# Online Continual Learning under Extreme Memory Constraints

arXiv: https://arxiv.org/abs/2008.01510 · HTML: https://mlsanity.com/paper/2008.01510/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2020.

## Built on by (most cited first, 30 of 48)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [Self-Supervised Models are Continual Learners](https://mlsanity.com/paper/2112.04215/) (2021)
- [A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning](https://mlsanity.com/paper/2307.09218/) (2023)
- [Continual evaluation for lifelong learning: Identifying the stability gap](https://mlsanity.com/paper/2205.13452/) (2022)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [Layerwise Optimization by Gradient Decomposition for Continual Learning](https://mlsanity.com/paper/2105.07561/) (2021)
- [Incremental Learning in Semantic Segmentation from Image Labels](https://mlsanity.com/paper/2112.01882/) (2021)
- [Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation](https://mlsanity.com/paper/2203.14098/) (2022)
- [Continual Learning as Computationally Constrained Reinforcement Learning](https://mlsanity.com/paper/2307.04345/) (2023)
- [Wanderlust: Online Continual Object Detection in the Real World](https://mlsanity.com/paper/2108.11005/) (2021)
- [Continual Learning on Noisy Data Streams via Self-Purified Replay](https://mlsanity.com/paper/2110.07735/) (2021)
- [Formalizing the Generalization-Forgetting Trade-off in Continual Learning](https://mlsanity.com/paper/2109.14035/) (2021)
- [Modeling Missing Annotations for Incremental Learning in Object Detection](https://mlsanity.com/paper/2204.08766/) (2022)
- [Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching](https://mlsanity.com/paper/2407.05005/) (2024)
- [Challenging Common Assumptions about Catastrophic Forgetting](https://mlsanity.com/paper/2207.04543/) (2022)
- [A soft nearest-neighbor framework for continual semi-supervised learning](https://mlsanity.com/paper/2212.05102/) (2022)
- [Label-Efficient Online Continual Object Detection in Streaming Video](https://mlsanity.com/paper/2206.00309/) (2022)
- [Continual Attentive Fusion for Incremental Learning in Semantic Segmentation](https://mlsanity.com/paper/2202.00432/) (2022)
- [On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers](https://mlsanity.com/paper/2308.09610/) (2023)
- [Non-Exemplar Online Class-incremental Continual Learning via Dual-prototype Self-augment and Refinement](https://mlsanity.com/paper/2303.10891/) (2023)
- [Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory](https://mlsanity.com/paper/2309.15413/) (2023)
- [Online Continual Learning on Hierarchical Label Expansion](https://mlsanity.com/paper/2308.14374/) (2023)
- [Online Unsupervised Domain Adaptation for Person Re-identification](https://mlsanity.com/paper/2205.04383/) (2022)
- [Knowledge Restore and Transfer for Multi-label Class-Incremental Learning](https://mlsanity.com/paper/2302.13334/) (2023)
- [Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured training](https://mlsanity.com/paper/2403.09613/) (2024)
- [Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modelling](https://mlsanity.com/paper/2407.15429/) (2024)
- [Label Delay in Online Continual Learning](https://mlsanity.com/paper/2312.00923/) (2023)
- [Few-shot Online Anomaly Detection and Segmentation](https://mlsanity.com/paper/2403.18201/) (2024)

## Abstract (arXiv)

Continual Learning (CL) aims to develop agents emulating the human ability to sequentially learn new tasks while being able to retain knowledge obtained from past experiences. In this paper, we introduce the novel problem of Memory-Constrained Online Continual Learning (MC-OCL) which imposes strict constraints on the memory overhead that a possible algorithm can use to avoid catastrophic forgetting. As most, if not all, previous CL methods violate these constraints, we propose an algorithmic solution to MC-OCL: Batch-level Distillation (BLD), a regularization-based CL approach, which effectively balances stability and plasticity in order to learn from data streams, while preserving the ability to solve old tasks through distillation. Our extensive experimental evaluation, conducted on three publicly available benchmarks, empirically demonstrates that our approach successfully addresses the MC-OCL problem and achieves comparable accuracy to prior distillation methods requiring higher memory overhead.