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 5726–5750 of 6661 papers

TitleStatusHype
Auto-MLM: Improved Contrastive Learning for Self-supervised Multi-lingual Knowledge Retrieval—0
Self-Supervised Image Representation Learning with Geometric Set Consistency—0
Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning—0
Self-Contrastive Learning based Semi-Supervised Radio Modulation Classification—0
Supervised Graph Contrastive Learning for Few-shot Node Classification—0
Contrasting the landscape of contrastive and non-contrastive learningCode0
UnShadowNet: Illumination Critic Guided Contrastive Learning For Shadow Removal—0
Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors SupervisionCode0
Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Tracking—0
A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training—0
Tackling Online One-Class Incremental Learning by Removing Negative Contrasts—0
Self-supervised Video-centralised Transformer for Video Face Clustering—0
Steganalysis of Image with Adaptively Parametric Activation—0
Probing Representation Forgetting in Supervised and Unsupervised Continual Learning—0
On Understanding and Mitigating the Dimensional Collapse of Graph Contrastive Learning: a Non-Maximum Removal Approach—0
mcBERT: Momentum Contrastive Learning with BERT for Zero-Shot Slot Filling—0
Negative Selection by Clustering for Contrastive Learning in Human Activity Recognition—0
Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition—0
Text Transformations in Contrastive Self-Supervised Learning: A Review—0
Utterance Rewriting with Contrastive Learning in Multi-turn Dialogue—0
Towards Textual Out-of-Domain Detection without In-Domain Labels—0
Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL—0
Partitioning Image Representation in Contrastive Learning—0
Contrastive Learning with Positive-Negative Frame Mask for Music Representation—0
CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in SegmentationCode0
Show:102550
← PrevPage 230 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