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

Showing 9761000 of 6661 papers

TitleStatusHype
Contrastive Viewpoint-aware Shape Learning for Long-term Person Re-IdentificationCode1
CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent MaskingCode1
COCOA: Cross Modality Contrastive Learning for Sensor DataCode1
CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive LearningCode1
Contrast-Phys+: Unsupervised and Weakly-supervised Video-based Remote Physiological Measurement via Spatiotemporal ContrastCode1
COCO-LM: Correcting and Contrasting Text Sequences for Language Model PretrainingCode1
CoCon: Cooperative-Contrastive LearningCode1
CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image FusionCode1
CoCoNets: Continuous Contrastive 3D Scene RepresentationsCode1
Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic SegmentationCode1
Learning 3D Representations of Molecular Chirality with Invariance to Bond RotationsCode1
Replication: Contrastive Learning and Data Augmentation in Traffic Classification Using a Flowpic Input RepresentationCode1
Active Contrastive Learning of Audio-Visual Video RepresentationsCode1
Convolutional Cross-View Pose EstimationCode1
Learning Better Contrastive View from Radiologist's GazeCode1
Aligning Language Models with Human Preferences via a Bayesian ApproachCode1
Learning Efficient Coding of Natural Images with Maximum Manifold Capacity RepresentationsCode1
Augmentations in Hypergraph Contrastive Learning: Fabricated and GenerativeCode1
CODER: Knowledge infused cross-lingual medical term embedding for term normalizationCode1
Community-Invariant Graph Contrastive LearningCode1
Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch MiningCode1
Augmented Dual-Contrastive Aggregation Learning for Unsupervised Visible-Infrared Person Re-IdentificationCode1
Learning From Noisy Data With Robust Representation LearningCode1
Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action RecognitionCode1
A Message Passing Perspective on Learning Dynamics of Contrastive LearningCode1
Show:102550
← PrevPage 40 of 267Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6Unverified
2ResNet50ImageNet Top-1 Accuracy73Unverified
3ResNet50ImageNet Top-1 Accuracy71.1Unverified
4ResNet50ImageNet Top-1 Accuracy69.3Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8Unverified
7ResNet50ImageNet Top-1 Accuracy63.6Unverified
8ResNet50ImageNet Top-1 Accuracy61.5Unverified
9ResNet50ImageNet Top-1 Accuracy61.5Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55Unverified