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 6526–6550 of 6661 papers

TitleStatusHype
Speech4Mesh: Speech-Assisted Monocular 3D Facial Reconstruction for Speech-Driven 3D Facial Animation—0
Speech Separation based on Contrastive Learning and Deep Modularization—0
Speech Sequence Embeddings using Nearest Neighbors Contrastive Learning—0
Speed Co-Augmentation for Unsupervised Audio-Visual Pre-training—0
Speed-enhanced Subdomain Adaptation Regression for Long-term Stable Neural Decoding in Brain-computer Interfaces—0
SpeGCL: Self-supervised Graph Spectrum Contrastive Learning without Positive Samples—0
SPF-Portrait: Towards Pure Portrait Customization with Semantic Pollution-Free Fine-tuning—0
SpineCLUE: Automatic Vertebrae Identification Using Contrastive Learning and Uncertainty Estimation—0
Spiral Contrastive Learning: An Efficient 3D Representation Learning Method for Unannotated CT Lesions—0
SPKLIP: Aligning Spike Video Streams with Natural Language—0
Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions—0
SpotFormer: Multi-Scale Spatio-Temporal Transformer for Facial Expression Spotting—0
SR-GCL: Session-Based Recommendation with Global Context Enhanced Augmentation in Contrastive Learning—0
SSAVSV: Towards Unified Model for Self-Supervised Audio-Visual Speaker Verification—0
S-SimCSE: Sampled Sub-networks for Contrastive Learning of Sentence Embedding—0
SSTN: Self-Supervised Domain Adaptation Thermal Object Detection for Autonomous Driving—0
Robust Stance Detection: Understanding Public Perceptions in Social Media—0
STaRFormer: Semi-Supervised Task-Informed Representation Learning via Dynamic Attention-Based Regional Masking for Sequential Data—0
STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing—0
Start from Video-Music Retrieval: An Inter-Intra Modal Loss for Cross Modal Retrieval—0
Static-Dynamic Class-level Perception Consistency in Video Semantic Segmentation—0
Static Word Embeddings for Sentence Semantic Representation—0
Statistical applications of contrastive learning—0
Statistical Dependency Guided Contrastive Learning for Multiple Labeling in Prenatal Ultrasound—0
Staying in Shape: Learning Invariant Shape Representations using Contrastive Learning—0
Show:102550
← PrevPage 262 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