# Memory Efficient Class-Incremental Learning for Image Classification

arXiv: https://arxiv.org/abs/2008.01411 · HTML: https://mlsanity.com/paper/2008.01411/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2020.

## Built on by (most cited first, 30 of 50)

- [Continual Learning of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2404.16789/) (2024)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need](https://mlsanity.com/paper/2303.07338/) (2023)
- [A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning](https://mlsanity.com/paper/2205.13218/) (2022)
- [Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning](https://mlsanity.com/paper/2403.12030/) (2024)
- [PILOT: A Pre-Trained Model-Based Continual Learning Toolbox](https://mlsanity.com/paper/2309.07117/) (2023)
- [PROB: Probabilistic Objectness for Open World Object Detection](https://mlsanity.com/paper/2212.01424/) (2022)
- [MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning](https://mlsanity.com/paper/2412.09441/) (2024)
- [RBC: Rectifying the Biased Context in Continual Semantic Segmentation](https://mlsanity.com/paper/2203.08404/) (2022)
- [Dealing with Cross-Task Class Discrimination in Online Continual Learning](https://mlsanity.com/paper/2305.14657/) (2023)
- [Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning](https://mlsanity.com/paper/2508.08165/) (2025)
- [When Video Classification Meets Incremental Classes](https://mlsanity.com/paper/2106.15827/) (2021)
- [Generative Negative Text Replay for Continual Vision-Language Pretraining](https://mlsanity.com/paper/2210.17322/) (2022)
- [Uncertainty-Aware Distillation for Semi-Supervised Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2301.09964/) (2023)
- [GRASP: A Rehearsal Policy for Efficient Online Continual Learning](https://mlsanity.com/paper/2308.13646/) (2023)
- [Early or Late Fusion Matters: Efficient RGB-D Fusion in Vision Transformers for 3D Object Recognition](https://mlsanity.com/paper/2210.00843/) (2022)
- [Masked Autoencoders are Efficient Class Incremental Learners](https://mlsanity.com/paper/2308.12510/) (2023)
- [Self-Supervised Class Incremental Learning](https://mlsanity.com/paper/2111.11208/) (2021)
- [Preventing Catastrophic Forgetting through Memory Networks in Continuous Detection](https://mlsanity.com/paper/2403.14797/) (2024)
- [DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype](https://mlsanity.com/paper/2503.18042/) (2025)
- [IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting](https://mlsanity.com/paper/2503.20612/) (2025)
- [Revisiting Catastrophic Forgetting in Class Incremental Learning](https://mlsanity.com/paper/2107.12308/) (2021)
- [Adma-GAN: Attribute-Driven Memory Augmented GANs for Text-to-Image Generation](https://mlsanity.com/paper/2209.14046/) (2022)
- [Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection](https://mlsanity.com/paper/2308.14286/) (2023)
- [Mamba-CL: Optimizing Selective State Space Model in Null Space for Continual Learning](https://mlsanity.com/paper/2411.15469/) (2024)
- [AdaptCL: Adaptive Continual Learning for Tackling Heterogeneity in Sequential Datasets](https://mlsanity.com/paper/2207.11005/) (2022)
- [MIRACLE3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model Construction](https://mlsanity.com/paper/2410.06418/) (2024)
- [Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning](https://mlsanity.com/paper/2508.05316/) (2025)
- [Elastic Weight Consolidation Done Right for Continual Learning](https://mlsanity.com/paper/2603.18596/) (2026)
- [HPCR: Holistic Proxy-based Contrastive Replay for Online Continual Learning](https://mlsanity.com/paper/2309.15038/) (2023)

## Abstract (arXiv)

With the memory-resource-limited constraints, class-incremental learning (CIL) usually suffers from the "catastrophic forgetting" problem when updating the joint classification model on the arrival of newly added classes. To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer. To utilize the memory buffer more efficiently, we propose to keep more auxiliary low-fidelity exemplar samples rather than the original real high-fidelity exemplar samples. Such a memory-efficient exemplar preserving scheme makes the old-class knowledge transfer more effective. However, the low-fidelity exemplar samples are often distributed in a different domain away from that of the original exemplar samples, that is, a domain shift. To alleviate this problem, we propose a duplet learning scheme that seeks to construct domain-compatible feature extractors and classifiers, which greatly narrows down the above domain gap. As a result, these low-fidelity auxiliary exemplar samples have the ability to moderately replace the original exemplar samples with a lower memory cost. In addition, we present a robust classifier adaptation scheme, which further refines the biased classifier (learned with the samples containing distillation label knowledge about old classes) with the help of the samples of pure true class labels. Experimental results demonstrate the effectiveness of this work against the state-of-the-art approaches.