# Incremental Learning In Online Scenario

arXiv: https://arxiv.org/abs/2003.13191 · HTML: https://mlsanity.com/paper/2003.13191/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2020.

## Built on by (most cited first, 30 of 71)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Replay in Deep Learning: Current Approaches and Missing Biological Elements](https://mlsanity.com/paper/2104.04132/) (2021)
- [Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference](https://mlsanity.com/paper/2110.10031/) (2021)
- [Continual Learning with Foundation Models: An Empirical Study of Latent Replay](https://mlsanity.com/paper/2205.00329/) (2022)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [Online Prototype Learning for Online Continual Learning](https://mlsanity.com/paper/2308.00301/) (2023)
- [Online Continual Learning For Visual Food Classification](https://mlsanity.com/paper/2108.06781/) (2021)
- [Open-world Machine Learning: Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2105.13448/) (2021)
- [Domain Generalization through Meta-Learning: A Survey](https://mlsanity.com/paper/2404.02785/) (2024)
- [CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning](https://mlsanity.com/paper/2505.24816/) (2025)
- [An End-to-End Food Image Analysis System](https://mlsanity.com/paper/2102.00645/) (2021)
- [Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysis](https://mlsanity.com/paper/2104.09396/) (2021)
- [Online Continual Learning with Contrastive Vision Transformer](https://mlsanity.com/paper/2207.13516/) (2022)
- [Do Pre-trained Models Benefit Equally in Continual Learning?](https://mlsanity.com/paper/2210.15701/) (2022)
- [Long-Tailed Continual Learning For Visual Food Recognition](https://mlsanity.com/paper/2307.00183/) (2023)
- [An Integrated System for Mobile Image-Based Dietary Assessment](https://mlsanity.com/paper/2110.01754/) (2021)
- [Long-tailed Food Classification](https://mlsanity.com/paper/2210.14748/) (2022)
- [Unsupervised Continual Learning Via Pseudo Labels](https://mlsanity.com/paper/2104.07164/) (2021)
- [Exemplar-free Online Continual Learning](https://mlsanity.com/paper/2202.05491/) (2022)
- [Online Class-Incremental Learning For Real-World Food Image Classification](https://mlsanity.com/paper/2301.05246/) (2023)
- [Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation](https://mlsanity.com/paper/2404.00417/) (2024)
- [Online Continual Learning Via Candidates Voting](https://mlsanity.com/paper/2110.08855/) (2021)
- [F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning](https://mlsanity.com/paper/2403.15751/) (2024)
- [Online Continual Learning on Hierarchical Label Expansion](https://mlsanity.com/paper/2308.14374/) (2023)
- [Out-Of-Distribution Detection In Unsupervised Continual Learning](https://mlsanity.com/paper/2204.05462/) (2022)
- [Self-Supervised Features Improve Open-World Learning](https://mlsanity.com/paper/2102.07848/) (2021)
- [Self-Supervised Class Incremental Learning](https://mlsanity.com/paper/2111.11208/) (2021)
- [DELTA: Decoupling Long-Tailed Online Continual Learning](https://mlsanity.com/paper/2404.04476/) (2024)

## Abstract (arXiv)

Modern deep learning approaches have achieved great success in many vision applications by training a model using all available task-specific data. However, there are two major obstacles making it challenging to implement for real life applications: (1) Learning new classes makes the trained model quickly forget old classes knowledge, which is referred to as catastrophic forgetting. (2) As new observations of old classes come sequentially over time, the distribution may change in unforeseen way, making the performance degrade dramatically on future data, which is referred to as concept drift. Current state-of-the-art incremental learning methods require a long time to train the model whenever new classes are added and none of them takes into consideration the new observations of old classes. In this paper, we propose an incremental learning framework that can work in the challenging online learning scenario and handle both new classes data and new observations of old classes. We address problem (1) in online mode by introducing a modified cross-distillation loss together with a two-step learning technique. Our method outperforms the results obtained from current state-of-the-art offline incremental learning methods on the CIFAR-100 and ImageNet-1000 (ILSVRC 2012) datasets under the same experiment protocol but in online scenario. We also provide a simple yet effective method to mitigate problem (2) by updating exemplar set using the feature of each new observation of old classes and demonstrate a real life application of online food image classification based on our complete framework using the Food-101 dataset.