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 1851–1900 of 6661 papers

TitleStatusHype
CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIPCode1
UMIC: An Unreferenced Metric for Image Captioning via Contrastive LearningCode1
Unbiased Supervised Contrastive LearningCode1
DialogueCSE: Dialogue-based Contrastive Learning of Sentence EmbeddingsCode1
Understanding Contrastive Representation Learning through Geometry on the HypersphereCode1
Understanding Dark Scenes by Contrasting Multi-Modal ObservationsCode1
Understanding Zero-Shot Adversarial Robustness for Large-Scale ModelsCode1
DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label ClassificationCode1
Evaluating Modules in Graph Contrastive LearningCode1
Domain Knowledge-Informed Self-Supervised Representations for Workout Form AssessmentCode1
Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation TasksCode1
UniVSE: Robust Visual Semantic Embeddings via Structured Semantic RepresentationsCode1
Factorized Contrastive Learning: Going Beyond Multi-view RedundancyCode1
UniGLM: Training One Unified Language Model for Text-Attributed Graph EmbeddingCode1
FashionViL: Fashion-Focused Vision-and-Language Representation LearningCode1
FLIP: Cross-domain Face Anti-spoofing with Language GuidanceCode1
Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive StructureCode1
UniSAR: Modeling User Transition Behaviors between Search and RecommendationCode1
HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text ClassificationCode1
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based RecommendationCode1
Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense InferenceCode1
ACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical ContrastCode1
Unlocking the Potential of Unlabeled Data in Semi-Supervised Domain GeneralizationCode1
Diffusion-based Contrastive Learning for Sequential RecommendationCode1
Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual LearningCode1
Diffusion Model is Secretly a Training-free Open Vocabulary Semantic SegmenterCode1
CluCDD:Contrastive Dialogue Disentanglement via ClusteringCode1
Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action LocalizationCode1
Digging into contrastive learning for robust depth estimation with diffusion modelsCode1
CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic SegmentationCode1
On Equivariant and Invariant Learning of Object Landmark RepresentationsCode1
Unsupervised Episode Generation for Graph Meta-learningCode1
Unsupervised Feature Learning by Cross-Level Instance-Group DiscriminationCode1
Extending global-local view alignment for self-supervised learning with remote sensing imageryCode1
Directed Graph Contrastive LearningCode1
Unsupervised Feature Representation Learning for Domain-generalized Cross-domain Image RetrievalCode1
Combined Scaling for Zero-shot Transfer Learning—0
Combating the Bucket Effect:Multi-Knowledge Alignment for Medication Recommendation—0
Unified Framework for Feature Extraction based on Contrastive Learning—0
A Unified Framework for Contrastive Learning from a Perspective of Affinity Matrix—0
Alignment and Outer Shell Isotropy for Hyperbolic Graph Contrastive Learning—0
COMAE: COMprehensive Attribute Exploration for Zero-shot Hashing—0
Colo-SCRL: Self-Supervised Contrastive Representation Learning for Colonoscopic Video Retrieval—0
Colorectal Polyp Classification from White-light Colonoscopy Images via Domain Alignment—0
A Unified Contrastive Transfer Framework with Propagation Structure for Boosting Low-Resource Rumor Detection—0
ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition—0
CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders—0
A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training—0
CoLLAP: Contrastive Long-form Language-Audio Pretraining with Musical Temporal Structure Augmentation—0
Collaborative Visual Place Recognition through Federated Learning—0
Show:102550
← PrevPage 38 of 134Next →
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