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 1951–1975 of 6661 papers

TitleStatusHype
Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity RepresentationCode3
Contrastive Mean-Shift Learning for Generalized Category Discovery—0
Fuse after Align: Improving Face-Voice Association Learning via Multimodal Encoder—0
UniSAR: Modeling User Transition Behaviors between Search and RecommendationCode1
Real-world Instance-specific Image Goal Navigation: Bridging Domain Gaps via Contrastive Learning—0
An Experimental Comparison Of Multi-view Self-supervised Methods For Music TaggingCode0
GCC: Generative Calibration Clustering—0
Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class DiscoveryCode1
RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representations—0
Exploring Contrastive Learning for Long-Tailed Multi-Label Text Classification—0
Generalized Contrastive Learning for Multi-Modal Retrieval and RankingCode2
HCL-MTSAD: Hierarchical Contrastive Consistency Learning for Accurate Detection of Industrial Multivariate Time Series Anomalies—0
CodeFort: Robust Training for Code Generation Models—0
Can Contrastive Learning Refine Embeddings—0
Latent Guard: a Safety Framework for Text-to-image GenerationCode2
Gaga: Group Any Gaussians via 3D-aware Memory Bank—0
Context-aware Video Anomaly Detection in Long-Term Datasets—0
PromptSync: Bridging Domain Gaps in Vision-Language Models through Class-Aware Prototype Alignment and Discrimination—0
Contrastive-Based Deep Embeddings for Label Noise-Resilient Histopathology Image ClassificationCode0
NeuroNet: A Novel Hybrid Self-Supervised Learning Framework for Sleep Stage Classification Using Single-Channel EEGCode2
Hybrid Multi-stage Decoding for Few-shot NER with Entity-aware Contrastive Learning—0
Unsupervised Visible-Infrared ReID via Pseudo-label Correction and Modality-level Alignment—0
Global Contrastive Training for Multimodal Electronic Health Records with Language Supervision—0
Counting Objects in a Robotic Hand—0
End-to-end training of Multimodal Model and ranking ModelCode1
Show:102550
← PrevPage 79 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