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 1701–1750 of 6661 papers

TitleStatusHype
DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial NetworkCode1
Reconsidering Representation Alignment for Multi-view ClusteringCode1
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-TrainingCode1
3D Human Pose, Shape and Texture from Low-Resolution Images and VideosCode1
FSCE: Few-Shot Object Detection via Contrastive Proposal EncodingCode1
Spatially Consistent Representation LearningCode1
VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial ExamplesCode1
SimTriplet: Simple Triplet Representation Learning with a Single GPUCode1
Doubly Contrastive Deep ClusteringCode1
Self-Supervised Longitudinal Neighbourhood EmbeddingCode1
Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical ImagesCode1
SoundCLR: Contrastive Learning of Representations For Improved Environmental Sound ClassificationCode1
Task-Adaptive Neural Network Search with Meta-Contrastive LearningCode1
Partially View-aligned Representation Learning with Noise-robust Contrastive LossCode1
Panoramic Panoptic Segmentation: Towards Complete Surrounding Understanding via Unsupervised Contrastive LearningCode1
Anomaly Detection on Attributed Networks via Contrastive Self-Supervised LearningCode1
Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning ViewCode1
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-LearningCode1
Molecular Contrastive Learning of Representations via Graph Neural NetworksCode1
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution CalibrationCode1
Contrastive Learning Inverts the Data Generating ProcessCode1
COCO-LM: Correcting and Contrasting Text Sequences for Language Model PretrainingCode1
Large-Scale Representation Learning on Graphs via BootstrappingCode1
Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-TuningCode1
CDPAM: Contrastive learning for perceptual audio similarityCode1
DetCo: Unsupervised Contrastive Learning for Object DetectionCode1
Negative Data AugmentationCode1
Quantifying and Mitigating Privacy Risks of Contrastive LearningCode1
Contrastive Embeddings for Neural ArchitecturesCode1
Semi-Supervised Action Recognition with Temporal Contrastive LearningCode1
Cleora: A Simple, Strong and Scalable Graph Embedding SchemeCode1
NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose EstimationCode1
Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude LearningCode1
Understanding and Achieving Efficient Robustness with Adversarial Supervised Contrastive LearningCode1
Few-shot Action Recognition with Prototype-centered Attentive LearningCode1
TCLR: Temporal Contrastive Learning for Video RepresentationCode1
Scaling Deep Contrastive Learning Batch Size under Memory Limited SetupCode1
Label Contrastive Coding based Graph Neural Network for Graph ClassificationCode1
Big Self-Supervised Models Advance Medical Image ClassificationCode1
Cross-Modal Contrastive Learning for Text-to-Image GenerationCode1
Cross-Modal Contrastive Learning of Representations for Navigation using Lightweight, Low-Cost Millimeter Wave Radar for Adverse Environmental ConditionsCode1
GAN-Control: Explicitly Controllable GANsCode1
Co2L: Contrastive Continual LearningCode1
Unsupervised Point Cloud Object Co-Segmentation by Co-Contrastive Learning and Mutual Attention SamplingCode1
Learning From Noisy Data With Robust Representation LearningCode1
Region-Aware Contrastive Learning for Semantic SegmentationCode1
Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive LearningCode1
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive LearningCode1
Spatial Contrastive Learning for Few-Shot ClassificationCode1
Self-Supervised Representation Learning for Astronomical ImagesCode1
Show:102550
← PrevPage 35 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