paper-with-me

홈 › Papers

Momentum Contrastive Autoencoder

2021-01-01 · Devansh Arpit, Aadyot Bhatnagar, Huan Wang, Caiming Xiong

Wasserstein autoencoder (WAE) shows that matching two distributions is equivalent to minimizing a simple autoencoder (AE) loss under the constraint that the latent space of this AE matches a pre-specified prior distribution. This latent space distribution matching is a core component in WAE, and is in itself a challenging task. In this paper, we propose to use the contrastive learning framework that has been shown to be effective for self-supervised representation learning, as a means to resolve this problem. We do so by exploiting the fact that contrastive learning objectives optimize the latent space distribution to be uniform over the unit hyper-sphere, which can be easily sampled from. This results in a simple and scalable algorithm that avoids many of the optimization challenges of existing generative models, while retaining the advantage of efficient sampling. Quantitatively, we show that our algorithm achieves a new state-of-the-art FID of 54.36 on CIFAR-10, and performs competitively with existing models on CelebA in terms of FID score. We also show qualitative results on CelebA-HQ in addition to these datasets, confirming that our algorithm can generate realistic images at multiple resolutions.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
Solana Customer Service Number +1-833-534-1729 설명 없음
AE An autoencoder is a type of artificial neural network used to learn efficient data codings in an unsupervised manner. The aim of an autoencoder is to learn a representation…

Similar Papers 제목 키워드 기반

Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE

2021-10-19 · Devansh Arpit, Aadyot Bhatnagar, Huan Wang, Caiming Xiong

Wasserstein autoencoder (WAE) shows that matching two distributions is equivalent to minimizing a simple autoencoder (AE) loss under the constraint that the latent space of this AE matches a pre-specified prior distribut…

Contrastive LearningRepresentation Learning

Contrastive Masked Autoencoders are Stronger Vision Learners

2022-07-27 · Zhicheng Huang, Xiaojie Jin, Chengze Lu, Qibin Hou 외

Masked image modeling (MIM) has achieved promising results on various vision tasks. However, the limited discriminability of learned representation manifests there is still plenty to go for making a stronger vision learn…

Contrastive LearningDecoderimage-classificationImage Classification+3

Masked Contrastive Representation Learning

2022-11-11 · Yuchong Yao, Nandakishor Desai, Marimuthu Palaniswami

Masked image modelling (e.g., Masked AutoEncoder) and contrastive learning (e.g., Momentum Contrast) have shown impressive performance on unsupervised visual representation learning. This work presents Masked Contrastive…

Contrastive LearningData AugmentationDecoderRepresentation Learning

Rethinking Graph Masked Autoencoders through Alignment and Uniformity

2024-02-11 · Xiang Tao, Qiang Liu, Shu Wu, Liang Wang

Self-supervised learning on graphs can be bifurcated into contrastive and generative methods. Contrastive methods, also known as graph contrastive learning (GCL), have dominated graph self-supervised learning in the past…

Contrastive LearningSelf-Supervised Learning

mcBERT: Momentum Contrastive Learning with BERT for Zero-Shot Slot Filling

2022-03-24 · Seong-Hwan Heo, WonKee Lee, Jong-Hyeok Lee

Zero-shot slot filling has received considerable attention to cope with the problem of limited available data for the target domain. One of the important factors in zero-shot learning is to make the model learn generaliz…

Contrastive Learningslot-fillingSlot FillingZero-Shot Learning+1