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 801–825 of 6661 papers

TitleStatusHype
CLDA-YOLO: Visual Contrastive Learning Based Domain Adaptive YOLO Detector—0
Leveraging Retrieval-Augmented Tags for Large Vision-Language Understanding in Complex Scenes—0
Future Sight and Tough Fights: Revolutionizing Sequential Recommendation with FENRecCode0
Gramian Multimodal Representation Learning and AlignmentCode2
Exploring Temporal Event Cues for Dense Video Captioning in Cyclic Co-learning—0
Temporal Contrastive Learning for Video Temporal Reasoning in Large Vision-Language Models—0
UniLoc: Towards Universal Place Recognition Using Any Single Modality—0
Multi-Graph Co-Training for Capturing User Intent in Session-based RecommendationCode0
Segment-Level Diffusion: A Framework for Controllable Long-Form Generation with Diffusion Language Models—0
Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning ModelCode0
RAC3: Retrieval-Augmented Corner Case Comprehension for Autonomous Driving with Vision-Language Models—0
CATALOG: A Camera Trap Language-guided Contrastive Learning ModelCode0
ExeChecker: Where Did I Go Wrong?Code0
MulSMo: Multimodal Stylized Motion Generation by Bidirectional Control Flow—0
TrafficLoc: Localizing Traffic Surveillance Cameras in 3D Scenes—0
Label-template based Few-Shot Text Classification with Contrastive Learning—0
A dual contrastive framework—0
UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging ModalitiesCode2
Single-View Graph Contrastive Learning with Soft Neighborhood AwarenessCode0
DomCLP: Domain-wise Contrastive Learning with Prototype Mixup for Unsupervised Domain GeneralizationCode0
Dynamic Contrastive Knowledge Distillation for Efficient Image RestorationCode1
USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature DecorrelationCode1
Residual Channel Boosts Contrastive Learning for Radio Frequency Fingerprint Identification—0
Multi-level Matching Network for Multimodal Entity LinkingCode0
jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images—0
Show:102550
← PrevPage 33 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