paper-with-me

홈 › Papers

Reviving Autoencoder Pretraining

2021-01-01 · You Xie, Nils Thuerey

The pressing need for pretraining algorithms has been diminished by numerous advances in terms of regularization, architectures, and optimizers. Despite this trend, we re-visit the classic idea of unsupervised autoencoder pretraining and propose a modified variant that relies on a full reverse pass trained in conjunction with a given training task. We establish links between SVD and pretraining and show how it can be leveraged for gaining insights about the learned structures. Most importantly, we demonstrate that our approach yields an improved performance for a wide variety of relevant learning and transfer tasks ranging from fully connected networks over ResNets to GANs. Our results demonstrate that unsupervised pretraining has not lost its practical relevance in today's deep learning environment.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Bootstrapped Masked Autoencoders for Vision BERT Pretraining

2022-07-14 · Xiaoyi Dong, Jianmin Bao, Ting Zhang, Dongdong Chen 외

We propose bootstrapped masked autoencoders (BootMAE), a new approach for vision BERT pretraining. BootMAE improves the original masked autoencoders (MAE) with two core designs: 1) momentum encoder that provides online f…

DecoderObject DetectionPredictionSelf-Supervised Image Classification+1

3D-MVP: 3D Multiview Pretraining for Manipulation

2025-01-01 · CVPR 2025 1 · Shengyi Qian, Kaichun Mo, Valts Blukis, David F. Fouhey 외

Recent works have shown that visual pretraining on egocentric datasets using masked autoencoders (MAE) can improve generalization for downstream robotics tasks. However, these approaches pretrain only on 2D images, w…

DecoderRobot ManipulationScene Understanding

3D-MVP: 3D Multiview Pretraining for Robotic Manipulation

2024-06-26 · Shengyi Qian, Kaichun Mo, Valts Blukis, David F. Fouhey 외

Recent works have shown that visual pretraining on egocentric datasets using masked autoencoders (MAE) can improve generalization for downstream robotics tasks. However, these approaches pretrain only on 2D images, while…

DecoderRobot ManipulationScene Understanding

Multi-pretrained Deep Neural Network

2016-06-02 · Zhen Hu, Zhuyin Xue, Tong Cui, Shiqiang Zong 외

Pretraining is widely used in deep neutral network and one of the most famous pretraining models is Deep Belief Network (DBN). The optimization formulas are different during the pretraining process for different pretrain…

Denoising

Reviving ConvNeXt for Efficient Convolutional Diffusion Models

2026-03-10 · Taesung Kwon, Lorenzo Bianchi, Lennart Wittke, Felix Watine 외 arxiv

Recent diffusion models increasingly favor Transformer backbones, motivated by the remarkable scalability of fully attentional architectures. Yet the locality bias, parameter efficiency, and hardware friendliness--the at…