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 5926–5950 of 6661 papers

TitleStatusHype
xMoCo: Cross Momentum Contrastive Learning for Open-Domain Question Answering—0
Control Image Captioning Spatially and Temporally—0
TA-MAMC at SemEval-2021 Task 4: Task-adaptive Pretraining and Multi-head Attention for Abstract Meaning Reading Comprehension—0
Object-aware Contrastive Learning for Debiased Scene RepresentationCode1
Enhancing Social Relation Inference with Concise Interaction Graph and Discriminative Scene Representation—0
Synth-by-Reg (SbR): Contrastive learning for synthesis-based registration of paired imagesCode1
On the Efficacy of Small Self-Supervised Contrastive Models without Distillation SignalsCode0
Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labelsCode1
Self-Supervised Learning for Fine-Grained Image ClassificationCode1
Unsupervised Outlier Detection using Memory and Contrastive Learning—0
DCL: Differential Contrastive Learning for Geometry-Aware Depth SynthesisCode0
Improve Unsupervised Pretraining for Few-label Transfer—0
Parametric Contrastive LearningCode1
AASAE: Augmentation-Augmented Stochastic AutoencodersCode1
What Remains of Visual Semantic Embeddings—0
Revisiting Catastrophic Forgetting in Class Incremental Learning—0
The Impact of Negative Sampling on Contrastive Structured World ModelsCode0
Multi-Label Image Classification with Contrastive Learning—0
On the Memorization Properties of Contrastive Learning—0
Improved Text Classification via Contrastive Adversarial Training—0
SMILE: Sparse-Attention based Multiple Instance Contrastive Learning for Glioma Sub-type Classification Using Pathological Image—0
ReSSL: Relational Self-Supervised Learning with Weak AugmentationCode1
Boosting Few-Shot Classification with View-Learnable Contrastive LearningCode1
Group Contrastive Self-Supervised Learning on Graphs—0
Separating Skills and Concepts for Novel Visual Question AnsweringCode1
Show:102550
← PrevPage 238 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