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 6301–6325 of 6661 papers

TitleStatusHype
Contrastive learning for natural language-based vehicle retrievalCode0
Mining Better Samples for Contrastive Learning of Temporal Correspondence—0
Self-Supervised Video GANs: Learning for Appearance Consistency and Motion Coherency—0
Mol2Image: Improved Conditional Flow Models for Molecule to Image Synthesis—0
Exploring Heterogeneous Clues for Weakly-Supervised Audio-Visual Video Parsing—0
Spatio-temporal Contrastive Domain Adaptation for Action Recognition—0
Progressive Unsupervised Learning for Visual Object Tracking—0
Investigating the Role of Negatives in Contrastive Representation Learning—0
Novelty Detection via Contrastive Learning with Negative Data Augmentation—0
Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images—0
Long-Short Temporal Contrastive Learning of Video Transformers—0
Learning to Predict Visual Attributes in the Wild—0
Deep Contrastive Graph Representation via Adaptive Homotopy Learning—0
MaCLR: Motion-aware Contrastive Learning of Representations for VideosCode0
Watching Too Much Television is Good: Self-Supervised Audio-Visual Representation Learning from Movies and TV Shows—0
C^3: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues—0
Contrastive Learning of Natural Language and Code Representations for Semantic Code Search—0
Bilateral Personalized Dialogue Generation with Contrastive LearningCode0
Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-IdentificationCode0
Noise-robust Graph Learning by Estimating and Leveraging Pairwise InteractionsCode0
Learning Task-Relevant Representations with Selective Contrast for Reinforcement Learning in a Real-World Application—0
Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning—0
Contrastive Semi-Supervised Learning for 2D Medical Image Segmentation—0
A comprehensive solution to retrieval-based chatbot construction—0
Towards User-Driven Neural Machine TranslationCode0
Show:102550
← PrevPage 253 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