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 2851–2900 of 6661 papers

TitleStatusHype
Multi-Facet Counterfactual Learning for Content Quality Evaluation—0
CSGDN: Contrastive Signed Graph Diffusion Network for Predicting Crop Gene-phenotype AssociationsCode0
LaB-CL: Localized and Balanced Contrastive Learning for improving parking slot detection—0
GrabDAE: An Innovative Framework for Unsupervised Domain Adaptation Utilizing Grab-Mask and Denoise Auto-Encoder—0
Evolutionary Contrastive Distillation for Language Model Alignment—0
Enhancing Hyperspectral Image Prediction with Contrastive Learning in Low-Label Regime—0
Aligning Motion-Blurred Images Using Contrastive Learning on Overcomplete PixelsCode0
Learn from Real: Reality Defender's Submission to ASVspoof5 Challenge—0
Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation—0
Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive ReplayCode0
SurANet: Surrounding-Aware Network for Concealed Object Detection via Highly-Efficient Interactive Contrastive Learning StrategyCode0
Grounding is All You Need? Dual Temporal Grounding for Video Dialog—0
Contrastive Learning to Fine-Tune Feature Extraction Models for the Visual Cortex—0
An Eye for an Ear: Zero-shot Audio Description Leveraging an Image Captioner using Audiovisual Distribution AlignmentCode0
Monocular Visual Place Recognition in LiDAR Maps via Cross-Modal State Space Model and Multi-View Matching—0
Multimodal Representation Learning using Adaptive Graph Construction—0
ConML: A Universal Meta-Learning Framework with Task-Level Contrastive Learning—0
WTCL-Dehaze: Rethinking Real-world Image Dehazing via Wavelet Transform and Contrastive Learning—0
SimO Loss: Anchor-Free Contrastive Loss for Fine-Grained Supervised Contrastive Learning—0
Contrastive Learning to Improve Retrieval for Real-world Fact Checking—0
FELLAS: Enhancing Federated Sequential Recommendation with LLM as External Services—0
Improving Object Detection via Local-global Contrastive Learning—0
Rethinking Weak-to-Strong Augmentation in Source-Free Domain Adaptive Object Detection—0
Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture—0
Multi-Tiered Self-Contrastive Learning for Medical Microwave Radiometry (MWR) Breast Cancer DetectionCode0
Enhancement of Dysarthric Speech Reconstruction by Contrastive Learning—0
Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss FunctionCode0
CUDLE: Learning Under Label Scarcity to Detect Cannabis Use in Uncontrolled Environments—0
Improving Node Representation by Boosting Target-Aware Contrastive Loss—0
Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding with LLMs—0
CoLLAP: Contrastive Long-form Language-Audio Pretraining with Musical Temporal Structure Augmentation—0
Channel-aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series ForecastingCode0
SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual RepresentationsCode0
Contextual Document Embeddings—0
FARM: Functional Group-Aware Representations for Small Molecules—0
Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge TracingCode0
Domain Aware Multi-Task Pretraining of 3D Swin Transformer for T1-weighted Brain MRICode0
ScVLM: Enhancing Vision-Language Model for Safety-Critical Event UnderstandingCode0
CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset—0
CktGen: Specification-Conditioned Analog Circuit Generation—0
NECOMIMI: Neural-Cognitive Multimodal EEG-informed Image Generation with Diffusion ModelsCode0
Contrastive Abstraction for Reinforcement Learning—0
Decoding the Echoes of Vision from fMRI: Memory Disentangling for Past Semantic InformationCode0
Enhancing GANs with Contrastive Learning-Based Multistage Progressive Finetuning SNN and RL-Based External Optimization—0
Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats—0
Contrastive ground-level image and remote sensing pre-training improves representation learning for natural world imagery—0
Reducing Semantic Ambiguity In Domain Adaptive Semantic Segmentation Via Probabilistic Prototypical Pixel ContrastCode0
UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion PerceptionCode0
TwinCL: A Twin Graph Contrastive Learning Model for Collaborative FilteringCode0
Understanding the Benefits of SimCLR Pre-Training in Two-Layer Convolutional Neural Networks—0
Show:102550
← PrevPage 58 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