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 3126–3150 of 6661 papers

TitleStatusHype
Colorectal Polyp Classification from White-light Colonoscopy Images via Domain Alignment—0
A Unified Contrastive Transfer Framework with Propagation Structure for Boosting Low-Resource Rumor Detection—0
Dual Contrastive Transformer for Hierarchical Preference Modeling in Sequential Recommendation—0
ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition—0
CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders—0
Dual Contrastive Learning for Spatio-temporal Representation—0
Dual Contrastive Learning for General Face Forgery Detection—0
CoLLAP: Contrastive Long-form Language-Audio Pretraining with Musical Temporal Structure Augmentation—0
Collaborative Visual Place Recognition through Federated Learning—0
Dual Circle Contrastive Learning-Based Blind Image Super-Resolution—0
Dual-Channel Latent Factor Analysis Enhanced Graph Contrastive Learning for Recommendation—0
Dual Adversarial Perturbators Generate rich Views for Recommendation—0
DSS: Synthesizing long Digital Ink using Data augmentation, Style encoding and Split generation—0
Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection—0
Collaborative Contrastive Network for Click-Through Rate Prediction—0
A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training—0
Alignment and Outer Shell Isotropy for Hyperbolic Graph Contrastive Learning—0
DrugCLIP: Contrastive Drug-Disease Interaction For Drug Repurposing—0
CROCS: Clustering and Retrieval of Cardiac Signals Based on Patient Disease Class, Sex, and Age—0
DROPS: Deep Retrieval of Physiological Signals via Attribute-specific Clinical Prototypes—0
DRK: Discriminative Rule-based Knowledge for Relieving Prediction Confusions in Few-shot Relation Extraction—0
CoKe: Localized Contrastive Learning for Robust Keypoint Detection—0
A Unified and Efficient Contrastive Learning Framework for Text Summarization—0
DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction—0
Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction—0
Show:102550
← PrevPage 126 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