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 2376–2400 of 6661 papers

TitleStatusHype
DACR: Distribution-Augmented Contrastive Reconstruction for Time-Series Anomaly Detection—0
Revealing Emotional Clusters in Speaker Embeddings: A Contrastive Learning Strategy for Speech Emotion Recognition—0
Adversarial Robustness of Link Sign Prediction in Signed Graphs—0
Named Entity Recognition Under Domain Shift via Metric Learning for Life SciencesCode0
Spatial-temporal Forecasting for Regions without ObservationsCode1
Enhancing medical vision-language contrastive learning via inter-matching relation modelling—0
DeepRLI: A Multi-objective Framework for Universal Protein--Ligand Interaction PredictionCode0
Learning Backdoors for Mixed Integer Linear Programs with Contrastive Learning—0
Learning High-Quality and General-Purpose Phrase RepresentationsCode1
PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly DetectionCode1
CPCL: Cross-Modal Prototypical Contrastive Learning for Weakly Supervised Text-based Person Re-IdentificationCode0
HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization—0
EfficientRec an unlimited user-item scale recommendation system based on clustering and users interaction embedding profileCode0
Question-Answer Cross Language Image Matching for Weakly Supervised Semantic SegmentationCode1
Self-supervised New Activity Detection in Sensor-based Smart Environments—0
CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding—0
On the Effect of Data-Augmentation on Local Embedding Properties in the Contrastive Learning of Music Audio Representations—0
Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models—0
Explaining Time Series via Contrastive and Locally Sparse PerturbationsCode1
Adversarial Masking Contrastive Learning for vein recognition—0
How does self-supervised pretraining improve robustness against noisy labels across various medical image classification datasets?—0
HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image RetrievalCode1
SpineCLUE: Automatic Vertebrae Identification Using Contrastive Learning and Uncertainty Estimation—0
MIMIC: Mask Image Pre-training with Mix Contrastive Fine-tuning for Facial Expression Recognition—0
Contrastive Learning with Negative Sampling Correction—0
Show:102550
← PrevPage 96 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