# Class-Incremental Learning with Strong Pre-trained Models

arXiv: https://arxiv.org/abs/2204.03634 · HTML: https://mlsanity.com/paper/2204.03634/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 7 Apr 2022.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (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)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [Expert Gate: Lifelong Learning with a Network of Experts](https://mlsanity.com/paper/1611.06194/) (2016)
- [DER: Dynamically Expandable Representation for Class Incremental Learning](https://mlsanity.com/paper/2103.16788/) (2021)
- [Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/1904.00310/) (2019)
- [Maintaining Discrimination and Fairness in Class Incremental Learning](https://mlsanity.com/paper/1911.07053/) (2019)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [Supermasks in Superposition](https://mlsanity.com/paper/2006.14769/) (2020)
- [Compacting, Picking and Growing for Unforgetting Continual Learning](https://mlsanity.com/paper/1910.06562/) (2019)
- [SS-IL: Separated Softmax for Incremental Learning](https://mlsanity.com/paper/2003.13947/) (2020)
- [Conditional Channel Gated Networks for Task-Aware Continual Learning](https://mlsanity.com/paper/2004.00070/) (2020)
- [Growing a Brain: Fine-Tuning by Increasing Model Capacity](https://mlsanity.com/paper/1907.07844/) (2019)
- [Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier](https://mlsanity.com/paper/2007.09898/) (2020)
- [NetTailor: Tuning the Architecture, Not Just the Weights](https://mlsanity.com/paper/1907.00274/) (2019)

## Built on by (most cited first, 30 of 60)

- [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)
- [SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model](https://mlsanity.com/paper/2303.05118/) (2023)
- [RanPAC: Random Projections and Pre-trained Models for Continual Learning](https://mlsanity.com/paper/2307.02251/) (2023)
- [A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning](https://mlsanity.com/paper/2205.13218/) (2022)
- [Computationally Budgeted Continual Learning: What Does Matter?](https://mlsanity.com/paper/2303.11165/) (2023)
- [No One Left Behind: Real-World Federated Class-Incremental Learning](https://mlsanity.com/paper/2302.00903/) (2023)
- [Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion](https://mlsanity.com/paper/2407.14143/) (2024)
- [First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning](https://mlsanity.com/paper/2303.13199/) (2023)
- [Dense Network Expansion for Class Incremental Learning](https://mlsanity.com/paper/2303.12696/) (2023)
- [Weighted Ensemble Models Are Strong Continual Learners](https://mlsanity.com/paper/2312.08977/) (2023)
- [CLAD: A realistic Continual Learning benchmark for Autonomous Driving](https://mlsanity.com/paper/2210.03482/) (2022)
- [Online Continual Learning Without the Storage Constraint](https://mlsanity.com/paper/2305.09253/) (2023)
- [Learnability and Algorithm for Continual Learning](https://mlsanity.com/paper/2306.12646/) (2023)
- [Generative Multi-modal Models are Good Class-Incremental Learners](https://mlsanity.com/paper/2403.18383/) (2024)
- [Continual Segment: Towards a Single, Unified and Accessible Continual Segmentation Model of 143 Whole-body Organs in CT Scans](https://mlsanity.com/paper/2302.00162/) (2023)
- [A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application](https://mlsanity.com/paper/2310.14277/) (2023)
- [Long-Tailed Continual Learning For Visual Food Recognition](https://mlsanity.com/paper/2307.00183/) (2023)
- [PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning](https://mlsanity.com/paper/2401.02094/) (2024)
- [LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning](https://mlsanity.com/paper/2503.18985/) (2025)
- [New Insights for the Stability-Plasticity Dilemma in Online Continual Learning](https://mlsanity.com/paper/2302.08741/) (2023)
- [Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery](https://mlsanity.com/paper/2303.15975/) (2023)
- [Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?](https://mlsanity.com/paper/2305.09275/) (2023)
- [Continual Adapter Tuning with Semantic Shift Compensation for Class-Incremental Learning](https://mlsanity.com/paper/2403.19979/) (2024)
- [MuseumMaker: Continual Style Customization without Catastrophic Forgetting](https://mlsanity.com/paper/2404.16612/) (2024)
- [SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training](https://mlsanity.com/paper/2408.08295/) (2024)
- [Learning with Style: Continual Semantic Segmentation Across Tasks and Domains](https://mlsanity.com/paper/2210.07016/) (2022)
- [SPECI: Skill Prompts based Hierarchical Continual Imitation Learning for Robot Manipulation](https://mlsanity.com/paper/2504.15561/) (2025)
- [POP: Prompt Of Prompts for Continual Learning](https://mlsanity.com/paper/2306.08200/) (2023)
- [An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning](https://mlsanity.com/paper/2308.11677/) (2023)

## Abstract (arXiv)

Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes). Instead, we explore an understudied real-world setting of CIL that starts with a strong model pre-trained on a large number of base classes. We hypothesize that a strong base model can provide a good representation for novel classes and incremental learning can be done with small adaptations. We propose a 2-stage training scheme, i) feature augmentation -- cloning part of the backbone and fine-tuning it on the novel data, and ii) fusion -- combining the base and novel classifiers into a unified classifier. Experiments show that the proposed method significantly outperforms state-of-the-art CIL methods on the large-scale ImageNet dataset (e.g. +10% overall accuracy than the best). We also propose and analyze understudied practical CIL scenarios, such as base-novel overlap with distribution shift. Our proposed method is robust and generalizes to all analyzed CIL settings. Code is available at https://github.com/amazon-research/sp-cil.