# On the Discrimination and Consistency for Exemplar-Free Class Incremental Learning

arXiv: https://arxiv.org/abs/2501.15454 · HTML: https://mlsanity.com/paper/2501.15454/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 43 references that are in the map.
- First posted on arXiv 26 Jan 2025.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [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)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Large Batch Training of Convolutional Networks](https://mlsanity.com/paper/1708.03888/) (2017)
- [DER: Dynamically Expandable Representation for Class Incremental Learning](https://mlsanity.com/paper/2103.16788/) (2021)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [FOSTER: Feature Boosting and Compression for Class-Incremental Learning](https://mlsanity.com/paper/2204.04662/) (2022)
- [A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning](https://mlsanity.com/paper/2205.13218/) (2022)
- [How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?](https://mlsanity.com/paper/2203.04450/) (2022)
- [FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning](https://mlsanity.com/paper/2211.13131/) (2022)
- [Conditional Channel Gated Networks for Task-Aware Continual Learning](https://mlsanity.com/paper/2004.00070/) (2020)
- [iTAML: An Incremental Task-Agnostic Meta-learning Approach](https://mlsanity.com/paper/2003.11652/) (2020)
- [A Theoretical Study on Solving Continual Learning](https://mlsanity.com/paper/2211.02633/) (2022)
- [Provable Guarantees for Understanding Out-of-distribution Detection](https://mlsanity.com/paper/2112.00787/) (2021)
- [ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection](https://mlsanity.com/paper/2205.14922/) (2022)
- [Posterior Meta-Replay for Continual Learning](https://mlsanity.com/paper/2103.01133/) (2021)
- [Learning with Mixture of Prototypes for Out-of-Distribution Detection](https://mlsanity.com/paper/2402.02653/) (2024)
- [Divide and not forget: Ensemble of selectively trained experts in Continual Learning](https://mlsanity.com/paper/2401.10191/) (2024)
- [Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning](https://mlsanity.com/paper/2402.03917/) (2024)
- [Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning](https://mlsanity.com/paper/2405.19074/) (2024)
- [Exemplar-free Continual Representation Learning via Learnable Drift Compensation](https://mlsanity.com/paper/2407.08536/) (2024)
- [Learnability and Algorithm for Continual Learning](https://mlsanity.com/paper/2306.12646/) (2023)
- [DiffClass: Diffusion-Based Class Incremental Learning](https://mlsanity.com/paper/2403.05016/) (2024)
- [Continual Learning Based on OOD Detection and Task Masking](https://mlsanity.com/paper/2203.09450/) (2022)
- [Class Incremental Learning via Likelihood Ratio Based Task Prediction](https://mlsanity.com/paper/2309.15048/) (2023)
- [Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding](https://mlsanity.com/paper/2401.09067/) (2024)

## Built on by (most cited first, 8 of 8)

- [SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning](https://mlsanity.com/paper/2503.10252/) (2025)
- [Distributed Zero-Shot Learning for Visual Recognition](https://mlsanity.com/paper/2511.08170/) (2025)
- [Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction](https://mlsanity.com/paper/2606.24156/) (2026)
- [No Forgetting Learning: Buffer-free Continual Learning Classification](https://mlsanity.com/paper/2503.04638/) (2025)
- [Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning](https://mlsanity.com/paper/2507.21588/) (2025)
- [Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models](https://mlsanity.com/paper/2606.24165/) (2026)
- [GR4CIL: Gap-compensated Routing for CLIP-based Class Incremental Learning](https://mlsanity.com/paper/2604.17822/) (2026)
- [Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?](https://mlsanity.com/paper/2605.15877/) (2026)

## Abstract (arXiv)

Exemplar-free class incremental learning (EF-CIL) is a nontrivial task that requires continuously enriching model capability with new classes while maintaining previously learned knowledge without storing and replaying any old class exemplars. An emerging theory-guided framework for CIL trains task-specific models for a shared network, shifting the pressure of forgetting to task-id prediction. In EF-CIL, task-id prediction is more challenging due to the lack of inter-task interaction (e.g., replays of exemplars). To address this issue, we conduct a theoretical analysis of the importance and feasibility of preserving a discriminative and consistent feature space, upon which we propose a novel method termed DCNet. Concretely, it progressively maps class representations into a hyperspherical space, in which different classes are orthogonally distributed to achieve ample inter-class separation. Meanwhile, it also introduces compensatory training to adaptively adjust supervision intensity, thereby aligning the degree of intra-class aggregation. Extensive experiments and theoretical analysis verified the superiority of the proposed DCNet.