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 6151–6200 of 6661 papers

TitleStatusHype
Solving Inefficiency of Self-supervised Representation LearningCode1
SimCSE: Simple Contrastive Learning of Sentence EmbeddingsCode2
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence EncodersCode1
Contrastive Learning for Sports Video: Unsupervised Player ClassificationCode1
Dual Contrastive Learning for Unsupervised Image-to-Image TranslationCode1
Contrastive Learning with Stronger AugmentationsCode1
A Semi-Supervised Classification Method of Apicomplexan Parasites and Host Cell Using Contrastive Learning Strategy—0
Probing Negative Sampling Strategies to Learn GraphRepresentations via Unsupervised Contrastive Learning—0
Knowledge-Augmented Contrastive Learning for Abnormality Classification and Localization in Chest X-rays with Radiomics using a Feedback Loop—0
Constructing Contrastive samples via Summarization for Text Classification with limited annotationsCode0
Disentangled Contrastive Learning for Learning Robust Textual RepresentationsCode0
Patient Contrastive Learning: a Performant, Expressive, and Practical Approach to ECG ModelingCode1
Bootstrapping Semantic Segmentation with Regional ContrastCode1
Context-self contrastive pretraining for crop type semantic segmentationCode1
Towards Fine-grained Visual Representations by Combining Contrastive Learning with Image Reconstruction and Attention-weighted PoolingCode1
CoCoNets: Continuous Contrastive 3D Scene RepresentationsCode1
Contrastive Learning of Global-Local Video RepresentationsCode1
Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data—0
Scene Graph Embeddings Using Relative Similarity Supervision—0
Strumming to the Beat: Audio-Conditioned Contrastive Video Textures—0
Localizing Visual Sounds the Hard WayCode1
Achieving Domain Generalization in Underwater Object Detection by Domain Mixup and Contrastive Learning—0
Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning—0
Graph Contrastive ClusteringCode1
Contrastively Learning Visual Attention as Affordance Cues from Demonstrations for Robotic GraspingCode0
LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable DirectionsCode1
Detecting Anomalies Through Contrast in Heterogeneous Data—0
ArSarcasm Shared Task: An Ensemble BERT Model for SarcasmDetection in Arabic Tweets—0
Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal ProcessingCode0
Enriched Music Representations with Multiple Cross-modal Contrastive LearningCode1
Jigsaw Clustering for Unsupervised Visual Representation LearningCode1
Unsupervised Sound Localization via Iterative Contrastive Learning—0
Composable Augmentation Encoding for Video Representation Learning—0
PointShuffleNet: Learning Non-Euclidean Features with Homotopy Equivalence and Mutual Information—0
Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity PerspectiveCode1
Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain AdaptationCode1
Denoise and Contrast for Category Agnostic Shape CompletionCode1
Progressive Domain Expansion Network for Single Domain GeneralizationCode1
Contrastive Learning of Single-Cell Phenotypic Representations for Treatment Classification—0
Model-Contrastive Federated LearningCode1
CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive LearningCode1
ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identificationCode1
Robust Audio-Visual Instance Discrimination—0
Elsa: Energy-based learning for semi-supervised anomaly detection—0
Classification of Seeds using Domain Randomization on Self-Supervised Learning Frameworks—0
Self-supervised Graph Neural Networks without explicit negative samplingCode1
Contrastive Domain Adaptation—0
Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification—0
Unsupervised Document Embedding via Contrastive Augmentation—0
Rethinking Self-Supervised Learning: Small is BeautifulCode1
Show:102550
← PrevPage 124 of 134Next →
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