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 1226–1250 of 6661 papers

TitleStatusHype
A sound description: Exploring prompt templates and class descriptions to enhance zero-shot audio classification—0
Multi-View Adaptive Contrastive Learning for Information Retrieval Based Fault Localization—0
COCO-OLAC: A Benchmark for Occluded Panoptic Segmentation and Image UnderstandingCode0
PRAGA: Prototype-aware Graph Adaptive Aggregation for Spatial Multi-modal Omics AnalysisCode1
Exploiting Minority Pseudo-Labels for Semi-Supervised Semantic Segmentation in Autonomous Driving—0
Enhancing Unsupervised Sentence Embeddings via Knowledge-Driven Data Augmentation and Gaussian-Decayed Contrastive Learning—0
PromSec: Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs)Code1
Scale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation—0
JEAN: Joint Expression and Audio-guided NeRF-based Talking Face Generation—0
Multimodal Generalized Category Discovery—0
RUIE: Retrieval-based Unified Information Extraction using Large Language ModelCode0
Contrastive Learning in Memristor-based Neuromorphic Systems—0
Self-Contrastive Forward-Forward Algorithm—0
Exploring ChatGPT-based Augmentation Strategies for Contrastive Aspect-based Sentiment Analysis—0
Fair Anomaly Detection For Imbalanced Groups—0
Learning Spatially-Aware Language and Audio Embeddings—0
CLIP Adaptation by Intra-modal Overlap Reduction—0
Robust image representations with counterfactual contrastive learningCode1
Learning Semi-Supervised Medical Image Segmentation from Spatial RegistrationCode0
Contrastive Learning for Character Detection in Ancient Greek PapyriCode0
MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion—0
Finetuning CLIP to Reason about Pairwise DifferencesCode1
Open-World Test-Time Training: Self-Training with Contrast Learning—0
Pre-Training for 3D Hand Pose Estimation with Contrastive Learning on Large-Scale Hand Images in the Wild—0
Self-supervised Learning for Acoustic Few-Shot Classification—0
Show:102550
← PrevPage 50 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