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 5051–5075 of 6661 papers

TitleStatusHype
Graph Contrastive Learning with Generative Adversarial Network—0
Graph Contrastive Learning with Multi-Objective for Personalized Product Retrieval in Taobao Search—0
Graph Contrastive Learning with Personalized Augmentation—0
Graph Contrastive Pre-training for Effective Theorem Reasoning—0
Graph Embedding Dynamic Feature-based Supervised Contrastive Learning of Transient Stability for Changing Power Grid Topologies—0
Graph Information Bottleneck for Remote Sensing Segmentation—0
Graph-level Protein Representation Learning by Structure Knowledge Refinement—0
Graph Multi-Similarity Learning for Molecular Property Prediction—0
X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learning—0
Graph Neural Networks for UnsupervisedDomain Adaptation of Histopathological ImageAnalytics—0
Learning Graph Representation by Aggregating Subgraphs via Mutual Information Maximization—0
Graph Representation Learning via Contrasting Cluster Assignments—0
Graph Self-Contrast Representation Learning—0
Graph Soft-Contrastive Learning via Neighborhood Ranking—0
Graph Structure Refinement with Energy-based Contrastive Learning—0
GraphTTA: Test Time Adaptation on Graph Neural Networks—0
GraVIS: Grouping Augmented Views from Independent Sources for Dermatology Analysis—0
GRE^2-MDCL: Graph Representation Embedding Enhanced via Multidimensional Contrastive Learning—0
GRETEL: Graph Contrastive Topic Enhanced Language Model for Long Document Extractive Summarization—0
GroPrompt: Efficient Grounded Prompting and Adaptation for Referring Video Object Segmentation—0
Grounded Language Acquisition From Object and Action Imagery—0
Grounding is All You Need? Dual Temporal Grounding for Video Dialog—0
Group-based Distinctive Image Captioning with Memory Attention—0
Group-based Distinctive Image Captioning with Memory Difference Encoding and Attention—0
Group Contrastive Self-Supervised Learning on Graphs—0
Show:102550
← PrevPage 203 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