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

Showing 14761500 of 6661 papers

TitleStatusHype
MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language ModelsCode1
Camera-aware Proxies for Unsupervised Person Re-IdentificationCode1
Contrastive Self-supervised Sequential Recommendation with Robust AugmentationCode1
Contrastive Semi-supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical StructuresCode1
Applying Self-supervised Learning to Network Intrusion Detection for Network Flows with Graph Neural NetworkCode1
MixCo: Mix-up Contrastive Learning for Visual RepresentationCode1
Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-trainingCode1
Self-supervised Spatial Reasoning on Multi-View Line DrawingsCode1
Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video RepresentationCode1
Can contrastive learning avoid shortcut solutions?Code1
A Closer Look at Self-Supervised Lightweight Vision TransformersCode1
3D Human Pose, Shape and Texture from Low-Resolution Images and VideosCode1
Contrastive Test-Time AdaptationCode1
Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based FeaturesCode1
Contrastive Trajectory Similarity Learning with Dual-Feature AttentionCode1
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text RetrievalCode1
Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic SegmentationCode1
Contrastive Tuning: A Little Help to Make Masked Autoencoders ForgetCode1
Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement LearningCode1
A Practical Contrastive Learning Framework for Single-Image Super-ResolutionCode1
Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial RobustnessCode1
Contrastive Variational Reinforcement Learning for Complex ObservationsCode1
Modality Curation: Building Universal Embeddings for Advanced Multimodal Information RetrievalCode1
Contrastive Video Question Answering via Video Graph TransformerCode1
Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive LearningCode1
Show:102550
← PrevPage 60 of 267Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6Unverified
2ResNet50ImageNet Top-1 Accuracy73Unverified
3ResNet50ImageNet Top-1 Accuracy71.1Unverified
4ResNet50ImageNet Top-1 Accuracy69.3Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8Unverified
7ResNet50ImageNet Top-1 Accuracy63.6Unverified
8ResNet50ImageNet Top-1 Accuracy61.5Unverified
9ResNet50ImageNet Top-1 Accuracy61.5Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55Unverified