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 6176–6200 of 6661 papers

TitleStatusHype
Self-supervised Learning for Semi-supervised Temporal Language Grounding—0
Contrastive Learning for Fair Representations—0
Learning Contrastive Representation for Semantic Correspondence—0
Generating Compositional Color Representations from Text—0
Homography augumented momentum constrastive learning for SAR image retrieval—0
VPN: Video Provenance Network for Robust Content Attribution—0
Contrastive Learning of Subject-Invariant EEG Representations for Cross-Subject Emotion Recognition—0
Adversarial Training with Contrastive Learning in NLP—0
CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive SummarizationCode0
Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signals—0
Interest-oriented Universal User Representation via Contrastive Learning—0
Multilingual Molecular Representation Learning via Contrastive Pre-training—0
Semi-Supervised Few-Shot Intent Classification and Slot Filling—0
Dense Semantic Contrast for Self-Supervised Visual Representation Learning—0
Deep Bregman Divergence for Contrastive Learning of Visual Representations—0
Federated Contrastive Learning for Decentralized Unlabeled Medical Images—0
Identifying partial mouse brain microscopy images from Allen reference atlas using a contrastively learned semantic spaceCode0
Camera-Tracklet-Aware Contrastive Learning for Unsupervised Vehicle Re-IdentificationCode0
Improving Gradient-based Adversarial Training for Text Classification by Contrastive Learning and Auto-Encoder—0
KFCNet: Knowledge Filtering and Contrastive Learning Network for Generative Commonsense Reasoning—0
Contrastive Learning for Context-aware Neural Machine TranslationUsing Coreference Information—0
Weakly Supervised Person Search with Region Siamese Networks—0
Attention-based Contrastive Learning for Winograd SchemasCode0
M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining—0
Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data SelectionCode0
Show:102550
← PrevPage 248 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