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 12011225 of 6661 papers

TitleStatusHype
Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly DetectionCode1
DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot LearningCode1
Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasetsCode1
Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed RecognitionCode1
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean LabelCode1
Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text RecognitionCode1
Self-Supervised Learning for Multimedia RecommendationCode1
FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image ClassificationCode1
Reducing Annotation Need in Self-Explanatory Models for Lung Nodule DiagnosisCode1
VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph CaptioningCode1
Vision Transformer for Contrastive ClusteringCode1
Wiener Graph Deconvolutional Network Improves Graph Self-Supervised LearningCode1
Language Models as Knowledge EmbeddingsCode1
SLIC: Self-Supervised Learning with Iterative Clustering for Human Action VideosCode1
CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal PoseCode1
Towards Galaxy Foundation Models with Hybrid Contrastive LearningCode1
Utilizing Expert Features for Contrastive Learning of Time-Series RepresentationsCode1
Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive LearningCode1
Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive LearningCode1
Conditioned and Composed Image Retrieval Combining and Partially Fine-Tuning CLIP-Based FeaturesCode1
MET: Masked Encoding for Tabular DataCode1
Learning Fair Representation via Distributional Contrastive DisentanglementCode1
NCAGC: A Neighborhood Contrast Framework for Attributed Graph ClusteringCode1
Let Invariant Rationale Discovery Inspire Graph Contrastive LearningCode1
Discrete Contrastive Diffusion for Cross-Modal Music and Image GenerationCode1
Show:102550
← PrevPage 49 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