Incremental Learning

375 papers with code • 22 benchmarks • 9 datasets

Incremental learning aims to develop artificially intelligent systems that can continuously learn to address new tasks from new data while preserving knowledge learned from previously learned tasks.

Libraries

Use these libraries to find Incremental Learning models and implementations
19 papers
669
11 papers
484
2 papers
14

Latest papers with no code

Enhancing Generative Class Incremental Learning Performance with Model Forgetting Approach

no code yet • 27 Mar 2024

This study presents a novel approach to Generative Class Incremental Learning (GCIL) by introducing the forgetting mechanism, aimed at dynamically managing class information for better adaptation to streaming data.

OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning

no code yet • 27 Mar 2024

To address these challenges, we propose the OrCo framework built on two core principles: features' orthogonality in the representation space, and contrastive learning.

Towards Non-Exemplar Semi-Supervised Class-Incremental Learning

no code yet • 27 Mar 2024

On the other hand, Semi-IPC learns a prototype for each class with unsupervised regularization, enabling the model to incrementally learn from partially labeled new data while maintaining the knowledge of old classes.

Recommendation of data-free class-incremental learning algorithms by simulating future data

no code yet • 26 Mar 2024

Our method outperforms competitive baselines, and performance is close to that of an oracle choosing the best algorithm in each setting.

One-Shot Domain Incremental Learning

no code yet • 25 Mar 2024

In DIL, we assume that samples on new domains are observed over time.

Object Detectors in the Open Environment: Challenges, Solutions, and Outlook

no code yet • 24 Mar 2024

This paper aims to bridge this gap by conducting a comprehensive review and analysis of object detectors in open environments.

Exemplar-Free Class Incremental Learning via Incremental Representation

no code yet • 24 Mar 2024

Exemplar-Free Class Incremental Learning (efCIL) aims to continuously incorporate the knowledge from new classes while retaining previously learned information, without storing any old-class exemplars (i. e., samples).

Enhancing Visual Continual Learning with Language-Guided Supervision

no code yet • 24 Mar 2024

Existing methods commonly utilize the one-hot labels and randomly initialize the classifier head.

AOCIL: Exemplar-free Analytic Online Class Incremental Learning with Low Time and Resource Consumption

no code yet • 23 Mar 2024

Online Class Incremental Learning (OCIL) aims to train the model in a task-by-task manner, where data arrive in mini-batches at a time while previous data are not accessible.

Defying Imbalanced Forgetting in Class Incremental Learning

no code yet • 22 Mar 2024

This intriguing phenomenon, discovered in replay-based Class Incremental Learning (CIL), highlights the imbalanced forgetting of learned classes, as their accuracy is similar before the occurrence of catastrophic forgetting.