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 5001–5025 of 6661 papers

TitleStatusHype
NYCU_TWD@LT-EDI-ACL2022: Ensemble Models with VADER and Contrastive Learning for Detecting Signs of Depression from Social Media—0
RoCBert: Robust Chinese Bert with Multimodal Contrastive Pretraining—0
Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense InferenceCode1
UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog—0
Unsupervised Contrastive Learning based Transformer for Lung Nodule Detection—0
Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning—0
Probing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders—0
Loss Function Entropy Regularization for Diverse Decision Boundaries—0
On Negative Sampling for Audio-Visual Contrastive Learning from Movies—0
Vision-Language Pre-Training for Boosting Scene Text DetectorsCode0
CLIP-Art: Contrastive Pre-training for Fine-Grained Art ClassificationCode2
RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive LearningCode1
SCS-Co: Self-Consistent Style Contrastive Learning for Image HarmonizationCode1
Statistical applications of contrastive learning—0
A Probabilistic Interpretation of Transformers—0
Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype ContrastCode1
Reducing Predictive Feature Suppression in Resource-Constrained Contrastive Image-Caption RetrievalCode0
Self-supervised Contrastive Learning for Audio-Visual Action Recognition—0
ELM: Embedding and Logit Margins for Long-Tail Learning—0
Use All The Labels: A Hierarchical Multi-Label Contrastive Learning FrameworkCode1
Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training—0
Supervised Contrastive CSI Representation Learning for Massive MIMO PositioningCode0
Label Anchored Contrastive Learning for Language Understanding—0
Self-Supervised Contrastive Learning for Singing VoicesCode1
A Review-aware Graph Contrastive Learning Framework for RecommendationCode1
Show:102550
← PrevPage 201 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