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 2451–2475 of 6661 papers

TitleStatusHype
Encoding Binary Events from Continuous Time Series in Rooted Trees using Contrastive Learning—0
Weakly-Supervised Audio-Visual Video Parsing with Prototype-based Pseudo-Labeling—0
MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning—0
CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning—0
Self-Supervised Representation Learning from Arbitrary Scenarios—0
PH-Net: Semi-Supervised Breast Lesion Segmentation via Patch-wise HardnessCode1
PeVL: Pose-Enhanced Vision-Language Model for Fine-Grained Human Action Recognition—0
Prompt-Driven Referring Image Segmentation with Instance Contrasting—0
Instance-aware Contrastive Learning for Occluded Human Mesh ReconstructionCode1
Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-IdentificationCode1
Building Vision-Language Models on Solid Foundations with Masked Distillation—0
Positive-Unlabeled Learning by Latent Group-Aware Meta DisambiguationCode1
Revisiting Counterfactual Problems in Referring Expression ComprehensionCode0
An Asymmetric Augmented Self-Supervised Learning Method for Unsupervised Fine-Grained Image Hashing—0
Fair-VPT: Fair Visual Prompt Tuning for Image Classification—0
Improving Graph Contrastive Learning via Adaptive Positive Sampling—0
Density-Guided Semi-Supervised 3D Semantic Segmentation with Dual-Space Hardness Sampling—0
Weakly Supervised Video Individual CountingCode1
Data Poisoning based Backdoor Attacks to Contrastive LearningCode1
Looking Similar Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning—0
Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning—0
Contrastive Learning for DeepFake Classification and Localization via Multi-Label Ranking—0
Enhancing Post-training Quantization Calibration through Contrastive Learning—0
Contextual Augmented Global Contrast for Multimodal Intent Recognition—0
Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion—0
Show:102550
← PrevPage 99 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