# Prototypical quadruplet for few-shot class incremental learning

arXiv: https://arxiv.org/abs/2211.02947 · HTML: https://mlsanity.com/paper/2211.02947/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 65 references that are in the map.
- First posted on arXiv 5 Nov 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Gradient Projection Memory for Continual Learning](https://mlsanity.com/paper/2103.09762/) (2021)
- [A simple neural network module for relational reasoning](https://mlsanity.com/paper/1706.01427/) (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)
- [Low-Shot Learning from Imaginary Data](https://mlsanity.com/paper/1801.05401/) (2018)
- [Beyond triplet loss: a deep quadruplet network for person re-identification](https://mlsanity.com/paper/1704.01719/) (2017)
- [Delving into Deep Imbalanced Regression](https://mlsanity.com/paper/2102.09554/) (2021)
- [Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2103.04059/) (2021)
- [Constrained Few-shot Class-incremental Learning](https://mlsanity.com/paper/2203.16588/) (2022)
- [GAN Memory with No Forgetting](https://mlsanity.com/paper/2006.07543/) (2020)
- [A PAC-Bayesian bound for Lifelong Learning](https://mlsanity.com/paper/1311.2838/) (2013)
- [Task Agnostic Continual Learning Using Online Variational Bayes](https://mlsanity.com/paper/1803.10123/) (2018)
- [Few-Shot Lifelong Learning](https://mlsanity.com/paper/2103.00991/) (2021)
- [Efficient Representations for Life-Long Learning and Autoencoding](https://mlsanity.com/paper/1411.1490/) (2014)
- [Regret Bounds for Lifelong Learning](https://mlsanity.com/paper/1610.08628/) (2016)
- [Quadruplet Network with One-Shot Learning for Fast Visual Object Tracking](https://mlsanity.com/paper/1705.07222/) (2017)

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

- [A Fusion of Variational Distribution Priors and Saliency Map Replay for Continual 3D Reconstruction](https://mlsanity.com/paper/2308.08812/) (2023)

## Abstract (arXiv)

Scarcity of data and incremental learning of new tasks pose two major bottlenecks for many modern computer vision algorithms. The phenomenon of catastrophic forgetting, i.e., the model's inability to classify previously learned data after training with new batches of data, is a major challenge. Conventional methods address catastrophic forgetting while compromising the current session's training. Generative replay-based approaches, such as generative adversarial networks (GANs), have been proposed to mitigate catastrophic forgetting, but training GANs with few samples may lead to instability. To address these challenges, we propose a novel method that improves classification robustness by identifying a better embedding space using an improved contrasting loss. Our approach retains previously acquired knowledge in the embedding space, even when trained with new classes, by updating previous session class prototypes to represent the true class mean, which is crucial for our nearest class mean classification strategy. We demonstrate the effectiveness of our method by showing that the embedding space remains intact after training the model with new classes and outperforms existing state-of-the-art algorithms in terms of accuracy across different sessions.