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 6551–6600 of 6661 papers

TitleStatusHype
Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning?Code0
Self-Contrastive Weakly Supervised Learning Framework for Prognostic Prediction Using Whole Slide ImagesCode0
Efficient Relation-aware Neighborhood Aggregation in Graph Neural Networks via Tensor DecompositionCode0
A Multi-attribute Controllable Generative Model for Histopathology Image SynthesisCode0
The Computation of Generalized Embeddings for Underwater Acoustic Target Recognition using Contrastive LearningCode0
Self-Distillation Improves DNA Sequence InferenceCode0
ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched EmbeddingsCode0
Why Multi-Interest Fairness Matters: Hypergraph Contrastive Multi-Interest Learning for Fair Conversational Recommender SystemCode0
SelF-Eval: Self-supervised Fine-grained Dialogue EvaluationCode0
EfficientRec an unlimited user-item scale recommendation system based on clustering and users interaction embedding profileCode0
Efficient Model-Stealing Attacks Against Inductive Graph Neural NetworksCode0
The Effectiveness of Graph Contrastive Learning on Mathematical Information RetrievalCode0
Efficient Labelling of Affective Video Datasets via Few-Shot & Multi-Task Contrastive LearningCode0
Efficient Information Extraction in Few-Shot Relation Classification through Contrastive Representation LearningCode0
Self-Paced Sample Selection for Barely-Supervised Medical Image SegmentationCode0
Efficient Hierarchical Contrastive Self-supervising Learning for Time Series Classification via Importance-aware Resolution SelectionCode0
Self-Reinforced Graph Contrastive LearningCode0
Efficient Cluster-Based k-Nearest-Neighbor Machine TranslationCode0
Efficient block contrastive learning via parameter-free meta-node approximationCode0
Efficient and Interpretable Information Retrieval for Product Question Answering with Heterogeneous DataCode0
Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset SelectionCode0
Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of RelevanceCode0
Graph Component Contrastive Learning for Concept Relatedness EstimationCode0
Effective Open Intent Classification with K-center Contrastive Learning and Adjustable Decision BoundaryCode0
The Impact of Negative Sampling on Contrastive Structured World ModelsCode0
Unified Visual-Semantic Embeddings: Bridging Vision and Language With Structured Meaning RepresentationsCode0
Self-Supervised Class-Cognizant Few-Shot ClassificationCode0
Effective Generation of Feasible Solutions for Integer Programming via Guided DiffusionCode0
Conditional Distribution Learning on GraphsCode0
Verbs in Action: Improving verb understanding in video-language modelsCode0
ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System PredictionCode0
AmpleHate: Amplifying the Attention for Versatile Implicit Hate DetectionCode0
Self-Supervised Contrastive BERT Fine-tuning for Fusion-based Reviewed-Item RetrievalCode0
Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning ModelCode0
Unifying Dual-Space Embedding for Entity Alignment via Contrastive LearningCode0
Edge computing on TPU for brain implant signal analysisCode0
Amortised Invariance Learning for Contrastive Self-SupervisionCode0
ECC-PolypDet: Enhanced CenterNet with Contrastive Learning for Automatic Polyp DetectionCode0
Self-supervised Contrastive Learning for Irrigation Detection in Satellite ImageryCode0
Self-supervised Contrastive Learning for Volcanic Unrest DetectionCode0
Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor AttacksCode0
ECAM: A Contrastive Learning Approach to Avoid Environmental Collision in Trajectory ForecastingCode0
The Optimal Noise in Noise-Contrastive Learning Is Not What You ThinkCode0
Benchmarking Vision-Language Contrastive Methods for Medical Representation LearningCode0
Adapting to Change: Robust Counterfactual Explanations in Dynamic Data LandscapesCode0
Self-Supervised Contrastive Learning for Videos using Differentiable Local AlignmentCode0
DyTSCL: Dynamic graph representation via tempo-structural contrastive learningCode0
Adapting Pretrained Language Models for Citation Classification via Self-Supervised Contrastive LearningCode0
ViCE: Improving Dense Representation Learning by Superpixelization and Contrasting Cluster AssignmentCode0
Dynamically Scaled Temperature in Self-Supervised Contrastive LearningCode0
Show:102550
← PrevPage 132 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