About

Incremental learning of a sequence of tasks when the task-ID is not available at test time.

Benchmarks

No evaluation results yet. Help compare methods by submit evaluation metrics.

Greatest papers with code

Three scenarios for continual learning

15 Apr 2019GMvandeVen/continual-learning

Standard artificial neural networks suffer from the well-known issue of catastrophic forgetting, making continual or lifelong learning difficult for machine learning.

CLASS-INCREMENTAL LEARNING INCREMENTAL LEARNING

Adaptive Aggregation Networks for Class-Incremental Learning

10 Oct 2020yaoyao-liu/mnemonics

Class-Incremental Learning (CIL) aims to learn a classification model with the number of classes increasing phase-by-phase.

CLASS-INCREMENTAL LEARNING INCREMENTAL LEARNING

Mnemonics Training: Multi-Class Incremental Learning without Forgetting

CVPR 2020 yaoyao-liu/mnemonics

However, there is an inherent trade-off to effectively learning new concepts without catastrophic forgetting of previous ones.

CLASS-INCREMENTAL LEARNING INCREMENTAL LEARNING

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

NeurIPS 2018 pokaxpoka/deep_Mahalanobis_detector

Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning applications.

CLASS-INCREMENTAL LEARNING INCREMENTAL LEARNING OUT-OF-DISTRIBUTION DETECTION

Brain-inspired replay for continual learning with artificial neural networks

13 Aug 2020GMvandeVen/brain-inspired-replay

In artificial neural networks, such memory replay can be implemented as ‘generative replay’, which can successfully – and surprisingly efficiently – prevent catastrophic forgetting on toy examples even in a class-incremental learning scenario.

CLASS-INCREMENTAL LEARNING INCREMENTAL LEARNING

A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks

3 Nov 2020EdenBelouadah/class-incremental-learning

A second type of approaches fix the deep model size and introduce a mechanism whose objective is to ensure a good compromise between stability and plasticity of the model.

CLASS-INCREMENTAL LEARNING INCREMENTAL LEARNING KNOWLEDGE DISTILLATION

Initial Classifier Weights Replay for Memoryless Class Incremental Learning

31 Aug 2020EdenBelouadah/class-incremental-learning

It leverages initial classifier weights which provide a strong representation of past classes because they are trained with all class data.

CLASS-INCREMENTAL LEARNING FAIRNESS INCREMENTAL LEARNING KNOWLEDGE DISTILLATION

Active Class Incremental Learning for Imbalanced Datasets

25 Aug 2020EdenBelouadah/class-incremental-learning

Most existing algorithms make two strong hypotheses which reduce the realism of the incremental scenario: (1) new data are assumed to be readily annotated when streamed and (2) tests are run with balanced datasets while most real-life datasets are actually imbalanced.

CLASS-INCREMENTAL LEARNING INCREMENTAL LEARNING KNOWLEDGE DISTILLATION

ScaIL: Classifier Weights Scaling for Class Incremental Learning

16 Jan 2020EdenBelouadah/class-incremental-learning

The problem is non trivial if the agent runs on a limited computational budget and has a bounded memory of past data.

CLASS-INCREMENTAL LEARNING INCREMENTAL LEARNING

IL2M: Class Incremental Learning With Dual Memory

ICCV 2019 EdenBelouadah/class-incremental-learning

This paper presents a class incremental learning (IL) method which exploits fine tuning and a dual memory to reduce the negative effect of catastrophic forgetting in image recognition.

CLASS-INCREMENTAL LEARNING INCREMENTAL LEARNING