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 2551–2575 of 6661 papers

TitleStatusHype
Text-Guided Face Recognition using Multi-Granularity Cross-Modal Contrastive Learning—0
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks—0
CLIP-guided Federated Learning on Heterogeneous and Long-Tailed DataCode1
Incomplete Contrastive Multi-View Clustering with High-Confidence GuidingCode0
ReCoRe: Regularized Contrastive Representation Learning of World Model—0
TiMix: Text-aware Image Mixing for Effective Vision-Language Pre-trainingCode0
Revisiting Recommendation Loss Functions through Contrastive Learning (Technical Report)—0
(Debiased) Contrastive Learning Loss for Recommendation (Technical Report)—0
Patch-wise Graph Contrastive Learning for Image TranslationCode1
CoRTEx: Contrastive Learning for Representing Terms via Explanations with Applications on Constructing Biomedical Knowledge GraphsCode0
FoundationPose: Unified 6D Pose Estimation and Tracking of Novel ObjectsCode4
Partial Symmetry Detection for 3D Geometry using Contrastive Learning with Geodesic Point Cloud Patches—0
Watchog: A Light-weight Contrastive Learning based Framework for Column Annotation—0
Domain Prompt Learning with Quaternion Networks—0
Toward Real Text Manipulation Detection: New Dataset and New SolutionCode1
Supervised Contrastive Learning for Fine-grained Chromosome Recognition—0
EdgePruner: Poisoned Edge Pruning in Graph Contrastive Learning—0
Transformer-based No-Reference Image Quality Assessment via Supervised Contrastive LearningCode1
CLASS-M: Adaptive stain separation-based contrastive learning with pseudo-labeling for histopathological image classificationCode0
Hallucination Augmented Contrastive Learning for Multimodal Large Language ModelCode1
Cross-modal Contrastive Learning with Asymmetric Co-attention Network for Video Moment RetrievalCode0
NearbyPatchCL: Leveraging Nearby Patches for Self-Supervised Patch-Level Multi-Class Classification in Whole-Slide ImagesCode0
Contrastive News and Social Media Linking using BERT for Articles and Tweets across Dual Platforms—0
Mining Gaze for Contrastive Learning toward Computer-Assisted DiagnosisCode1
Contrastive Multi-view Subspace Clustering of Hyperspectral Images based on Graph Convolutional Networks—0
Show:102550
← PrevPage 103 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