# Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation

arXiv: https://arxiv.org/abs/2505.20704 · HTML: https://mlsanity.com/paper/2505.20704/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 54 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Parameter-free Online Test-time Adaptation](https://mlsanity.com/paper/2201.05718/) (2022)
- [Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data](https://mlsanity.com/paper/2010.03622/) (2020)
- [Self-supervised Augmentation Consistency for Adapting Semantic Segmentation](https://mlsanity.com/paper/2105.00097/) (2021)
- [Efficient Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2403.18293/) (2024)
- [Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System](https://mlsanity.com/paper/2201.12604/) (2022)
- [Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors](https://mlsanity.com/paper/2403.07366/) (2024)
- [TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation](https://mlsanity.com/paper/2302.05155/) (2023)
- [SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2012.11460/) (2020)
- [MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2204.12667/) (2022)
- [DELTA: degradation-free fully test-time adaptation](https://mlsanity.com/paper/2301.13018/) (2023)
- [MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption](https://mlsanity.com/paper/2103.16201/) (2021)
- [RDumb: A simple approach that questions our progress in continual test-time adaptation](https://mlsanity.com/paper/2306.05401/) (2023)
- [MixNorm: Test-Time Adaptation Through Online Normalization Estimation](https://mlsanity.com/paper/2110.11478/) (2021)
- [Video Test-Time Adaptation for Action Recognition](https://mlsanity.com/paper/2211.15393/) (2022)
- [Rethinking Distributional Matching Based Domain Adaptation](https://mlsanity.com/paper/2006.13352/) (2020)

## Built on by (most cited first, 11 of 11)

- [Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models](https://mlsanity.com/paper/2508.01225/) (2025)
- [Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization](https://mlsanity.com/paper/2509.04977/) (2025)
- [ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapse](https://mlsanity.com/paper/2509.23183/) (2025)
- [Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation](https://mlsanity.com/paper/2605.23257/) (2026)
- [Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts](https://mlsanity.com/paper/2508.20488/) (2025)
- [Sparse Reasoning is Enough: Biological-Inspired Framework for Video Anomaly Detection with Large Pre-trained Models](https://mlsanity.com/paper/2511.17094/) (2025)
- [Rethinking Test-Time Training: Tilting The Latent Distribution For Few-Shot Source-Free Adaptation](https://mlsanity.com/paper/2602.02633/) (2026)
- [Sample-wise Targeted Adversarial Attacks on Test-time Adaptation](https://mlsanity.com/paper/2605.23411/) (2026)
- [MixTTA: Low-Rank Cross-Channel Mixing for Reliable Test-Time Adaptation](https://mlsanity.com/paper/2606.28142/) (2026)
- [Not Every Correction Helps: Gain-Guided Continual Test-Time Adaptation](https://mlsanity.com/paper/2609.36655/) (2026)
- [Credit-Guided Policy Improvement for Test-time Adaptive Vision-Language Navigation](https://mlsanity.com/paper/2609.37591/) (2026)

## Abstract (arXiv)

Wild Test-Time Adaptation (WTTA) is proposed to adapt a source model to unseen domains under extreme data scarcity and multiple shifts. Previous approaches mainly focused on sample selection strategies, while overlooking the fundamental problem on underlying optimization. Initially, we critically analyze the widely-adopted entropy minimization framework in WTTA and uncover its significant limitations in noisy optimization dynamics that substantially hinder adaptation efficiency. Through our analysis, we identify region confidence as a superior alternative to traditional entropy, however, its direct optimization remains computationally prohibitive for real-time applications. In this paper, we introduce a novel region-integrated method ReCAP that bypasses the lengthy process. Specifically, we propose a probabilistic region modeling scheme that flexibly captures semantic changes in embedding space. Subsequently, we develop a finite-to-infinite asymptotic approximation that transforms the intractable region confidence into a tractable and upper-bounded proxy. These innovations significantly unlock the overlooked potential dynamics in local region in a concise solution. Our extensive experiments demonstrate the consistent superiority of ReCAP over existing methods across various datasets and wild scenarios.