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 4151–4175 of 6661 papers

TitleStatusHype
A Knowledge-based Learning Framework for Self-supervised Pre-training Towards Enhanced Recognition of Biomedical Microscopy ImagesCode0
SliceMatch: Geometry-guided Aggregation for Cross-View Pose EstimationCode1
Human-machine Interactive Tissue Prototype Learning for Label-efficient Histopathology Image SegmentationCode1
A Unified Framework for Contrastive Learning from a Perspective of Affinity Matrix—0
Unsupervised Wildfire Change Detection based on Contrastive LearningCode1
Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic SegmentationCode1
Towards Better Document-level Relation Extraction via Iterative InferenceCode0
Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head SynthesisCode1
Supervised Contrastive Prototype Learning: Augmentation Free Robust Neural Network—0
Link Prediction with Non-Contrastive LearningCode0
A Semi-supervised Learning Approach for B-line Detection in Lung Ultrasound Images—0
Global and Local Hierarchy-aware Contrastive Framework for Implicit Discourse Relation RecognitionCode1
Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene SegmentationCode0
Cross-domain Transfer of defect features in technical domains based on partial target data—0
Pose-disentangled Contrastive Learning for Self-supervised Facial RepresentationCode1
Graph Contrastive Learning for Materials—0
Learning with Partial Labels from Semi-supervised PerspectiveCode1
Contrastive pretraining for semantic segmentation is robust to noisy positive pairs—0
Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing AugmentationsCode1
Few-shot Object Detection with Refined Contrastive Learning—0
Self-supervised vision-language pretraining for Medical visual question answeringCode1
How do Cross-View and Cross-Modal Alignment Affect Representations in Contrastive Learning?—0
Contrastive Identity-Aware Learning for Multi-Agent Value DecompositionCode1
Robust Mean Teacher for Continual and Gradual Test-Time Adaptation—0
Texts as Images in Prompt Tuning for Multi-Label Image RecognitionCode1
Show:102550
← PrevPage 167 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