer paradigm for large-scale models, delivering promising results in adaptation to continually changing distributions.
• AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation
  25 Apr 2023 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 2 pointer-only (licence)
  In particular, when the adaptation target is a series of domains, the adaptation accuracy of AdaNPC is 50% higher than advanced TTA methods.
• MECTA: Memory-Economic Continual Test-Time Model Adaptation
  1 Feb 2023 2 repositories listed
  The proposed MECTA is efficient and can be seamlessly plugged into state-of-theart CTA algorithms at negligible overhead on computation and memory.
• Test-Time Adaptation via Self-Training with Nearest Neighbor Information
  8 Jul 2022 2 repositories listed Syntology ran 13 of 19 samples · 6 unverified · 19 pointer-only (licence)
  To overcome this limitation, we propose a novel test-time adaptation method, called Test-time Adaptation via Self-Training with nearest neighbor information (TAST), which is composed of the following procedures: (1)…
• Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition
  27 Mar 2022 2 repositories listed
  Although deep learning-based end-to-end Automatic Speech Recognition (ASR) has shown remarkable performance in recent years, it suffers severe performance regression on test samples drawn from different data…
• AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation
  24 Oct 2021 2 repositories listed
  Since inconsistency mainly arises from the model's uncertainty in its output, we propose an adaptation scheme where the model learns from its own segmentation decisions as it streams a video, which allows producing more…
• MEMO: Test Time Robustness via Adaptation and Augmentation
  18 Oct 2021 2 repositories listed Syntology ran 14 of 18 samples · 4 unverified · 15 pointer-only (licence)
  We study the problem of test time robustification, i.
• Tent: Fully Test-time Adaptation by Entropy Minimization
  18 Jun 2020 2 repositories listed Syntology ran 8 of 9 samples · 1 unverified · 3 pointer-only (licence)
  A model must adapt itself to generalize to new and different data during testing.
• Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation
  9 Apr 2020 2 repositories listed
  In medical image segmentation, this premise is violated when there is a mismatch between training and test images in terms of their acquisition details, such as the scanner model or the protocol.
• Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation
  7 Jun 2025 1 repository listed
  MSD-CoT progressively disentangles image captions to eliminate semantic ambiguity, while RDVP injects spatial constraints into visual prompting and independently samples visual prompts for foreground and background…
• AVROBUSTBENCH: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
  31 May 2025 1 repository listed Syntology ran 0 of 2 samples · 2 unverified
  While recent audio-visual models have demonstrated impressive performance, their robustness to distributional shifts at test-time remains not fully understood.
• Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation
  28 May 2025 1 repository listed
  Recently, test-time adaptation has attracted wide interest in the context of vision-language models for image classification.
• Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation
  24 May 2025 1 repository listed
  Empirically, our method achieves state-of-the-art results compared to existing test-time adaptation (TTA) approaches and significantly enhances the resilience and generalization of DF detectors during inference.
• Test-Time Adaptation with Binary Feedback
  24 May 2025 1 repository listed Syntology ran 5 of 13 samples · 8 unverified
  To address this issue, we introduce a new setting of TTA with binary feedback.
• Ranked Entropy Minimization for Continual Test-Time Adaptation
  22 May 2025 1 repository listed Syntology ran 1 of 2 samples · 1 unverified
  We propose ranked entropy minimization to mitigate the stability problem of the entropy minimization method and extend its applicability to continuous scenarios.
• Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruption
  19 May 2025 1 repository listed
  We found that this is because image embeddings are "corrupted" in terms of uniformity, a measure related to the amount of information.
• From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection
  19 May 2025 1 repository listed
  Pretrained vision-language models (VLMs), e.
• APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Clouds
  15 May 2025 1 repository listed
  Finally, we construct two benchmarks, ISPRSC and H3DC, to address the lack of CTTA benchmarks for ALS point cloud segmentation.
• Threshold Modulation for Online Test-Time Adaptation of Spiking Neural Networks
  8 May 2025 1 repository listed
  The proposed method offers a practical solution for online test-time adaptation of SNNs, providing inspiration for the design of future neuromorphic chips.
• TeDA: Boosting Vision-Lanuage Models for Zero-Shot 3D Object Retrieval via Testing-time Distribution Alignment
  5 May 2025 1 repository listed
  Learning discriminative 3D representations that generalize well to unknown testing categories is an emerging requirement for many real-world 3D applications.
• COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation
  30 Mar 2025 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  Recent vision-language models (VLMs) face significant challenges in test-time adaptation to novel domains.
• SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity
  26 Mar 2025 1 repository listed Syntology ran 15 of 19 samples · 4 unverified · 19 pointer-only (licence)
  Despite the growing integration of deep models into mobile terminals, the accuracy of these models declines significantly due to various deployment interferences.
• Test-Time Domain Generalization via Universe Learning: A Multi-Graph Matching Approach for Medical Image Segmentation
  17 Mar 2025 1 repository listed Syntology ran 4 of 5 samples · 1 unverified · 5 pointer-only (licence)
  Despite domain generalization (DG) has significantly addressed the performance degradation of pre-trained models caused by domain shifts, it often falls short in real-world deployment.
• SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting
  17 Mar 2025 1 repository listed Syntology ran 1 of 4 samples · 3 unverified
  To address these limitations, we propose a novel transductive TTA framework, Supportive Clique-based Attribute Prompting (SCAP), which effectively combines visual and textual information to enhance adaptation by…

Syntology lines on 14 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.