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 4626–4650 of 6661 papers

TitleStatusHype
Probing the Role of Positional Information in Vision-Language Models—0
Contrastive Label Enhancement—0
UOR: Universal Backdoor Attacks on Pre-trained Language Models—0
Distilling Semantic Concept Embeddings from Contrastively Fine-Tuned Language ModelsCode0
Masked Collaborative Contrast for Weakly Supervised Semantic SegmentationCode0
Improved baselines for vision-language pre-training—0
Latent Processes Identification From Multi-View Time SeriesCode0
RC3: Regularized Contrastive Cross-lingual Cross-modal Pre-trainingCode0
Instance Smoothed Contrastive Learning for Unsupervised Sentence EmbeddingCode0
Learning the Visualness of Text Using Large Vision-Language Models—0
Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild—0
Masked Audio Text Encoders are Effective Multi-Modal Rescorers—0
Continual Vision-Language Representation Learning with Off-Diagonal Information—0
iEdit: Localised Text-guided Image Editing with Weak Supervision—0
Inclusive FinTech Lending via Contrastive Learning and Domain Adaptation—0
Dynamic Graph Representation Learning for Depression Screening with Transformer—0
Multi-hop Commonsense Knowledge Injection Framework for Zero-Shot Commonsense Question Answering—0
Self-Supervised Video Representation Learning via Latent Time Navigation—0
Weakly-supervised ROI extraction method based on contrastive learning for remote sensing imagesCode0
Unsupervised Dense Retrieval Training with Web AnchorsCode0
MSVQ: Self-Supervised Learning with Multiple Sample Views and QueuesCode0
Region-based Contrastive Pretraining for Medical Image Retrieval with Anatomic Query—0
Traffic Forecasting on New Roads Using Spatial Contrastive Pre-Training (SCPT)Code0
Exploiting Pseudo Image Captions for Multimodal Summarization—0
Vision Language Pre-training by Contrastive Learning with Cross-Modal Similarity Regulation—0
Show:102550
← PrevPage 186 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