# Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class Incremental Learning

arXiv: https://arxiv.org/abs/2312.12722 · HTML: https://mlsanity.com/paper/2312.12722/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 20 Dec 2023.

## Builds on (most cited first, 14 of 14)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (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)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion](https://mlsanity.com/paper/2111.11326/) (2021)
- [Semantic Drift Compensation for Class-Incremental Learning](https://mlsanity.com/paper/2004.00440/) (2020)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Data-Free Learning of Student Networks](https://mlsanity.com/paper/1904.01186/) (2019)
- [Adaptive Aggregation Networks for Class-Incremental Learning](https://mlsanity.com/paper/2010.05063/) (2020)
- [Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting](https://mlsanity.com/paper/1802.02950/) (2018)
- [Self-Training for Class-Incremental Semantic Segmentation](https://mlsanity.com/paper/2012.03362/) (2020)

## Built on by (most cited first, 9 of 9)

- [Language Guided Concept Bottleneck Models for Interpretable Continual Learning](https://mlsanity.com/paper/2503.23283/) (2025)
- [Dynamic Integration of Task-Specific Adapters for Class Incremental Learning](https://mlsanity.com/paper/2409.14983/) (2024)
- [Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning](https://mlsanity.com/paper/2502.07560/) (2025)
- [Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning](https://mlsanity.com/paper/2408.01076/) (2024)
- [CEAT: Continual Expansion and Absorption Transformer for Non-Exemplar Class-Incremental Learning](https://mlsanity.com/paper/2403.06670/) (2024)
- [Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective](https://mlsanity.com/paper/2407.17120/) (2024)
- [Harmony: A Unified Framework for Modality Incremental Learning](https://mlsanity.com/paper/2504.13218/) (2025)
- [Continual Learning Beyond Experience Rehearsal and Full Model Surrogates](https://mlsanity.com/paper/2505.21942/) (2025)
- [Compensating Visual Insufficiency with Stratified Language Guidance for Long-Tail Class Incremental Learning](https://mlsanity.com/paper/2603.21708/) (2026)

## Abstract (arXiv)

Non-exemplar class incremental learning aims to learn both the new and old tasks without accessing any training data from the past. This strict restriction enlarges the difficulty of alleviating catastrophic forgetting since all techniques can only be applied to current task data. Considering this challenge, we propose a novel framework of fine-grained knowledge selection and restoration. The conventional knowledge distillation-based methods place too strict constraints on the network parameters and features to prevent forgetting, which limits the training of new tasks. To loose this constraint, we proposed a novel fine-grained selective patch-level distillation to adaptively balance plasticity and stability. Some task-agnostic patches can be used to preserve the decision boundary of the old task. While some patches containing the important foreground are favorable for learning the new task. Moreover, we employ a task-agnostic mechanism to generate more realistic prototypes of old tasks with the current task sample for reducing classifier bias for fine-grained knowledge restoration. Extensive experiments on CIFAR100, TinyImageNet and ImageNet-Subset demonstrate the effectiveness of our method. Code is available at https://github.com/scok30/vit-cil.