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 6076–6100 of 6661 papers

TitleStatusHype
Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases—0
Proposal-Contrastive Pretraining for Object Detection from Fewer Data—0
ProTIP: Progressive Tool Retrieval Improves Planning—0
ProtoGMM: Multi-prototype Gaussian-Mixture-based Domain Adaptation Model for Semantic Segmentation—0
Prototype and Instance Contrastive Learning for Unsupervised Domain Adaptation in Speaker Verification—0
Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation—0
PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classification—0
Prototypical Contrastive Learning and Adaptive Interest Selection for Candidate Generation in Recommendations—0
Prototypical Contrastive Predictive Coding—0
Prototypical Cross-domain Knowledge Transfer for Cervical Dysplasia Visual Inspection—0
Prototypical Extreme Multi-label Classification with a Dynamic Margin Loss—0
Prototypical Representation Learning for Low-resource Knowledge Extraction: Summary and Perspective—0
Prototypical Verbalizer for Prompt-based Few-shot Tuning—0
Provable Optimization for Adversarial Fair Self-supervised Contrastive Learning—0
Provable Representation Learning for Imitation with Contrastive Fourier Features—0
Provable Rich Observation Reinforcement Learning with Combinatorial Latent States—0
Pseudo Contrastive Learning for Graph-based Semi-supervised Learning—0
Pseudo-Data based Self-Supervised Federated Learning for Classification of Histopathological Images—0
Pseudo-Label Calibration Semi-supervised Multi-Modal Entity Alignment—0
PseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings—0
PSG-MAE: Robust Multitask Sleep Event Monitoring using Multichannel PSG Reconstruction and Inter-channel Contrastive Learning—0
PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning—0
Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic Embeddings—0
QAGCF: Graph Collaborative Filtering for Q&A Recommendation—0
QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models—0
Show:102550
← PrevPage 244 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