# Continual Prototype Evolution: Learning Online from Non-Stationary Data Streams

arXiv: https://arxiv.org/abs/2009.00919 · HTML: https://mlsanity.com/paper/2009.00919/

## Key facts

- Cited by 144 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2020.

## Built on by (most cited first, 30 of 144)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [RanPAC: Random Projections and Pre-trained Models for Continual Learning](https://mlsanity.com/paper/2307.02251/) (2023)
- [FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning](https://mlsanity.com/paper/2309.14062/) (2023)
- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [Rehearsal revealed: The limits and merits of revisiting samples in continual learning](https://mlsanity.com/paper/2104.07446/) (2021)
- [Computationally Budgeted Continual Learning: What Does Matter?](https://mlsanity.com/paper/2303.11165/) (2023)
- [Continual evaluation for lifelong learning: Identifying the stability gap](https://mlsanity.com/paper/2205.13452/) (2022)
- [Online Prototype Learning for Online Continual Learning](https://mlsanity.com/paper/2308.00301/) (2023)
- [Real-Time Evaluation in Online Continual Learning: A New Hope](https://mlsanity.com/paper/2302.01047/) (2023)
- [Natural continual learning: success is a journey, not (just) a destination](https://mlsanity.com/paper/2106.08085/) (2021)
- [Posterior Meta-Replay for Continual Learning](https://mlsanity.com/paper/2103.01133/) (2021)
- [SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection](https://mlsanity.com/paper/2402.17323/) (2024)
- [EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding](https://mlsanity.com/paper/2309.08816/) (2023)
- [Class-Incremental Learning with Generative Classifiers](https://mlsanity.com/paper/2104.10093/) (2021)
- [Understanding Continual Learning Settings with Data Distribution Drift Analysis](https://mlsanity.com/paper/2104.01678/) (2021)
- [CLAD: A realistic Continual Learning benchmark for Autonomous Driving](https://mlsanity.com/paper/2210.03482/) (2022)
- [Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning](https://mlsanity.com/paper/2303.14771/) (2023)
- [Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal](https://mlsanity.com/paper/2302.01242/) (2023)
- [Meta-attention for ViT-backed Continual Learning](https://mlsanity.com/paper/2203.11684/) (2022)
- [Online Continual Learning Without the Storage Constraint](https://mlsanity.com/paper/2305.09253/) (2023)
- [Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation](https://mlsanity.com/paper/2211.06866/) (2022)
- [Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation](https://mlsanity.com/paper/2411.05663/) (2024)
- [OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2403.18550/) (2024)
- [Optimizing Reusable Knowledge for Continual Learning via Metalearning](https://mlsanity.com/paper/2106.05390/) (2021)
- [Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy](https://mlsanity.com/paper/2312.10549/) (2023)
- [Low-rank extended Kalman filtering for online learning of neural networks from streaming data](https://mlsanity.com/paper/2305.19535/) (2023)
- [VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Model](https://mlsanity.com/paper/2403.05346/) (2024)
- [A Practitioner's Guide to Continual Multimodal Pretraining](https://mlsanity.com/paper/2408.14471/) (2024)
- [DOTA: Distributional Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2409.19375/) (2024)

## Abstract (arXiv)

Attaining prototypical features to represent class distributions is well established in representation learning. However, learning prototypes online from streaming data proves a challenging endeavor as they rapidly become outdated, caused by an ever-changing parameter space during the learning process. Additionally, continual learning does not assume the data stream to be stationary, typically resulting in catastrophic forgetting of previous knowledge. As a first, we introduce a system addressing both problems, where prototypes evolve continually in a shared latent space, enabling learning and prediction at any point in time. In contrast to the major body of work in continual learning, data streams are processed in an online fashion, without additional task-information, and an efficient memory scheme provides robustness to imbalanced data streams. Besides nearest neighbor based prediction, learning is facilitated by a novel objective function, encouraging cluster density about the class prototype and increased inter-class variance. Furthermore, the latent space quality is elevated by pseudo-prototypes in each batch, constituted by replay of exemplars from memory. As an additional contribution, we generalize the existing paradigms in continual learning to incorporate data incremental learning from data streams by formalizing a two-agent learner-evaluator framework. We obtain state-of-the-art performance by a significant margin on eight benchmarks, including three highly imbalanced data streams.