# Class-incremental Learning with Pre-allocated Fixed Classifiers

arXiv: https://arxiv.org/abs/2010.08657 · HTML: https://mlsanity.com/paper/2010.08657/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2020.

## Built on by (most cited first, 30 of 33)

- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Forward Compatible Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2203.06953/) (2022)
- [Class-Incremental Continual Learning into the eXtended DER-verse](https://mlsanity.com/paper/2201.00766/) (2022)
- [Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2302.03004/) (2023)
- [Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation](https://mlsanity.com/paper/2210.04524/) (2022)
- [Regular Polytope Networks](https://mlsanity.com/paper/2103.15632/) (2021)
- [Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning](https://mlsanity.com/paper/2508.08165/) (2025)
- [CoReS: Compatible Representations via Stationarity](https://mlsanity.com/paper/2111.07632/) (2021)
- [Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants](https://mlsanity.com/paper/2308.01746/) (2023)
- [NPCL: Neural Processes for Uncertainty-Aware Continual Learning](https://mlsanity.com/paper/2310.19272/) (2023)
- [Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding](https://mlsanity.com/paper/2401.09067/) (2024)
- [Predicting the Susceptibility of Examples to Catastrophic Forgetting](https://mlsanity.com/paper/2406.09935/) (2024)
- [Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2407.06136/) (2024)
- [CL2R: Compatible Lifelong Learning Representations](https://mlsanity.com/paper/2211.09032/) (2022)
- [Latent Spectral Regularization for Continual Learning](https://mlsanity.com/paper/2301.03345/) (2023)
- [Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning](https://mlsanity.com/paper/2306.03364/) (2023)
- [Fine-Grained Adversarial Semi-supervised Learning](https://mlsanity.com/paper/2110.05848/) (2021)
- [Pairwise Similarity Learning is SimPLE](https://mlsanity.com/paper/2310.09449/) (2023)
- [Wake-Sleep Consolidated Learning](https://mlsanity.com/paper/2401.08623/) (2023)
- [Future-Proofing Class-Incremental Learning](https://mlsanity.com/paper/2404.03200/) (2024)
- [Contrastive Supervised Distillation for Continual Representation Learning](https://mlsanity.com/paper/2205.05476/) (2022)
- [Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning](https://mlsanity.com/paper/2508.05316/) (2025)
- [MASIL: Towards Maximum Separable Class Representation for Few Shot Class Incremental Learning](https://mlsanity.com/paper/2304.05362/) (2023)
- [Constructing Sample-to-Class Graph for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2310.20268/) (2023)
- [Class incremental learning with probability dampening and cascaded gated classifier](https://mlsanity.com/paper/2402.01262/) (2024)
- [A Stationary (and Therefore Compatible) Representation is All You Need](https://mlsanity.com/paper/2606.12488/) (2026)
- [Classifier Crafting: Turn Your ConvNet into a Zero-Shot Learner!](https://mlsanity.com/paper/2103.11112/) (2021)
- [Two-level Graph Network for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2303.13862/) (2023)
- [Revisiting Softmax Masking: Stop Gradient for Enhancing Stability in Replay-based Continual Learning](https://mlsanity.com/paper/2309.14808/) (2023)
- [POET: Prompt Offset Tuning for Continual Human Action Adaptation](https://mlsanity.com/paper/2504.18059/) (2025)

## Abstract (arXiv)

In class-incremental learning, a learning agent faces a stream of data with the goal of learning new classes while not forgetting previous ones. Neural networks are known to suffer under this setting, as they forget previously acquired knowledge. To address this problem, effective methods exploit past data stored in an episodic memory while expanding the final classifier nodes to accommodate the new classes. In this work, we substitute the expanding classifier with a novel fixed classifier in which a number of pre-allocated output nodes are subject to the classification loss right from the beginning of the learning phase. Contrarily to the standard expanding classifier, this allows: (a) the output nodes of future unseen classes to firstly see negative samples since the beginning of learning together with the positive samples that incrementally arrive; (b) to learn features that do not change their geometric configuration as novel classes are incorporated in the learning model. Experiments with public datasets show that the proposed approach is as effective as the expanding classifier while exhibiting novel intriguing properties of the internal feature representation that are otherwise not-existent. Our ablation study on pre-allocating a large number of classes further validates the approach.