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

Showing 27762800 of 6661 papers

TitleStatusHype
Line Graph Contrastive Learning for Link PredictionCode0
Knowing Where and What: Unified Word Block Pretraining for Document UnderstandingCode0
Knowledge-aware Dual-side Attribute-enhanced RecommendationCode0
Contrast and Clustering: Learning Neighborhood Pair Representation for Source-free Domain AdaptationCode0
PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive LearningCode0
Equivariant Contrastive Learning for Sequential RecommendationCode0
EqCo: Equivalent Rules for Self-supervised Contrastive LearningCode0
ContraSim -- Analyzing Neural Representations Based on Contrastive LearningCode0
Key Point Analysis via Contrastive Learning and Extractive Argument SummarizationCode0
Reducing Predictive Feature Suppression in Resource-Constrained Contrastive Image-Caption RetrievalCode0
Keypoint Aware Masked Image ModellingCode0
Expression Prompt Collaboration Transformer for Universal Referring Video Object SegmentationCode0
JTCSE: Joint Tensor-Modulus Constraints and Cross-Attention for Unsupervised Contrastive Learning of Sentence EmbeddingsCode0
Adaptive Multi-head Contrastive LearningCode0
Joint Searching and Grounding: Multi-Granularity Video Content RetrievalCode0
Joint Representation Learning for Text and 3D Point CloudCode0
JojoSCL: Shrinkage Contrastive Learning for single-cell RNA sequence ClusteringCode0
Ensemble Modeling with Contrastive Knowledge Distillation for Sequential RecommendationCode0
Adversarial Bootstrapped Question Representation Learning for Knowledge TracingCode0
BANER: Boundary-Aware LLMs for Few-Shot Named Entity RecognitionCode0
Joint Masked Reconstruction and Contrastive Learning for Mining Interactions Between ProteinsCode0
Joint Prediction of Meningioma Grade and Brain Invasion via Task-Aware Contrastive LearningCode0
Enhancing the Ranking Context of Dense Retrieval Methods through Reciprocal Nearest NeighborsCode0
JCSE: Contrastive Learning of Japanese Sentence Embeddings and Its ApplicationsCode0
Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic DecompositionCode0
Show:102550
← PrevPage 112 of 267Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6Unverified
2ResNet50ImageNet Top-1 Accuracy73Unverified
3ResNet50ImageNet Top-1 Accuracy71.1Unverified
4ResNet50ImageNet Top-1 Accuracy69.3Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8Unverified
7ResNet50ImageNet Top-1 Accuracy63.6Unverified
8ResNet50ImageNet Top-1 Accuracy61.5Unverified
9ResNet50ImageNet Top-1 Accuracy61.5Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55Unverified