paper-with-me

홈 › Papers

AAG: Self-Supervised Representation Learning by Auxiliary Augmentation with GNT-Xent Loss

2020-09-17 · Yanlun Tu, Jianxing Feng, Yang Yang

Self-supervised representation learning is an emerging research topic for its powerful capacity in learning with unlabeled data. As a mainstream self-supervised learning method, augmentation-based contrastive learning has achieved great success in various computer vision tasks that lack manual annotations. Despite current progress, the existing methods are often limited by extra cost on memory or storage, and their performance still has large room for improvement. Here we present a self-supervised representation learning method, namely AAG, which is featured by an auxiliary augmentation strategy and GNT-Xent loss. The auxiliary augmentation is able to promote the performance of contrastive learning by increasing the diversity of images. The proposed GNT-Xent loss enables a steady and fast training process and yields competitive accuracy. Experiment results demonstrate the superiority of AAG to previous state-of-the-art methods on CIFAR10, CIFAR100, and SVHN. Especially, AAG achieves 94.5% top-1 accuracy on CIFAR10 with batch size 64, which is 0.5% higher than the best result of SimCLR with batch size 1024.

📄 PDF Abstract BibTeX arXiv:2009.07994

Code (3)

MindCode-4/code-14/tree/main/AVA_cifar mindspore
MindSpore-paper-code-3/code1/tree/main/AVA_cifar mindspore
mindspore-ai/models/tree/master/research/cv/AVA_cifar mindspore

Tasks

Contrastive LearningDiversityRepresentation LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Kaiming Initialization 설명 없음
Average Pooling 설명 없음
Batch Normalization 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
ColorJitter 설명 없음

Similar Papers 제목 키워드 기반

Self-Guided Contrastive Learning for BERT Sentence Representations

2021-06-03 · ACL 2021 5 · Taeuk Kim, Kang Min Yoo, Sang-goo Lee

Although BERT and its variants have reshaped the NLP landscape, it still remains unclear how best to derive sentence embeddings from such pre-trained Transformers. In this work, we propose a contrastive learning method t…

Contrastive LearningData AugmentationRepresentation LearningSentence+1

The NT-Xent loss upper bound

2022-05-06 · Wilhelm Ågren

Self-supervised learning is a growing paradigm in deep representation learning, showing great generalization capabilities and competitive performance in low-labeled data regimes. The SimCLR framework proposes the NT-Xent…

Representation LearningSelf-Supervised Learning

G-SimCLR: Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling

2020-09-28 · Souradip Chakraborty, Aritra Roy Gosthipaty, Sayak Paul

In the realms of computer vision, it is evident that deep neural networks perform better in a supervised setting with a large amount of labeled data. The representations learned with supervision are not only of high qual…

Contrastive LearningDenoisingRepresentation LearningSelf-Supervised Learning

G-SimCLR : Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling

2020-09-25 · Souradip Chakraborty, Aritra Roy Gosthipaty, Sayak Paul

In the realms of computer vision, it is evident that deep neural networks perform better in a supervised setting with a large amount of labeled data. The representations learned with supervision are not only of high qual…

Contrastive LearningDenoisingRepresentation Learning

Improving Transferability of Representations via Augmentation-Aware Self-Supervision

2021-11-18 · NeurIPS 2021 12 · Hankook Lee, Kibok Lee, Kimin Lee, Honglak Lee 외

Recent unsupervised representation learning methods have shown to be effective in a range of vision tasks by learning representations invariant to data augmentations such as random cropping and color jittering. However, …

Representation LearningTransfer Learning