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 1101–1150 of 6661 papers

TitleStatusHype
CMAL: A Novel Cross-Modal Associative Learning Framework for Vision-Language Pre-Training—0
Feature Augmentation for Self-supervised Contrastive Learning: A Closer Look—0
StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples—0
From Real Artifacts to Virtual Reference: A Robust Framework for Translating Endoscopic Images—0
Unleashing the Power of LLMs as Multi-Modal Encoders for Text and Graph-Structured Data—0
SeaDATE: Remedy Dual-Attention Transformer with Semantic Alignment via Contrast Learning for Multimodal Object Detection—0
Contrastive learning of cell state dynamics in response to perturbationsCode2
Toward a Well-Calibrated Discrimination via Survival Outcome-Aware Contrastive Learning—0
CONSULT: Contrastive Self-Supervised Learning for Few-shot Tumor Detection—0
StatioCL: Contrastive Learning for Time Series via Non-Stationary and Temporal ContrastCode0
Affinity-Graph-Guided Contractive Learning for Pretext-Free Medical Image Segmentation with Minimal Annotation—0
SpeGCL: Self-supervised Graph Spectrum Contrastive Learning without Positive Samples—0
Querying functional and structural niches on spatial transcriptomics dataCode0
Unified Representation of Genomic and Biomedical Concepts through Multi-Task, Multi-Source Contrastive Learning—0
Eliminating the Language Bias for Visual Question Answering with fine-grained Causal Intervention—0
BrainMVP: Multi-modal Vision Pre-training for Brain Image Analysis using Multi-parametric MRICode2
Revisiting and Benchmarking Graph Autoencoders: A Contrastive Learning PerspectiveCode0
Large-Scale 3D Medical Image Pre-training with Geometric Context PriorsCode3
ViFi-ReID: A Two-Stream Vision-WiFi Multimodal Approach for Person Re-identification—0
EchoPrime: A Multi-Video View-Informed Vision-Language Model for Comprehensive Echocardiography Interpretation—0
t-READi: Transformer-Powered Robust and Efficient Multimodal Inference for Autonomous Driving—0
Bridging Gaps: Federated Multi-View Clustering in Heterogeneous Hybrid ViewsCode1
Pic@Point: Cross-Modal Learning by Local and Global Point-Picture Correspondence—0
Contrastive Learning for Implicit Social Factors in Social Media Popularity PredictionCode0
Bridging Text and Image for Artist Style Transfer via Contrastive Learning—0
Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question AnsweringCode1
Intent-Enhanced Data Augmentation for Sequential Recommendation—0
Towards Cross-domain Few-shot Graph Anomaly Detection—0
CSGDN: Contrastive Signed Graph Diffusion Network for Predicting Crop Gene-phenotype AssociationsCode0
Multi-Facet Counterfactual Learning for Content Quality Evaluation—0
LaB-CL: Localized and Balanced Contrastive Learning for improving parking slot detection—0
Enhancing Hyperspectral Image Prediction with Contrastive Learning in Low-Label Regime—0
Evolutionary Contrastive Distillation for Language Model Alignment—0
GrabDAE: An Innovative Framework for Unsupervised Domain Adaptation Utilizing Grab-Mask and Denoise Auto-Encoder—0
DISCO: A Hierarchical Disentangled Cognitive Diagnosis Framework for Interpretable Job RecommendationCode0
Aligning Motion-Blurred Images Using Contrastive Learning on Overcomplete PixelsCode0
Learn from Real: Reality Defender's Submission to ASVspoof5 Challenge—0
Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and TrainingCode2
Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation—0
SurANet: Surrounding-Aware Network for Concealed Object Detection via Highly-Efficient Interactive Contrastive Learning StrategyCode0
Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive ReplayCode0
Contrastive Learning to Fine-Tune Feature Extraction Models for the Visual Cortex—0
Monocular Visual Place Recognition in LiDAR Maps via Cross-Modal State Space Model and Multi-View Matching—0
An Eye for an Ear: Zero-shot Audio Description Leveraging an Image Captioner using Audiovisual Distribution AlignmentCode0
Continuous Contrastive Learning for Long-Tailed Semi-Supervised RecognitionCode1
Grounding is All You Need? Dual Temporal Grounding for Video Dialog—0
ConML: A Universal Meta-Learning Framework with Task-Level Contrastive Learning—0
Multimodal Representation Learning using Adaptive Graph Construction—0
BEVLoc: Cross-View Localization and Matching via Birds-Eye-View SynthesisCode2
Rethinking Weak-to-Strong Augmentation in Source-Free Domain Adaptive Object Detection—0
Show:102550
← PrevPage 23 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