mlsanityData to 13 Oct 2026

ClusT3: Information Invariant Test-Time Training

arXiv 2310.12345 ↗First posted 18 Oct 2023cs.CV cs.AI cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

Deep Learning models have shown remarkable performance in a broad range of vision tasks. However, they are often vulnerable against domain shifts at test-time. Test-time training (TTT) methods have been developed in an attempt to mitigate these vulnerabilities, where a secondary task is solved at training time simultaneously with the main task, to be later used as an self-supervised proxy task at test-time. In this work, we propose a novel unsupervised TTT technique based on the maximization of Mutual Information between multi-scale feature maps and a discrete latent representation, which can be integrated to the standard training as an auxiliary clustering task. Experimental results demonstrate competitive classification performance on different popular test-time adaptation benchmarks.

Key facts. Cited by 21 papers in the map (data through 13 Oct 2026). Builds on 26 of its 35 references that are in the map. First posted on arXiv 18 Oct 2023.

Builds on

26 of 35 references.

References · 26

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,009
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,712
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,364
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,862
  6. 2016Density estimation using Real NVPcited by 2,033
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,542
  8. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,510
  9. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 846
  10. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 764
  11. 2021Domain Generalization with MixStylecited by 563
  12. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
14 more
  1. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  2. 2019On Mutual Information Maximization for Representation Learningcited by 315
  3. 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 236
  4. 2022Test-Time Training with Masked Autoencoderscited by 209
  5. 2022Surgical Fine-Tuning Improves Adaptation to Distribution Shiftscited by 205
  6. 2018Do CIFAR-10 Classifiers Generalize to CIFAR-10?cited by 198
  7. 2022Parameter-free Online Test-time Adaptationcited by 185
  8. 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
  9. 2018Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Datacited by 94
  10. 2022A Broad Study of Pre-training for Domain Generalization and Adaptationcited by 64
  11. 2021SITA: Single Image Test-time Adaptationcited by 59
  12. 2020Transductive Information Maximization For Few-Shot Learningcited by 45
  13. 2018Deep clustering: On the link between discriminative models and K-meanscited by 37
  14. 2022TTTFlow: Unsupervised Test-Time Training with Normalizing Flowcited by 33

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 5; 2025: 14; 2026: 2.

21 papers.

Sort:

By area:

  1. 2025Centaur: Robust End-to-End Autonomous Driving with Test-Time Trainingcited by 42
  2. 2024WATT: Weight Average Test-Time Adaptation of CLIPcited by 33
  3. 2025Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challengescited by 15
  4. 2024CLIPArTT: Adaptation of CLIP to New Domains at Test Timecited by 14
  5. 2025NNGPT: Rethinking AutoML with Large Language Modelscited by 13
  6. 2025Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptationcited by 11
  7. 2025Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentationcited by 10
  8. 2024Test-time Adaptation for Regression by Subspace Alignmentcited by 9
  9. 2025AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoningcited by 7
  10. 2024FDS: Feedback-guided Domain Synthesis with Multi-Source Conditional Diffusion Models for Domain Generalizationcited by 5
  11. 2024ReC-TTT: Contrastive Feature Reconstruction for Test-Time Trainingcited by 5
  12. 2025Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Trainingcited by 5
9 more
  1. 2025Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Modelscited by 5
  2. 2026Histopath-C: Towards Realistic Domain Shifts for Histopathology Vision-Language Adaptationcited by 4
  3. 2025Reasoning-Style Poisoning of LLM Agents via Stealthy Style Transfer: Process-Level Attacks and Runtime Monitoring in RSV Spacecited by 3
  4. 2025Structural Alignment Improves Graph Test-Time Adaptationcited by 2
  5. 2025Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regressioncited by 1
  6. 2025CTA: Cross-Task Alignment for Better Test Time Trainingcited by 1
  7. 2025Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shiftscited by 1
  8. 2025Adaptive Test-Time Training for Predicting Need for Invasive Mechanical Ventilation in Multi-Center Cohortscited by 0
  9. 2026Toward Robust Open-set Adaptation: Synapse Consolidation Inspired by Rac1/MAPK Pathwayscited by 0