paper-with-me

Papers

AggSS: An Aggregated Self-Supervised Approach for Class-Incremental Learning

2024-08-08 · Jayateja Kalla, Soma Biswas

This paper investigates the impact of self-supervised learning, specifically image rotations, on various class-incremental learning paradigms. Here, each image with a predefined rotation is considered as a new class for training. At inference, all image rotation predictions are aggregated for the final prediction, a strategy we term Aggregated Self-Supervision (AggSS). We observe a shift in the deep neural network's attention towards intrinsic object features as it learns through AggSS strategy. This learning approach significantly enhances class-incremental learning by promoting robust feature learning. AggSS serves as a plug-and-play module that can be seamlessly incorporated into any class-incremental learning framework, leveraging its powerful feature learning capabilities to enhance performance across various class-incremental learning approaches. Extensive experiments conducted on standard incremental learning datasets CIFAR-100 and ImageNet-Subset demonstrate the significant role of AggSS in improving performance within these paradigms.

📄 PDF Abstract BibTeX arXiv:2408.04347

Code (0)

등록된 구현이 없습니다.

Tasks

class-incremental learningClass Incremental LearningIncremental LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Self-Supervised Class Incremental Learning

2021-11-18 · Zixuan Ni, Siliang Tang, Yueting Zhuang

Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the…

class-incremental learningClass Incremental LearningData AugmentationIncremental Learning+2

Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning

2022-05-09 · Na Dong, Yongqiang Zhang, Mingli Ding, Gim Hee Lee

Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes. Most related prior works are on increme…

Few-Shot Object DetectionKnowledge DistillationObjectobject-detection+2

Curvature-aided Incremental Aggregated Gradient Method

2017-10-24 · Hoi-To Wai, Wei Shi, Angelia Nedic, Anna Scaglione

We propose a new algorithm for finite sum optimization which we call the curvature-aided incremental aggregated gradient (CIAG) method. Motivated by the problem of training a classifier for a d-dimensional problem, where…

Fast Incremental Method for Nonconvex Optimization

2016-03-19 · Sashank J. Reddi, Suvrit Sra, Barnabas Poczos, Alex Smola

We analyze a fast incremental aggregated gradient method for optimizing nonconvex problems of the form $\min_x \sum_i f_i(x)$. Specifically, we analyze the SAGA algorithm within an Incremental First-order Oracle framewor…

Self-Supervised Training Enhances Online Continual Learning

2021-03-25 · Jhair Gallardo, Tyler L. Hayes, Christopher Kanan

In continual learning, a system must incrementally learn from a non-stationary data stream without catastrophic forgetting. Recently, multiple methods have been devised for incrementally learning classes on large-scale i…

Continual Learningimage-classificationImage Classification