# Adaptive Retention & Correction: Test-Time Training for Continual Learning

arXiv: https://arxiv.org/abs/2405.14318 · HTML: https://mlsanity.com/paper/2405.14318/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2024.

## Built on by (most cited first, 6 of 6)

- [Dual-Phase Continual Learning: Supervised Adaptation Meets Unsupervised Retention](https://mlsanity.com/paper/2406.13653/) (2024)
- [SAMix: Calibrated and Accurate Continual Learning via Sphere-Adaptive Mixup and Neural Collapse](https://mlsanity.com/paper/2510.15751/) (2025)
- [Task-Focused Memorization for Multimodal Agents](https://mlsanity.com/paper/2605.31075/) (2026)
- [Multi-Prompt Progressive Alignment for Multi-Source Unsupervised Domain Adaptation](https://mlsanity.com/paper/2507.23373/) (2025)
- [BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding](https://mlsanity.com/paper/2508.18187/) (2025)
- [Information-Theoretic Decoupled Prompt Tuning for Continual Learning](https://mlsanity.com/paper/2609.26257/) (2026)

## Abstract (arXiv)

Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias towards the most recent task. Traditionally, methods have relied on incorporating data from past tasks during training to mitigate this issue. However, the recent shift in continual learning to memory-free environments has rendered these approaches infeasible. In this study, we propose a solution focused on the testing phase. We first introduce a simple Out-of-Task Detection method, OTD, designed to accurately identify samples from past tasks during testing. Leveraging OTD, we then propose: (1) an Adaptive Retention mechanism for dynamically tuning the classifier layer on past task data; (2) an Adaptive Correction mechanism for revising predictions when the model classifies data from previous tasks into classes from the current task. We name our approach Adaptive Retention & Correction (ARC). While designed for memory-free environments, ARC also proves effective in memory-based settings. Extensive experiments show that our proposed method can be plugged in to virtually any existing continual learning approach without requiring any modifications to its training procedure. Specifically, when integrated with state-of-the-art approaches, ARC achieves an average performance increase of 2.7% and 2.6% on the CIFAR-100 and Imagenet-R datasets, respectively.