# Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning

arXiv: https://arxiv.org/abs/2501.15998 · HTML: https://mlsanity.com/paper/2501.15998/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 27 Jan 2025.

## Builds on (most cited first, 23 of 23)

- [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)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima](https://mlsanity.com/paper/2111.01549/) (2021)
- [Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2103.04059/) (2021)
- [Large Scale Visual Food Recognition](https://mlsanity.com/paper/2103.16107/) (2021)
- [MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2006.15524/) (2020)
- [Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.00426/) (2023)
- [Class-Incremental Exemplar Compression for Class-Incremental Learning](https://mlsanity.com/paper/2303.14042/) (2023)
- [A Survey on Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.08130/) (2023)
- [OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2403.18550/) (2024)
- [Long-Tailed Continual Learning For Visual Food Recognition](https://mlsanity.com/paper/2307.00183/) (2023)
- [Online Class-Incremental Learning For Real-World Food Image Classification](https://mlsanity.com/paper/2301.05246/) (2023)
- [Online Continual Learning for Robust Indoor Object Recognition](https://mlsanity.com/paper/2307.09827/) (2023)
- [Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search](https://mlsanity.com/paper/2407.07541/) (2024)
- [Object-conditioned Bag of Instances for Few-Shot Personalized Instance Recognition](https://mlsanity.com/paper/2404.01397/) (2024)
- [Incremental Learning on Food Instance Segmentation](https://mlsanity.com/paper/2306.15910/) (2023)
- [Generalizable Two-Branch Framework for Image Class-Incremental Learning](https://mlsanity.com/paper/2402.18086/) (2024)

## Built on by (most cited first, 1 of 1)

- [Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL](https://mlsanity.com/paper/2510.03608/) (2025)

## Abstract (arXiv)

Class-incremental learning in the context of limited personal labeled samples (few-shot) is critical for numerous real-world applications, such as smart home devices. A key challenge in these scenarios is balancing the trade-off between adapting to new, personalized classes and maintaining the performance of the model on the original, base classes. Fine-tuning the model on novel classes often leads to the phenomenon of catastrophic forgetting, where the accuracy of base classes declines unpredictably and significantly. In this paper, we propose a simple yet effective mechanism to address this challenge by controlling the trade-off between novel and base class accuracy. We specifically target the ultra-low-shot scenario, where only a single example is available per novel class. Our approach introduces a Novel Class Detection (NCD) rule, which adjusts the degree of forgetting a priori while simultaneously enhancing performance on novel classes. We demonstrate the versatility of our solution by applying it to state-of-the-art Few-Shot Class-Incremental Learning (FSCIL) methods, showing consistent improvements across different settings. To better quantify the trade-off between novel and base class performance, we introduce new metrics: NCR@2FOR and NCR@5FOR. Our approach achieves up to a 30% improvement in novel class accuracy on the CIFAR100 dataset (1-shot, 1 novel class) while maintaining a controlled base class forgetting rate of 2%.