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 3651–3700 of 6661 papers

TitleStatusHype
Focalized Contrastive View-invariant Learning for Self-supervised Skeleton-based Action Recognition—0
Unsupervised Cross-domain Pulmonary Nodule Detection without Source DataCode0
Open-Vocabulary Point-Cloud Object Detection without 3D AnnotationCode1
MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action RecognitionCode1
Abnormal Event Detection via Hypergraph Contrastive Learning—0
SPAN: Learning Similarity between Scene Graphs and Images with TransformersCode1
Constructive Assimilation: Boosting Contrastive Learning Performance through View Generation Strategies—0
Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental LearningCode1
Dual Contrastive Prediction for Incomplete Multi-view Representation LearningCode1
MP-FedCL: Multiprototype Federated Contrastive Learning for Edge Intelligence—0
Towards Understanding the Mechanism of Contrastive Learning via Similarity Structure: A Theoretical Analysis—0
HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of ActionsCode0
Weakly-Supervised Text-driven Contrastive Learning for Facial Behavior Understanding—0
Simple Contrastive Representation Learning for Time Series ForecastingCode1
Dynamic Conceptional Contrastive Learning for Generalized Category DiscoveryCode1
Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning—0
Reliable Representations Learning for Incomplete Multi-View Partial Multi-Label Classification—0
Mixed Autoencoder for Self-supervised Visual Representation LearningCode1
Dual Circle Contrastive Learning-Based Blind Image Super-Resolution—0
ContraSim -- Analyzing Neural Representations Based on Contrastive LearningCode0
Sounding Video Generator: A Unified Framework for Text-guided Sounding Video GenerationCode0
Seeing What You Said: Talking Face Generation Guided by a Lip Reading ExpertCode2
FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-tail Trajectory PredictionCode1
Model and Evaluation: Towards Fairness in Multilingual Text Classification—0
Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding—0
Spatiotemporal Self-supervised Learning for Point Clouds in the WildCode1
Data Efficient Contrastive Learning in Histopathology using Active SamplingCode0
Deep Incomplete Multi-view Clustering with Cross-view Partial Sample and Prototype Alignment—0
Colo-SCRL: Self-Supervised Contrastive Representation Learning for Colonoscopic Video Retrieval—0
Meeting Action Item Detection with Regularized Context Modeling—0
Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete TokensCode1
Text-to-Image Diffusion Models are Zero-Shot ClassifiersCode0
Sigmoid Loss for Language Image Pre-TrainingCode3
Leveraging Hidden Positives for Unsupervised Semantic SegmentationCode1
Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure TimeCode1
Generalizable Denoising of Microscopy Images using Generative Adversarial Networks and Contrastive Learning—0
Contrastive Learning Is Spectral Clustering On Similarity GraphCode1
GestureDiffuCLIP: Gesture Diffusion Model with CLIP LatentsCode2
A Contrastive Learning Scheme with Transformer Innate PatchesCode0
Deep Augmentation: Self-Supervised Learning with Transformations in Activation Space—0
ViPFormer: Efficient Vision-and-Pointcloud Transformer for Unsupervised Pointcloud UnderstandingCode1
Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic SegmentationCode0
Deep Active Learning with Contrastive Learning Under Realistic Data Pool Assumptions—0
Selective Structured State-Spaces for Long-Form Video Understanding—0
Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation LearningCode1
Hybrid Augmented Automated Graph Contrastive Learning—0
Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning—0
Best of Both Worlds: Multimodal Contrastive Learning with Tabular and Imaging DataCode1
Aligning Step-by-Step Instructional Diagrams to Video DemonstrationsCode0
CCL: Continual Contrastive Learning for LiDAR Place RecognitionCode1
Show:102550
← PrevPage 74 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