paper-with-me

Papers

Masked Autoencoders are Efficient Class Incremental Learners

2023-08-24 · ICCV 2023 1 · Jiang-Tian Zhai, Xialei Liu, Andrew D. Bagdanov, Ke Li, Ming-Ming Cheng

Class Incremental Learning (CIL) aims to sequentially learn new classes while avoiding catastrophic forgetting of previous knowledge. We propose to use Masked Autoencoders (MAEs) as efficient learners for CIL. MAEs were originally designed to learn useful representations through reconstructive unsupervised learning, and they can be easily integrated with a supervised loss for classification. Moreover, MAEs can reliably reconstruct original input images from randomly selected patches, which we use to store exemplars from past tasks more efficiently for CIL. We also propose a bilateral MAE framework to learn from image-level and embedding-level fusion, which produces better-quality reconstructed images and more stable representations. Our experiments confirm that our approach performs better than the state-of-the-art on CIFAR-100, ImageNet-Subset, and ImageNet-Full. The code is available at https://github.com/scok30/MAE-CIL .

📄 PDF Abstract BibTeX arXiv:2308.12510

Code (1)

scok30/mae-cil 공식 구현 pytorch

Tasks

class-incremental learningClass Incremental LearningIncremental Learning

Methods 이 논문이 사용한 방법론

MAE 설명 없음

Similar Papers 제목 키워드 기반

A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond

2022-07-30 · Chaoning Zhang, Chenshuang Zhang, Junha Song, John Seon Keun Yi 외

Masked autoencoders are scalable vision learners, as the title of MAE \cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, genera…

Contrastive LearningDenoisingSelf-Supervised Learning

Denoising Diffusion Autoencoders are Unified Self-supervised Learners

2023-03-17 · ICCV 2023 1 · Weilai Xiang, Hongyu Yang, Di Huang, Yunhong Wang

Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classification via generative pre-training. Thi…

Contrastive LearningDenoisingImage GenerationLinear evaluation+2

SupMAE: Supervised Masked Autoencoders Are Efficient Vision Learners

2022-05-28 · Feng Liang, Yangguang Li, Diana Marculescu

Recently, self-supervised Masked Autoencoders (MAE) have attracted unprecedented attention for their impressive representation learning ability. However, the pretext task, Masked Image Modeling (MIM), reconstructs the mi…

Representation LearningTransfer Learning

Masked Autoencoders as Image Processors

2023-03-30 · Huiyu Duan, Wei Shen, Xiongkuo Min, Danyang Tu 외

Transformers have shown significant effectiveness for various vision tasks including both high-level vision and low-level vision. Recently, masked autoencoders (MAE) for feature pre-training have further unleashed the po…

DeblurringDenoisingImage Defocus DeblurringImage Denoising+1

Masked Autoencoders are PDE Learners

2024-03-26 · Anthony Zhou, Amir Barati Farimani

Neural solvers for partial differential equations (PDEs) have great potential to generate fast and accurate physics solutions, yet their practicality is currently limited by their generalizability. PDEs evolve over broad…

Self-Supervised LearningSuper-Resolution