# Exemplar-Free Class Incremental Learning via Incremental Representation

arXiv: https://arxiv.org/abs/2403.16221 · HTML: https://mlsanity.com/paper/2403.16221/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 51 references that are in the map.
- First posted on arXiv 24 Mar 2024.

## Builds on (most cited first, 12 of 12)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines](https://mlsanity.com/paper/1810.12488/) (2018)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning](https://mlsanity.com/paper/2106.11562/) (2021)
- [RMM: Reinforced Memory Management for Class-Incremental Learning](https://mlsanity.com/paper/2301.05792/) (2023)
- [Lifelong Generative Learning via Knowledge Reconstruction](https://mlsanity.com/paper/2201.06418/) (2022)

## Abstract (arXiv)

Exemplar-Free Class Incremental Learning (efCIL) aims to continuously incorporate the knowledge from new classes while retaining previously learned information, without storing any old-class exemplars (i.e., samples). For this purpose, various efCIL methods have been proposed over the past few years, generally with elaborately constructed old pseudo-features, increasing the difficulty of model development and interpretation. In contrast, we propose a simple Incremental Representation (IR) framework for efCIL without constructing old pseudo-features. IR utilizes dataset augmentation to cover a suitable feature space and prevents the model from forgetting by using a single L2 space maintenance loss. We discard the transient classifier trained on each one of the sequence tasks and instead replace it with a 1-near-neighbor classifier for inference, ensuring the representation is incrementally updated during CIL. Extensive experiments demonstrate that our proposed IR achieves comparable performance while significantly preventing the model from forgetting on CIFAR100, TinyImageNet, and ImageNetSubset datasets.