SOTAVerified

Contrastive Learning

Contrastive Learning is a deep learning technique for unsupervised representation learning. The goal is to learn a representation of data such that similar instances are close together in the representation space, while dissimilar instances are far apart.

It has been shown to be effective in various computer vision and natural language processing tasks, including image retrieval, zero-shot learning, and cross-modal retrieval. In these tasks, the learned representations can be used as features for downstream tasks such as classification and clustering.

(Image credit: Schroff et al. 2015)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 6326–6350 of 6661 papers

TitleStatusHype
Fast Training of Contrastive Learning with Intermediate Contrastive Loss—0
Enabling Efficient On-Device Self-supervised Contrastive Learning by Data Selection—0
Auto-view contrastive learning for few-shot image recognition—0
Towards Robust Textual Representations with Disentangled Contrastive Learning—0
Towards Robust and Efficient Contrastive Textual Representation Learning—0
Learning Representations by Contrasting Clusters While Bootstrapping Instances—0
Self-supervised representation learning via adaptive hard-positive mining—0
Contrastive Video Textures—0
Exploring Balanced Feature Spaces for Representation Learning—0
A Flexible Framework for Discovering Novel Categories with Contrastive Learning—0
Improving Generalizability of Protein Sequence Models via Data Augmentations—0
Provable Rich Observation Reinforcement Learning with Combinatorial Latent States—0
Momentum Contrastive Autoencoder—0
On Self-Supervised Image Representations for GAN Evaluation—0
Unsupervised Active Pre-Training for Reinforcement Learning—0
Impact-driven Exploration with Contrastive Unsupervised Representations—0
Unsupervised Word Alignment via Cross-Lingual Contrastive LearningCode0
Novelty Detection with Rotated Contrastive Predictive Coding—0
CLEAR: Contrastive Learning for Sentence Representation—0
UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive LearningCode0
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive LearningCode1
COIN: Contrastive Identifier Network for Breast Mass Diagnosis in Mammography—0
CMV-BERT: Contrastive multi-vocab pretraining of BERT—0
Domain Generalisation with Domain Augmented Supervised Contrastive Learning (Student Abstract)—0
ANL: Anti-Noise Learning for Cross-Domain Person Re-Identification—0
Show:102550
← PrevPage 254 of 267Next →
All datasetsimagenet-1k10,000 People - Human Pose Recognition DataCIFAR-10STL-10

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6—Unverified
2ResNet50ImageNet Top-1 Accuracy73—Unverified
3ResNet50ImageNet Top-1 Accuracy71.1—Unverified
4ResNet50ImageNet Top-1 Accuracy69.3—Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6—Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8—Unverified
7ResNet50ImageNet Top-1 Accuracy63.6—Unverified
8ResNet50ImageNet Top-1 Accuracy61.5—Unverified
9ResNet50ImageNet Top-1 Accuracy61.5—Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3—Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1—Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77—Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55—Unverified