Incremental Learning

Incremental learning aims to enable machine learning models to continuously acquire new knowledge from sequential data streams without forgetting previously learned information, a challenge known as catastrophic forgetting. Current research focuses on developing algorithms and model architectures, such as those employing knowledge distillation, generative replay, and various regularization techniques, to address this issue across diverse applications like image classification, gesture recognition, and medical image analysis. This field is significant because it moves machine learning closer to human-like continuous learning capabilities, with potential impacts on personalized medicine, robotics, and other areas requiring adaptation to evolving data.

Papers

December 20, 2021

Proving Theorems using Incremental Learning and Hindsight Experience Replay
Eser Aygün, Laurent Orseau, Ankit Anand, Xavier Glorot, Vlad Firoiu, Lei M. Zhang, Doina Precup, Shibl Mourad
Incremental Learning Theorem Proving First Order Logic Theorem Provers Hindsight Experience Replay Conflict Driven Clause Learning

December 12, 2021

Improving Vision Transformers for Incremental Learning
Pei Yu, Yinpeng Chen, Ying Jin, Zicheng Liu
Convolutional Neural Network Vision Transformer Incremental Learning Convolutional Neural Network Architecture

December 7, 2021

A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images
Edoardo Arnaudo, Fabio Cermelli, Antonio Tavera, Claudio Rossi, Barbara Caputo
Semantic Segmentation Incremental Learning Class Incremental Learning Aerial Image Contrastive Distillation Incremental Semantic Segmentation

December 5, 2021

CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks
Zixuan Ke, Bing Liu, Hu Xu, Lei Shu
Contrastive Learning Knowledge Distillation Continual LEArning Incremental Learning Federat\textbf{T}ed Cl\textbf{A}ss Continual Lea\textbf{R}nin\textbf{G CLASSIC Modern Contemporary Aspect Based Sentiment Classification Contrastive Continual Learning

December 3, 2021

Incremental Learning in Semantic Segmentation from Image Labels
Fabio Cermelli, Dario Fontanel, Antonio Tavera, Marco Ciccone, Barbara Caputo
Semantic Segmentation Incremental Learning Pixel Level Annotation Image Level Label Labeling Image

November 18, 2021

Self-Supervised Class Incremental Learning
Zixuan Ni, Siliang Tang, Yueting Zhuang
Incremental Learning Class Incremental Learning Self Supervised Representation Learning

November 10, 2021

Lightweight machine unlearning in neural network
Kongyang Chen, Yiwen Wang, Yao Huang
Neural Network Incremental Learning Machine Unlearning Memory Trace Data Privacy