paper-with-me

Papers

Class-Incremental Learning with Strong Pre-trained Models

2022-04-07 · CVPR 2022 1 · Tz-Ying Wu, Gurumurthy Swaminathan, Zhizhong Li, Avinash Ravichandran, Nuno Vasconcelos, Rahul Bhotika, Stefano Soatto

Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes). Instead, we explore an understudied real-world setting of CIL that starts with a strong model pre-trained on a large number of base classes. We hypothesize that a strong base model can provide a good representation for novel classes and incremental learning can be done with small adaptations. We propose a 2-stage training scheme, i) feature augmentation -- cloning part of the backbone and fine-tuning it on the novel data, and ii) fusion -- combining the base and novel classifiers into a unified classifier. Experiments show that the proposed method significantly outperforms state-of-the-art CIL methods on the large-scale ImageNet dataset (e.g. +10% overall accuracy than the best). We also propose and analyze understudied practical CIL scenarios, such as base-novel overlap with distribution shift. Our proposed method is robust and generalizes to all analyzed CIL settings. Code is available at https://github.com/amazon-research/sp-cil.

📄 PDF Abstract BibTeX arXiv:2204.03634

Code (2)

amazon-research/sp-cil 공식 구현 pytorch
kitbransby/class-incremental-learning-echo pytorch

Tasks

class-incremental learningClass Incremental LearningIncremental Learning

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

On the Stability-Plasticity Dilemma of Class-Incremental Learning

2023-04-04 · CVPR 2023 1 · Dongwan Kim, Bohyung Han

A primary goal of class-incremental learning is to strike a balance between stability and plasticity, where models should be both stable enough to retain knowledge learned from previously seen classes, and plastic enough…

class-incremental learningClass Incremental LearningIncremental LearningRepresentation Learning

Incremental Learning with Differentiable Architecture and Forgetting Search

2022-05-19 · James Seale Smith, Zachary Seymour, Han-Pang Chiu

As progress is made on training machine learning models on incrementally expanding classification tasks (i.e., incremental learning), a next step is to translate this progress to industry expectations. One technique miss…

Classificationimage-classificationImage ClassificationIncremental Learning+1

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

2023-09-13 · Hai-Long Sun, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan

While traditional machine learning can effectively tackle a wide range of problems, it primarily operates within a closed-world setting, which presents limitations when dealing with streaming data. As a solution, increme…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning

Initial Classifier Weights Replay for Memoryless Class Incremental Learning

2020-08-31 · Eden Belouadah, Adrian Popescu, Ioannis Kanellos

Incremental Learning (IL) is useful when artificial systems need to deal with streams of data and do not have access to all data at all times. The most challenging setting requires a constant complexity of the deep model…

Allclass-incremental learningClass Incremental LearningFairness+2

Co-Transport for Class-Incremental Learning

2021-07-27 · Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan

Traditional learning systems are trained in closed-world for a fixed number of classes, and need pre-collected datasets in advance. However, new classes often emerge in real-world applications and should be learned incre…

class-incremental learningClass Incremental LearningIncremental Learning