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 5976–6000 of 6661 papers

TitleStatusHype
Simple Contrastive Representation Adversarial Learning for NLP Tasks—0
MIO : Mutual Information Optimization using Self-Supervised Binary Contrastive Learning—0
ViCE: Improving Dense Representation Learning by Superpixelization and Contrasting Cluster AssignmentCode0
S-SimCSE: Sampled Sub-networks for Contrastive Learning of Sentence Embedding—0
CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning—0
Exploring Feature Representation Learning for Semi-supervised Medical Image SegmentationCode0
Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition—0
Approximate Bayesian Computation via Classification—0
HoughCL: Finding Better Positive Pairs in Dense Self-supervised Learning—0
Decentralized Unsupervised Learning of Visual Representations—0
Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming—0
Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning—0
Combined Scaling for Zero-shot Transfer Learning—0
DeepQR: Neural-based Quality Ratings for Learnersourced Multiple-Choice Questions—0
CSI: Contrastive Data Stratification for Interaction Prediction and its Application to Compound-Protein Interaction Prediction—0
CLMB: deep contrastive learning for robust metagenomic binningCode0
Pedestrian Detection by Exemplar-Guided Contrastive Learning—0
Self-Supervised Contrastive Learning with Adversarial Perturbations for Robust Pretrained Language Models—0
Detect Low-Resource Rumors in Microblog Posts via Adversarial Contrastive Learning—0
Sentence-aware Contrastive Learning for Open-Domain Passage Retrieval—0
Pose Recognition in the Wild: Animal pose estimation using Agglomerative Clustering and Contrastive Learning—0
A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings—0
MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction—0
Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text—0
A Scalable Holistic approach for Age and Gender inference of Twitter Users—0
Show:102550
← PrevPage 240 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