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 3976–4000 of 6661 papers

TitleStatusHype
MN-Pair Contrastive Damage Representation and Clustering for Prognostic Explanation—0
Exploiting Auxiliary Caption for Video Grounding—0
FedSSC: Shared Supervised-Contrastive Federated Learning—0
Knowledge Enhancement for Contrastive Multi-Behavior Recommendation—0
RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image SegmentationCode1
Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss—0
Pylon: Semantic Table Union Search in Data LakesCode0
Learning to Summarize Videos by Contrasting Clips—0
SemPPL: Predicting pseudo-labels for better contrastive representationsCode1
CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPCode1
Signed Directed Graph Contrastive Learning with Laplacian Augmentation—0
Unsupervised Driving Event Discovery Based on Vehicle CAN-data—0
Anomalies, Representations, and Self-Supervision—0
Generative-Contrastive Learning for Self-Supervised Latent Representations of 3D Shapes from Multi-Modal Euclidean Input—0
Clustering disease trajectories in contrastive feature space for biomarker discovery in age-related macular degeneration—0
Heterogeneous Tri-stream Clustering NetworkCode0
GraVIS: Grouping Augmented Views from Independent Sources for Dermatology Analysis—0
From Plate to Prevention: A Dietary Nutrient-aided Platform for Health Promotion in Singapore—0
Metric Compatible Training for Online Backfilling in Large-Scale Retrieval—0
CDA: Contrastive-adversarial Domain Adaptation—0
CLASH: Contrastive learning through alignment shifting to extract stimulus information from EEG—0
Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked ModelingCode3
Simplifying Open-Set Video Domain Adaptation with Contrastive LearningCode0
Nearest Neighbor-Based Contrastive Learning for Hyperspectral and LiDAR Data ClassificationCode1
Mitigating Human and Computer Opinion Fraud via Contrastive Learning—0
Show:102550
← PrevPage 160 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