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 5201–5250 of 6661 papers

TitleStatusHype
Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and ClusteringCode1
Bures Joint Distribution Alignment with Dynamic Margin for Unsupervised Domain Adaptation—0
Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based LearningCode1
Cross-View-Prediction: Exploring Contrastive Feature for Hyperspectral Image Classification—0
S5CL: Unifying Fully-Supervised, Self-Supervised, and Semi-Supervised Learning Through Hierarchical Contrastive LearningCode1
Rethinking Minimal Sufficient Representation in Contrastive LearningCode1
ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation—0
WCL-BBCD: A Contrastive Learning and Knowledge Graph Approach to Named Entity Recognition—0
Contrastive Learning for Automotive mmWave Radar Detection Points Based Instance Segmentation—0
Neuromorphic Data Augmentation for Training Spiking Neural NetworksCode1
LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text RetrievalCode1
A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence EmbeddingsCode1
Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object DetectionCode1
Protein Representation Learning by Geometric Structure PretrainingCode2
MetAug: Contrastive Learning via Meta Feature AugmentationCode1
Domain Generalization via Shuffled Style Assembly for Face Anti-SpoofingCode1
3SD: Self-Supervised Saliency Detection With No LabelsCode0
Multi-modal Brain Tumor Segmentation via Missing Modality Synthesis and Modality-level Attention Fusion—0
What Matters For Meta-Learning Vision Regression Tasks?Code1
Mutual Contrastive Low-rank Learning to Disentangle Whole Slide Image Representations for Glioma Grading—0
Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text ClassificationCode1
UniXcoder: Unified Cross-Modal Pre-training for Code RepresentationCode1
Predicting conversion of mild cognitive impairment to Alzheimer's disease—0
Contrastive Conditional Neural Processes—0
Selective-Supervised Contrastive Learning with Noisy LabelsCode1
Multi-Scale Self-Contrastive Learning with Hard Negative Mining for Weakly-Supervised Query-based Video Grounding—0
Unsupervised Domain Adaptation with Contrastive Learning for OCT Segmentation—0
Comparing representations of biological data learned with different AI paradigms, augmenting and cropping strategiesCode0
Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networksCode1
Learning to Ground Decentralized Multi-Agent Communication with Contrastive Learning—0
Cluster-based Contrastive Disentangling for Generalized Zero-Shot Learning—0
Consistent Representation Learning for Continual Relation ExtractionCode1
SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language ModelsCode2
Contrastive Graph Convolutional Networks for Hardware Trojan Detection in Third Party IP Cores—0
MixCL: Pixel label matters to contrastive learning—0
Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious CorrelationsCode1
BatchFormer: Learning to Explore Sample Relationships for Robust Representation LearningCode2
Relative distance matters for one-shot landmark detection—0
Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation LearningCode1
Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation TasksCode1
Learning Moving-Object Tracking with FMCW LiDAR—0
The Optimal Noise in Noise-Contrastive Learning Is Not What You ThinkCode0
Adaptive Discriminative Regularization for Visual Classification—0
Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from ImagesCode0
Self-supervised Transformer for Deepfake Detection—0
InsertionNet 2.0: Minimal Contact Multi-Step Insertion Using Multimodal Multiview Sensory Input—0
Two-Level Supervised Contrastive Learning for Response Selection in Multi-Turn Dialogue—0
CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud UnderstandingCode2
ACTIVE:Augmentation-Free Graph Contrastive Learning for Partial Multi-View Clustering—0
DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction—0
Show:102550
← PrevPage 105 of 134Next →
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