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 701–750 of 6661 papers

TitleStatusHype
Multimodal Contrastive Representation Learning in Augmented Biomedical Knowledge GraphsCode1
MADGEN: Mass-Spec attends to De Novo Molecular generationCode1
Few-shot Implicit Function Generation via Equivariance—0
AdaCrossNet: Adaptive Dynamic Loss Weighting for Cross-Modal Contrastive Point Cloud LearningCode0
Contrastive Learning from Exploratory Actions: Leveraging Natural Interactions for Preference Elicitation—0
MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector QuantizationCode3
Understanding Difficult-to-learn Examples in Contrastive Learning: A Theoretical Framework for Spectral Contrastive Learning—0
An Inclusive Theoretical Framework of Robust Supervised Contrastive Loss against Label Noise—0
PromptHash:Affinity-Prompted Collaborative Cross-Modal Learning for Adaptive Hashing RetrievalCode0
Relation3D : Enhancing Relation Modeling for Point Cloud Instance SegmentationCode1
V^2Dial: Unification of Video and Visual Dialog via Multimodal Experts—0
Adapting to Observation Length of Trajectory Prediction via Contrastive Learning—0
Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution—0
SKE-Layout: Spatial Knowledge Enhanced Layout Generation with LLMs—0
A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets—0
Multi-modal Vision Pre-training for Medical Image Analysis—0
ODA-GAN: Orthogonal Decoupling Alignment GAN Assisted by Weakly-supervised Learning for Virtual Immunohistochemistry StainingCode0
Foley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows—0
CLOC: Contrastive Learning for Ordinal Classification with Multi-Margin N-pair Loss—0
Pay Attention to the Foreground in Object-Centric Learning—0
UMFN: Unified Multi-Domain Face Normalization for Joint Cross-domain Prototype Learning and Heterogeneous Face Recognition—0
Dynamic Stereotype Theory Induced Micro-expression Recognition with Oriented Deformation—0
Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation—0
EASEMVC:Efficient Dual Selection Mechanism for Deep Multi-View Clustering—0
Incorporating Dense Knowledge Alignment into Unified Multimodal Representation Models—0
DyCON: Dynamic Uncertainty-aware Consistency and Contrastive Learning for Semi-supervised Medical Image Segmentation—0
Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis—0
Perceptual Inductive Bias Is What You Need Before Contrastive Learning—0
Multi-Modal Contrastive Masked Autoencoders: A Two-Stage Progressive Pre-training Approach for RGBD Datasets—0
SLADE: Shielding against Dual Exploits in Large Vision-Language Models—0
Less Attention is More: Prompt Transformer for Generalized Category DiscoveryCode0
Viewpoint Rosetta Stone: Unlocking Unpaired Ego-Exo Videos for View-invariant Representation Learning—0
Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering—0
SmartCLIP: Modular Vision-language Alignment with Identification GuaranteesCode1
ROLL: Robust Noisy Pseudo-label Learning for Multi-View Clustering with Noisy Correspondence—0
Link-based Contrastive Learning for One-Shot Unsupervised Domain Adaptation—0
Multi-modal Contrastive Learning with Negative Sampling Calibration for Phenotypic Drug Discovery—0
Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements—0
Make Domain Shift a Catastrophic Forgetting Alleviator in Class-Incremental Learning—0
Phoneme-Level Contrastive Learning for User-Defined Keyword Spotting with Flexible Enrollment—0
Unsupervised dense retrieval with conterfactual contrastive learning—0
Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation LearningCode1
Hierarchical Banzhaf Interaction for General Video-Language Representation Learning—0
EraseAnything: Enabling Concept Erasure in Rectified Flow TransformersCode1
Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning—0
Multi-Modality Driven LoRA for Adverse Condition Depth Estimation—0
Self-Calibrated Dual Contrasting for Annotation-Efficient Bacteria Raman Spectroscopy Clustering and Classification—0
Injecting Explainability and Lightweight Design into Weakly Supervised Video Anomaly Detection Systems—0
Neighbor Does Matter: Density-Aware Contrastive Learning for Medical Semi-supervised Segmentation—0
NijiGAN: Transform What You See into Anime with Contrastive Semi-Supervised Learning and Neural Ordinary Differential Equations—0
Show:102550
← PrevPage 15 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