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 401–425 of 6661 papers

TitleStatusHype
DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies—0
FusDreamer: Label-efficient Remote Sensing World Model for Multimodal Data ClassificationCode1
Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment—0
A Survey on Self-supervised Contrastive Learning for Multimodal Text-Image Analysis—0
Variational Bayesian Personalized RankingCode1
Unicorn: A Universal and Collaborative Reinforcement Learning Approach Towards Generalizable Network-Wide Traffic Signal Control—0
LuSeg: Efficient Negative and Positive Obstacles Segmentation via Contrast-Driven Multi-Modal Feature Fusion on the LunarCode1
OuroMamba: A Data-Free Quantization Framework for Vision Mamba Models—0
RankPO: Preference Optimization for Job-Talent MatchingCode0
Technical Approach for the EMI Challenge in the 8th Affective Behavior Analysis in-the-Wild Competition—0
Hierarchical Self-Supervised Adversarial Training for Robust Vision Models in HistopathologyCode1
SOLA-GCL: Subgraph-Oriented Learnable Augmentation Method for Graph Contrastive Learning—0
TacticExpert: Spatial-Temporal Graph Language Model for Basketball Tactics—0
Bilingual Dual-Head Deep Model for Parkinson's Disease Detection from SpeechCode0
Enhance Exploration in Safe Reinforcement Learning with Contrastive Representation Learning—0
A Siamese Network to Detect If Two Iris Images Are Monozygotic—0
Domain Adaptation for Japanese Sentence Embeddings with Contrastive Learning based on Synthetic Sentence GenerationCode0
Diff-CL: A Novel Cross Pseudo-Supervision Method for Semi-supervised Medical Image Segmentation—0
Astrea: A MOE-based Visual Understanding Model with Progressive Alignment—0
Towards Robust Multimodal Representation: A Unified Approach with Adaptive Experts and AlignmentCode0
Decoupled Doubly Contrastive Learning for Cross Domain Facial Action Unit Detection—0
Patch-Wise Hypergraph Contrastive Learning with Dual Normal Distribution Weighting for Multi-Domain Stain Transfer—0
Robust Asymmetric Heterogeneous Federated Learning with Corrupted ClientsCode0
Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model—0
Incomplete Multi-view Clustering via Diffusion Contrastive Generation—0
Show:102550
← PrevPage 17 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