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 2851–2875 of 6661 papers

TitleStatusHype
Adaptive Multi-head Contrastive LearningCode0
Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift—0
Transferable Availability Poisoning AttacksCode0
Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text ClassificationCode1
SemST: Semantically Consistent Multi-Scale Image Translation via Structure-Texture Alignment—0
Boosting Facial Action Unit Detection Through Jointly Learning Facial Landmark Detection and Domain Separation and Reconstruction—0
Integrating Contrastive Learning into a Multitask Transformer Model for Effective Domain Adaptation—0
Unbiased and Robust: External Attention-enhanced Graph Contrastive Learning for Cross-domain Sequential RecommendationCode0
Towards Dynamic and Small Objects Refinement for Unsupervised Domain Adaptative Nighttime Semantic Segmentation—0
Degradation-Aware Self-Attention Based Transformer for Blind Image Super-ResolutionCode1
CUPre: Cross-domain Unsupervised Pre-training for Few-Shot Cell Segmentation—0
Perfect Alignment May be Poisonous to Graph Contrastive LearningCode0
Fragment-based Pretraining and Finetuning on Molecular GraphsCode1
Certifiably Robust Graph Contrastive LearningCode1
Diffusion Models as Masked Audio-Video Learners—0
Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor AttacksCode0
Deep Variational Multivariate Information Bottleneck -- A Framework for Variational Losses—0
Beyond Random Augmentations: Pretraining with Hard ViewsCode0
Cold-start Bundle Recommendation via Popularity-based Coalescence and Curriculum HeatingCode0
TPDR: A Novel Two-Step Transformer-based Product and Class Description Match and Retrieval Method—0
PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classification—0
Multimodal Prompt Transformer with Hybrid Contrastive Learning for Emotion Recognition in Conversation—0
Inclusive Data Representation in Federated Learning: A Novel Approach Integrating Textual and Visual Prompt—0
AstroCLIP: A Cross-Modal Foundation Model for GalaxiesCode1
Continual Contrastive Spoken Language Understanding—0
Show:102550
← PrevPage 115 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