Shot Continual Learning

Shot continual learning (SCL) focuses on enabling artificial intelligence systems to learn new concepts from limited data ("few-shot") without forgetting previously acquired knowledge, a crucial aspect of lifelong learning. Current research emphasizes developing algorithms and model architectures that address the "catastrophic forgetting" problem, often employing techniques like prototype-based learning, meta-learning, and adaptive knowledge aggregation within various model types, including vision transformers and language models. This field is significant for advancing AI capabilities in resource-constrained environments and enabling more robust and adaptable systems across diverse applications such as robotics, remote sensing, and educational technology.

Papers

September 5, 2024

Few-Shot Continual Learning for Activity Recognition in Classroom Surveillance Images
Yilei Qian, Kanglei Geng, Kailong Chen, Shaoxu Cheng, Linfeng Xu, Hongliang Li, Fanman Meng, Qingbo Wu
Continual LEArning Continual Learning Activity Recognition Shot Continual Learning Student Classroom Behavior

June 4, 2024

Unsupervised Few-Shot Continual Learning for Remote Sensing Image Scene Classification
Muhammad Anwar Ma'sum, Mahardhika Pratama, Ramasamy Savitha, Lin Liu, Habibullah, Ryszard Kowalczyk
Continual LEArning Unsupervised Setting Hyperspectral Datasets Scene Datasets Remote Sensing Scene Classification Shot Continual Learning

April 22, 2024

Q-Tuning: Queue-based Prompt Tuning for Lifelong Few-shot Language Learning
Yanhui Guo, Shaoyuan Xu, Jinmiao Fu, Jia Liu, Chaosheng Dong, Bryan Wang
Shot Continual Learning P Tuning

April 9, 2024

Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers
Dipam Goswami, Bartłomiej Twardowski, Joost van de Weijer
Class Incremental Learning Pre Trained Vision Transformer Shot Class Shot Continual Learning Shot Data Order Statistic

March 30, 2024

Continual Learning for Autonomous Robots: A Prototype-based Approach
Elvin Hajizada, Balachandran Swaminathan, Yulia Sandamirskaya
Continual LEArning Autonomous Robot Prototype Based Prototype Selection Chip Learning Shot Continual Learning

November 7, 2023

Learning to Learn for Few-shot Continual Active Learning
Stella Ho, Ming Liu, Shang Gao, Longxiang Gao
LeArning Abstract Continual LEArning Continual Learning Shot Continual Learning Meta Continual Learning

September 2, 2023

Big-model Driven Few-shot Continual Learning
Ziqi Gu, Chunyan Xu, Zihan Lu, Xin Liu, Anbo Dai, Zhen Cui
Continual Learning Large Model Shot Continual Learning Shot Incremental

June 26, 2023

Few-Shot Continual Learning via Flat-to-Wide Approaches
Muhammad Anwar Ma'sum, Mahardhika Pratama, Edwin Lughofer, Lin Liu, Habibullah, Ryszard Kowalczyk
Continual LEArning Constructive Approach Catastrophic Forgetting Shot Continual Learning

July 14, 2022

In-memory Realization of In-situ Few-shot Continual Learning with a Dynamically Evolving Explicit Memory
Geethan Karunaratne, Michael Hersche, Jovin Langenegger, Giovanni Cherubini, Manuel Le Gallo-Bourdeau, Urs Egger, Kevin Brew, Sam Choi, INJO OK, Mary Claire Silvestre, Ning Li, Nicole Saulnier, Victor Chan, Ishtiaq Ahsan, Vijay Narayanan, Luca Benini, Abu Sebastian, Abbas Rahimi
Neural Network Continual LEArning Visual Memory Shot Continual Learning Compute in Memory Phase Change Memory Memory Evolution

July 10, 2022

Continual Few-Shot Learning with Adversarial Class Storage
Kun Wu, Chengxiang Yin, Jian Tang, Zhiyuan Xu, Yanzhi Wang, Dejun Yang
LeArning Abstract Shot Learning Catastrophic Forgetting Federat\textbf{T}ed Cl\textbf{A}ss Continual Lea\textbf{R}nin\textbf{G Meta Learning Framework Shot Continual Learning Meta Continual Learning

June 16, 2022

Lifelong Wandering: A realistic few-shot online continual learning setting
Mayank Lunayach, James Smith, Zsolt Kira
Shot Learning Catastrophic Forgetting Instance Level Shot Continual Learning Wandering Voice

May 4, 2022

Lifelong Ensemble Learning based on Multiple Representations for Few-Shot Object Recognition
Hamidreza Kasaei, Songsong Xiong
Object Recognition Multiple Representation Shot Continual Learning

February 17, 2022

Full-Span Log-Linear Model and Fast Learning Algorithm
Kazuya Takabatake, Shotaro Akaho
Efficient Learning Boltzmann Machine Shot Continual Learning