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 1251–1275 of 6661 papers

TitleStatusHype
NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-training—0
Open-World Test-Time Training: Self-Training with Contrast Learning—0
Turbo your multi-modal classification with contrastive learning—0
Evaluating Pre-trained Convolutional Neural Networks and Foundation Models as Feature Extractors for Content-based Medical Image RetrievalCode4
Acoustic identification of individual animals with hierarchical contrastive learning—0
Multi-intent Aware Contrastive Learning for Sequential Recommendation—0
Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding—0
Multiplex Graph Contrastive Learning with Soft NegativesCode0
BLens: Contrastive Captioning of Binary Functions using Ensemble Embedding—0
Multi-object event graph representation learning for Video Question Answering—0
GRE^2-MDCL: Graph Representation Embedding Enhanced via Multidimensional Contrastive Learning—0
Taylor-Sensus Network: Embracing Noise to Enlighten Uncertainty for Scientific Data—0
Enhancing Sequential Music Recommendation with Negative Feedback-informed Contrastive LearningCode0
A Unified Contrastive Loss for Self-TrainingCode0
What to align in multimodal contrastive learning?—0
VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos—0
How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval—0
DV-FSR: A Dual-View Target Attack Framework for Federated Sequential RecommendationCode0
Cross-Modal Self-Supervised Learning with Effective Contrastive Units for LiDAR Point CloudsCode0
Alignist: CAD-Informed Orientation Distribution Estimation by Fusing Shape and CorrespondencesCode0
DetailCLIP: Detail-Oriented CLIP for Fine-Grained TasksCode2
Weakly-supervised Camera Localization by Ground-to-satellite Image RegistrationCode1
INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding—0
PharmacoMatch: Efficient 3D Pharmacophore Screening via Neural Subgraph Matching—0
Contrastive Federated Learning with Tabular Data Silos—0
Show:102550
← PrevPage 51 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