Incremental Learning
390 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 implementationsDatasets
Most implemented papers
Class-incremental Learning via Deep Model Consolidation
The idea is to first train a separate model only for the new classes, and then combine the two individual models trained on data of two distinct set of classes (old classes and new classes) via a novel double distillation training objective.
Learning a Unified Classifier Incrementally via Rebalancing
However, it has been observed that incremental learning is subject to a fundamental difficulty -- catastrophic forgetting, namely adapting a model to new data often results in severe performance degradation on previous tasks or classes.
Incremental Learning Techniques for Semantic Segmentation
To tackle this task we propose to distill the knowledge of the previous model to retain the information about previously learned classes, whilst updating the current model to learn the new ones.
IL2M: Class Incremental Learning With Dual Memory
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.
Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks
When training a neural network for a desired task, one may prefer to adapt a pre-trained network rather than starting from randomly initialized weights.
Mnemonics Training: Multi-Class Incremental Learning without Forgetting
However, there is an inherent trade-off to effectively learning new concepts without catastrophic forgetting of previous ones.
Incremental Object Detection via Meta-Learning
In a real-world setting, object instances from new classes can be continuously encountered by object detectors.
Semantic Drift Compensation for Class-Incremental Learning
The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes.
PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning
Lifelong learning has attracted much attention, but existing works still struggle to fight catastrophic forgetting and accumulate knowledge over long stretches of incremental learning.
GloDyNE: Global Topology Preserving Dynamic Network Embedding
The main and common objective of Dynamic Network Embedding (DNE) is to efficiently update node embeddings while preserving network topology at each time step.