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 3551–3575 of 6661 papers

TitleStatusHype
Multimodal Fusion and Coherence Modeling for Video Topic Segmentation—0
Parkinson's Disease Detection from Resting State EEG using Multi-Head Graph Structure Learning with Gradient Weighted Graph Attention Explanations—0
MMPKUBase: A Comprehensive and High-quality Chinese Multi-modal Knowledge Graph—0
Safe Semi-Supervised Contrastive Learning Using In-Distribution Data as Positive Examples—0
A Multi-Source Heterogeneous Knowledge Injected Prompt Learning Method for Legal Charge Prediction—0
A Two-Stage Progressive Pre-training using Multi-Modal Contrastive Masked Autoencoders—0
Contrastive Learning and Abstract Concepts: The Case of Natural Numbers—0
StyEmp: Stylizing Empathetic Response Generation via Multi-Grained Prefix Encoder and Personality Reinforcement—0
Feedback Reciprocal Graph Collaborative Filtering—0
ConDL: Detector-Free Dense Image Matching—0
A Debiased Nearest Neighbors Framework for Multi-Label Text Classification—0
Contrastive Learning for Image Complexity Representation—0
Contrastive Learning for Knowledge-Based Question Generation in Large Language Models—0
BGM2Pose: Active 3D Human Pose Estimation with Non-Stationary Sounds—0
Learning Actionable World Models for Industrial Process Control—0
Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering—0
FRET: Feature Redundancy Elimination for Test Time Adaptation—0
MoCLIP: Motion-Aware Fine-Tuning and Distillation of CLIP for Human Motion Generation—0
Fractal Graph Contrastive Learning—0
Aligning Proteins and Language: A Foundation Model for Protein Retrieval—0
Controllable Expressive 3D Facial Animation via Diffusion in a Unified Multimodal Space—0
2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation—0
2M-NER: Contrastive Learning for Multilingual and Multimodal NER with Language and Modal Fusion—0
2-Tier SimCSE: Elevating BERT for Robust Sentence Embeddings—0
3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation—0
Show:102550
← PrevPage 143 of 267Next →
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