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 3026–3050 of 6661 papers

TitleStatusHype
QD-VMR: Query Debiasing with Contextual Understanding Enhancement for Video Moment Retrieval—0
Leveraging Contrastive Learning and Self-Training for Multimodal Emotion Recognition with Limited Labeled SamplesCode0
TRRG: Towards Truthful Radiology Report Generation With Cross-modal Disease Clue Enhanced Large Language Model—0
Multi-Task Curriculum Graph Contrastive Learning with Clustering Entropy Guidance—0
GarmentAligner: Text-to-Garment Generation via Retrieval-augmented Multi-level Corrections—0
Improving Query-by-Vocal Imitation with Contrastive Learning and Audio PretrainingCode0
Practical token pruning for foundation models in few-shot conversational virtual assistant systems—0
LARR: Large Language Model Aided Real-time Scene Recommendation with Semantic Understanding—0
SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs—0
Estimated Audio-Caption Correspondences Improve Language-Based Audio RetrievalCode0
Universal Novelty Detection Through Adaptive Contrastive LearningCode0
Athena: Safe Autonomous Agents with Verbal Contrastive Learning—0
Breast tumor classification based on self-supervised contrastive learning from ultrasound videos—0
Multi-level Monte-Carlo Gradient Methods for Stochastic Optimization with Biased Oracles—0
Just a Hint: Point-Supervised Camouflaged Object Detection—0
OCTCube-M: A 3D multimodal optical coherence tomography foundation model for retinal and systemic diseases with cross-cohort and cross-device validation—0
WRIM-Net: Wide-Ranging Information Mining Network for Visible-Infrared Person Re-Identification—0
Enforcing View-Consistency in Class-Agnostic 3D Segmentation Fields—0
AI, Entrepreneurs, and Privacy: Deep Learning Outperforms Humans in Detecting Entrepreneurs from Image Data—0
Debiased Contrastive Representation Learning for Mitigating Dual Biases in Recommender Systems—0
Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise—0
Uniting contrastive and generative learning for event sequences models—0
3D-Consistent Human Avatars with Sparse Inputs via Gaussian Splatting and Contrastive Learning—0
Structure-enhanced Contrastive Learning for Graph Clustering—0
Resolving Lexical Bias in Edit Scoping with Projector Editor NetworksCode0
Show:102550
← PrevPage 122 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