# A Multi-Head Model for Continual Learning via Out-of-Distribution Replay

arXiv: https://arxiv.org/abs/2208.09734 · HTML: https://mlsanity.com/paper/2208.09734/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 63 references that are in the map.
- First posted on arXiv 20 Aug 2022.

## Builds on (most cited first, 30 of 47)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Class-incremental learning: survey and performance evaluation on image classification](https://mlsanity.com/paper/2010.15277/) (2020)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [DER: Dynamically Expandable Representation for Class Incremental Learning](https://mlsanity.com/paper/2103.16788/) (2021)
- [Gradient Projection Memory for Continual Learning](https://mlsanity.com/paper/2103.09762/) (2021)
- [On Tiny Episodic Memories in Continual Learning](https://mlsanity.com/paper/1902.10486/) (2019)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [Learning without Memorizing](https://mlsanity.com/paper/1811.08051/) (2018)
- [Supermasks in Superposition](https://mlsanity.com/paper/2006.14769/) (2020)
- [Mnemonics Training: Multi-Class Incremental Learning without Forgetting](https://mlsanity.com/paper/2002.10211/) (2020)
- [Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/1805.07810/) (2018)

## Built on by (most cited first, 27 of 27)

- [Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality](https://mlsanity.com/paper/2310.07234/) (2023)
- [FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning](https://mlsanity.com/paper/2309.14062/) (2023)
- [A Theoretical Study on Solving Continual Learning](https://mlsanity.com/paper/2211.02633/) (2022)
- [The Ideal Continual Learner: An Agent That Never Forgets](https://mlsanity.com/paper/2305.00316/) (2023)
- [Learnability and Algorithm for Continual Learning](https://mlsanity.com/paper/2306.12646/) (2023)
- [Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy](https://mlsanity.com/paper/2312.10549/) (2023)
- [HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuning](https://mlsanity.com/paper/2407.05229/) (2024)
- [Class Incremental Learning via Likelihood Ratio Based Task Prediction](https://mlsanity.com/paper/2309.15048/) (2023)
- [Adapter Learning in Pretrained Feature Extractor for Continual Learning of Diseases](https://mlsanity.com/paper/2304.09042/) (2023)
- [LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning](https://mlsanity.com/paper/2508.06202/) (2025)
- [Continual Evidential Deep Learning for Out-of-Distribution Detection](https://mlsanity.com/paper/2309.02995/) (2023)
- [Continual Learning in the Presence of Repetition](https://mlsanity.com/paper/2405.04101/) (2024)
- [Advancing Prompt-Based Methods for Replay-Independent General Continual Learning](https://mlsanity.com/paper/2503.00677/) (2025)
- [PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning](https://mlsanity.com/paper/2407.14029/) (2024)
- [CLoG: Benchmarking Continual Learning of Image Generation Models](https://mlsanity.com/paper/2406.04584/) (2024)
- [Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning](https://mlsanity.com/paper/2406.02428/) (2024)
- [DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2411.19154/) (2024)
- [H2ST: Hierarchical Two-Sample Tests for Continual Out-of-Distribution Detection](https://mlsanity.com/paper/2503.14832/) (2025)
- [Class Incremental Learning with Task-Specific Batch Normalization and Out-of-Distribution Detection](https://mlsanity.com/paper/2411.00430/) (2024)
- [Buffer-free Class-Incremental Learning with Out-of-Distribution Detection](https://mlsanity.com/paper/2505.23412/) (2025)
- [Data Heterogeneity and Forgotten Labels in Split Federated Learning](https://mlsanity.com/paper/2511.09736/) (2025)
- [Balancing the Causal Effects in Class-Incremental Learning](https://mlsanity.com/paper/2402.10063/) (2024)
- [Out-of-Distribution Detection for Continual Learning: Design Principles and Benchmarking](https://mlsanity.com/paper/2512.19725/) (2025)
- [A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillation](https://mlsanity.com/paper/2603.20648/) (2026)
- [Out of Distribution Detection for Efficient Continual Learning in Quality Prediction for Arc Welding](https://mlsanity.com/paper/2508.16832/) (2025)
- [Learning After Model Deployment](https://mlsanity.com/paper/2510.17160/) (2025)
- [GR4CIL: Gap-compensated Routing for CLIP-based Class Incremental Learning](https://mlsanity.com/paper/2604.17822/) (2026)

## Abstract (arXiv)

This paper studies class incremental learning (CIL) of continual learning (CL). Many approaches have been proposed to deal with catastrophic forgetting (CF) in CIL. Most methods incrementally construct a single classifier for all classes of all tasks in a single head network. To prevent CF, a popular approach is to memorize a small number of samples from previous tasks and replay them during training of the new task. However, this approach still suffers from serious CF as the parameters learned for previous tasks are updated or adjusted with only the limited number of saved samples in the memory. This paper proposes an entirely different approach that builds a separate classifier (head) for each task (called a multi-head model) using a transformer network, called MORE. Instead of using the saved samples in memory to update the network for previous tasks/classes in the existing approach, MORE leverages the saved samples to build a task specific classifier (adding a new classification head) without updating the network learned for previous tasks/classes. The model for the new task in MORE is trained to learn the classes of the task and also to detect samples that are not from the same data distribution (i.e., out-of-distribution (OOD)) of the task. This enables the classifier for the task to which the test instance belongs to produce a high score for the correct class and the classifiers of other tasks to produce low scores because the test instance is not from the data distributions of these classifiers. Experimental results show that MORE outperforms state-of-the-art baselines and is also naturally capable of performing OOD detection in the continual learning setting.