TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Few-Shot Class-Incremental Learning	CIFAR-100	AL-MML	Average Accuracy	42.62	# 8
Few-Shot Class-Incremental Learning	mini-Imagenet	AL-MML	Average Accuracy	39.64	# 9
Few-Shot Class-Incremental Learning	mini-Imagenet	AL-MML	Last Accuracy	24.42	# 10

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/few-shot-class-incremental-learning/few-shot-class-incremental-learning-on-cifar)](https://paperswithcode.com/sota/few-shot-class-incremental-learning-on-cifar?p=few-shot-class-incremental-learning)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/few-shot-class-incremental-learning/few-shot-class-incremental-learning-on-mini)](https://paperswithcode.com/sota/few-shot-class-incremental-learning-on-mini?p=few-shot-class-incremental-learning)`

Few-Shot Class-Incremental Learning

CVPR 2020 · Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang, Songlin Dong, Xing Wei, Yihong Gong ·

The ability to incrementally learn new classes is crucial to the development of real-world artificial intelligence systems. In this paper, we focus on a challenging but practical few-shot class-incremental learning (FSCIL) problem. FSCIL requires CNN models to incrementally learn new classes from very few labelled samples, without forgetting the previously learned ones. To address this problem, we represent the knowledge using a neural gas (NG) network, which can learn and preserve the topology of the feature manifold formed by different classes. On this basis, we propose the TOpology-Preserving knowledge InCrementer (TOPIC) framework. TOPIC mitigates the forgetting of the old classes by stabilizing NG's topology and improves the representation learning for few-shot new classes by growing and adapting NG to new training samples. Comprehensive experimental results demonstrate that our proposed method significantly outperforms other state-of-the-art class-incremental learning methods on CIFAR100, miniImageNet, and CUB200 datasets.

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract

Code

Add Remove Mark official

xyutao/fscil

209

Tasks

Add Remove

Class Incremental Learning

Few-Shot Class-Incremental Learning

Incremental Learning

Representation Learning

Datasets

CIFAR-100

CUB-200-2011 mini-Imagenet

Results from the Paper

Edit

Ranked #8 on Few-Shot Class-Incremental Learning on CIFAR-100 (Average Accuracy metric)

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Few-Shot Class-Incremental Learning	CIFAR-100	AL-MML	Average Accuracy	42.62	# 8	Compare
Few-Shot Class-Incremental Learning	mini-Imagenet	AL-MML	Average Accuracy	39.64	# 9	Compare
Few-Shot Class-Incremental Learning	mini-Imagenet	AL-MML	Last Accuracy	24.42	# 10	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

Few-Shot Class-Incremental Learning

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove