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 5851–5900 of 6661 papers

TitleStatusHype
JTCSE: Joint Tensor-Modulus Constraints and Cross-Attention for Unsupervised Contrastive Learning of Sentence EmbeddingsCode0
Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-DiversityCode0
Overcoming Dimensional Collapse in Self-supervised Contrastive Learning for Medical Image SegmentationCode0
Cross-domain Contrastive Learning for Unsupervised Domain AdaptationCode0
CL-MFAP: A Contrastive Learning-Based Multimodal Foundation Model for Molecular Property Prediction and Antibiotic ScreeningCode0
Attacks on Node Attributes in Graph Neural NetworksCode0
Attack-Augmentation Mixing-Contrastive Skeletal Representation LearningCode0
CrossBind: Collaborative Cross-Modal Identification of Protein Nucleic-Acid-Binding ResiduesCode0
CropMix: Sampling a Rich Input Distribution via Multi-Scale CroppingCode0
PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive LearningCode0
CROCODILE: Causality aids RObustness via COntrastive DIsentangled LEarningCode0
CroCo: Cross-Modal Contrastive learning for localization of Earth Observation dataCode0
JojoSCL: Shrinkage Contrastive Learning for single-cell RNA sequence ClusteringCode0
Criteria Comparative Learning for Real-scene Image Super-ResolutionCode0
Joint Searching and Grounding: Multi-Granularity Video Content RetrievalCode0
Joint Representation Learning for Text and 3D Point CloudCode0
Panoramic Interests: Stylistic-Content Aware Personalized Headline GenerationCode0
Joint Prediction of Meningioma Grade and Brain Invasion via Task-Aware Contrastive LearningCode0
Joint Masked Reconstruction and Contrastive Learning for Mining Interactions Between ProteinsCode0
Cross-Model Cross-Stream Learning for Self-Supervised Human Action RecognitionCode0
SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues EvaluationCode0
JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model EditsCode0
JCSE: Contrastive Learning of Japanese Sentence Embeddings and Its ApplicationsCode0
Slimmable Networks for Contrastive Self-supervised LearningCode0
Slot Induction via Pre-trained Language Model Probing and Multi-level Contrastive LearningCode0
Topology Only Pre-Training: Towards Generalised Multi-Domain Graph ModelsCode0
MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive LearningCode0
IRConStyle: Image Restoration Framework Using Contrastive Learning and Style TransferCode0
Adversarial Self-Supervised Learning for Out-of-Domain DetectionCode0
IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature RepresentationCode0
CLMB: deep contrastive learning for robust metagenomic binningCode0
CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive SummarizationCode0
PARTICLE: Part Discovery and Contrastive Learning for Fine-grained RecognitionCode0
Cracking the Code of Negative Transfer: A Cooperative Game Theoretic Approach for Cross-Domain Sequential RecommendationCode0
Action-conditioned On-demand Motion GenerationCode0
PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay ReconstructionCode0
HaSa: Hardness and Structure-Aware Contrastive Knowledge Graph EmbeddingCode0
Patch-Based Contrastive Learning and Memory Consolidation for Online Unsupervised Continual LearningCode0
Intrinsic and Extrinsic Factor Disentanglement for Recommendation in Various Context ScenariosCode0
Intra-video Positive Pairs in Self-Supervised Learning for UltrasoundCode0
CPCL: Cross-Modal Prototypical Contrastive Learning for Weakly Supervised Text-based Person Re-IdentificationCode0
Path and Bone-Contour Regularized Unpaired MRI-to-CT TranslationCode0
Path-aware Siamese Graph Neural Network for Link PredictionCode0
CLIC: Contrastive Learning Framework for Unsupervised Image Complexity RepresentationCode0
Paths of A Million People: Extracting Life Trajectories from WikipediaCode0
Intra- and Inter-modal Context Interaction Modeling for Conversational Speech SynthesisCode0
SMC-NCA: Semantic-guided Multi-level Contrast for Semi-supervised Temporal Action SegmentationCode0
Patient-level Microsatellite Stability Assessment from Whole Slide Images By Combining Momentum Contrast Learning and Group Patch EmbeddingsCode0
Counterfactual Cross-modality Reasoning for Weakly Supervised Video Moment LocalizationCode0
Towards Robust Event-based Networks for Nighttime via Unpaired Day-to-Night Event TranslationCode0
Show:102550
← PrevPage 118 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