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 2476–2500 of 6661 papers

TitleStatusHype
Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIPCode0
Analyzing Local Representations of Self-supervised Vision Transformers—0
Contrastive learning-based agent modeling for deep reinforcement learning—0
Mitigating the Impact of False Negatives in Dense Retrieval with Contrastive Confidence RegularizationCode1
QGFace: Quality-Guided Joint Training For Mixed-Quality Face Recognition—0
Towards Mitigating Dimensional Collapse of Representations in Collaborative Filtering—0
Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion—0
Learning Vision from Models Rivals Learning Vision from DataCode2
3DTINC: Time-Equivariant Non-Contrastive Learning for Predicting Disease Progression from Longitudinal OCTs—0
A Contrastive Variational Graph Auto-Encoder for Node ClusteringCode0
Adversarial Representation with Intra-Modal and Inter-Modal Graph Contrastive Learning for Multimodal Emotion Recognition—0
One Model to Rule them All: Towards Universal Segmentation for Medical Images with Text PromptsCode2
Spatial-Related Sensors Matters: 3D Human Motion Reconstruction Assisted with Textual Semantics—0
Learning to Embed Time Series Patches IndependentlyCode1
Learning Time-aware Graph Structures for Spatially Correlated Time Series Forecasting—0
Soft Contrastive Learning for Time SeriesCode1
scRNA-seq Data Clustering by Cluster-aware Iterative Contrastive LearningCode0
Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks—0
MIM4DD: Mutual Information Maximization for Dataset Distillation—0
RDGCL: Reaction-Diffusion Graph Contrastive Learning for Recommendation—0
Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data LimitationsCode0
Medical Report Generation based on Segment-Enhanced Contrastive Representation Learning—0
Masked Contrastive Reconstruction for Cross-modal Medical Image-Report Retrieval—0
Federated Hyperdimensional Computing—0
TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation LearningCode1
Show:102550
← PrevPage 100 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