Class Incremental Learning

Class incremental learning (CIL) focuses on training machine learning models to continuously learn new classes of data without forgetting previously learned ones, a crucial challenge for real-world applications with evolving data streams. Current research emphasizes techniques like dynamic model architectures (e.g., adding task-specific adapters), generative replay methods to synthesize past data, and the use of pre-trained models to leverage existing knowledge. These advancements aim to improve accuracy and fairness while addressing issues like catastrophic forgetting and data imbalance, impacting fields such as medical image analysis, sound source localization, and personalized AI systems.

Papers

October 5, 2023

Hadamard Domain Training with Integers for Class Incremental Quantized Learning
Martin Schiemer, Clemens JS Schaefer, Jayden Parker Vap, Mark James Horeni, Yu Emma Wang, Juan Ye, Siddharth Joshi
Continual LEArning Incremental Learning Class Incremental Learning Quantization Technique Integer Arithmetic Low Precision Training Directed Accumulator Mixed Domain

October 4, 2023

COOLer: Class-Incremental Learning for Appearance-Based Multiple Object Tracking
Zhizheng Liu, Mattia Segu, Fisher Yu
Continual LEArning Continual Learning Class Incremental Learning Multiple Object Tracking Incremental Instance

September 26, 2023

Class Incremental Learning via Likelihood Ratio Based Task Prediction
Haowei Lin, Yijia Shao, Weinan Qian, Ningxin Pan, Yiduo Guo, Bing Liu
Continual LEArning Incremental Learning Class Incremental Learning Task Specific Model Task Prediction Task Incremental Learning

September 13, 2023

PILOT: A Pre-Trained Model-Based Continual Learning Toolbox
Hai-Long Sun, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan
Pre Trained Model Incremental Learning Class Incremental Learning Continual Pre Training Continual Learning Algorithm Mercedes Benz Drive Pilot

September 11, 2023

September 6, 2023

Image-Object-Specific Prompt Learning for Few-Shot Class-Incremental Learning
In-Ug Yoon, Tae-Min Choi, Sun-Kyung Lee, Young-Min Kim, Jong-Hwan Kim
Prompt Learning Class Incremental Learning Contrastive Language Image Unseen Class Novel Training Training Set

August 25, 2023

Dynamic Residual Classifier for Class Incremental Learning
Xiuwei Chen, Xiaobin Chang
Catastrophic Forgetting Incremental Learning Class Incremental Learning Model Adaptation Residual Classifier

August 24, 2023

Masked Autoencoders are Efficient Class Incremental Learners
Jiang-Tian Zhai, Xialei Liu, Andrew D. Bagdanov, Ke Li, Ming-Ming Cheng
Class Incremental Learning Masked Autoencoders Efficient Learning Incremental Learning Framework

August 22, 2023

An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning
Grégoire Petit, Michael Soumm, Eva Feillet, Adrian Popescu, Bertrand Delezoide, David Picard, Céline Hudelot
General Analysis Incremental Learning Class Incremental Learning Training Dynamic Exemplar Free Class Incremental Learning

August 18, 2023

NAPA-VQ: Neighborhood Aware Prototype Augmentation with Vector Quantization for Continual Learning
Tamasha Malepathirana, Damith Senanayake, Saman Halgamuge
Continual LEArning Catastrophic Forgetting Class Incremental Learning Vector Quantization Prototype Based Prototype Highlighting Current Challenge

August 13, 2023

SATHUR: Self Augmenting Task Hallucinal Unified Representation for Generalized Class Incremental Learning
Sathursan Kanagarajah, Thanuja Ambegoda, Ranga Rodrigo
Convolutional Neural Network Incremental Learning Class Incremental Learning Convolutional Layer Self Information

August 7, 2023

Heterogeneous Forgetting Compensation for Class-Incremental Learning
Jiahua Dong, Wenqi Liang, Yang Cong, Gan Sun
Catastrophic Forgetting Class Incremental Learning Anti Forgetting Relation Distillation

August 4, 2023

Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning
Wenzhuo Liu, Xinjian Wu, Fei Zhu, Mingming Yu, Chuang Wang, Cheng-Lin Liu
Deep Neural Network Catastrophic Forgetting Incremental Learning Class Incremental Learning Self Supervised Pre Training Representation Drift

August 3, 2023

Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants
Yibo Yang, Haobo Yuan, Xiangtai Li, Jianlong Wu, Lefei Zhang, Zhouchen Lin, Philip Torr, Dacheng Tao, Bernard Ghanem
Unified Framework Incremental Learning Class Incremental Learning Neural Collapse Tail Class Natural Language Oriented Variant Incremental Training Shot Class

July 31, 2023

CBCL-PR: A Cognitively Inspired Model for Class-Incremental Learning in Robotics
Ali Ayub, Alan R. Wagner
Non Humanoid Robot Object Detection Robotics Domain Class Incremental Learning Robot Demonstration Inspired Model

July 21, 2023

XLDA: Linear Discriminant Analysis for Scaling Continual Learning to Extreme Classification at the Edge
Karan Shah, Vishruth Veerendranath, Anushka Hebbar, Raghavendra Bhat
Continual LEArning Class Incremental Learning Extreme Edge Discriminant Analysis Probabilistic Linear Discriminant Analysis Extreme Classification Linear Discriminant Analysis

July 5, 2023

June 30, 2023

Class-Incremental Learning using Diffusion Model for Distillation and Replay
Quentin Jodelet, Xin Liu, Yin Jun Phua, Tsuyoshi Murata
Diffusion Model Generative Model Supervised ImageNet Class Incremental Learning Mutual Distillation Stable Diffusion Model RePLAy Loss Incremental Model

Class Incremental Learning

Papers

Hadamard Domain Training with Integers for Class Incremental Quantized Learning

COOLer: Class-Incremental Learning for Appearance-Based Multiple Object Tracking

Class Incremental Learning via Likelihood Ratio Based Task Prediction

PILOT: A Pre-Trained Model-Based Continual Learning Toolbox

MultIOD: Rehearsal-free Multihead Incremental Object Detector

Class-Incremental Grouping Network for Continual Audio-Visual Learning

Image-Object-Specific Prompt Learning for Few-Shot Class-Incremental Learning

Dynamic Residual Classifier for Class Incremental Learning

Masked Autoencoders are Efficient Class Incremental Learners

An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning

NAPA-VQ: Neighborhood Aware Prototype Augmentation with Vector Quantization for Continual Learning

SATHUR: Self Augmenting Task Hallucinal Unified Representation for Generalized Class Incremental Learning

Heterogeneous Forgetting Compensation for Class-Incremental Learning

Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning

Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants

CBCL-PR: A Cognitively Inspired Model for Class-Incremental Learning in Robotics

XLDA: Linear Discriminant Analysis for Scaling Continual Learning to Extreme Classification at the Edge

Active Class Selection for Few-Shot Class-Incremental Learning

S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning

Class-Incremental Learning using Diffusion Model for Distillation and Replay