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 5301–5325 of 6661 papers

TitleStatusHype
Focus-Driven Contrastive Learning for Medical Question Summarization—0
Contrastive Corpus Attribution for Explaining RepresentationsCode0
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training—0
Slimmable Networks for Contrastive Self-supervised LearningCode0
Contrastive Graph Few-Shot Learning—0
Prompt-guided Scene Generation for 3D Zero-Shot Learning—0
REST: REtrieve & Self-Train for generative action recognition—0
Few-shot Text Classification with Dual Contrastive Consistency—0
Graph Soft-Contrastive Learning via Neighborhood Ranking—0
Learning Deep Representations via Contrastive Learning for Instance Retrieval—0
Weighted Contrastive HashingCode0
Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval—0
Efficient block contrastive learning via parameter-free meta-node approximationCode0
Supervised Contrastive Learning as Multi-Objective Optimization for Fine-Tuning Large Pre-trained Language Models—0
RepsNet: Combining Vision with Language for Automated Medical Reports—0
Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited LabelsCode0
Regularized Contrastive Learning of Semantic Search—0
End-to-End Lyrics Recognition with Self-supervised Learning—0
Contrastive learning for unsupervised medical image clustering and reconstruction—0
Self-supervised Image Clustering from Multiple Incomplete Views via Constrastive Complementary Generation—0
View-Invariant Skeleton-based Action Recognition via Global-Local Contrastive Learning—0
Whodunit? Learning to Contrast for Authorship AttributionCode0
SR-GCL: Session-Based Recommendation with Global Context Enhanced Augmentation in Contrastive Learning—0
An Information Minimization Based Contrastive Learning Model for Unsupervised Sentence Embeddings LearningCode0
AVT: Audio-Video Transformer for Multimodal Action Recognition—0
Show:102550
← PrevPage 213 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