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 876–900 of 6661 papers

TitleStatusHype
MuSiCNet: A Gradual Coarse-to-Fine Framework for Irregularly Sampled Multivariate Time Series Analysis—0
LamRA: Large Multimodal Model as Your Advanced Retrieval AssistantCode2
CSP-AIT-Net: A contrastive learning-enhanced spatiotemporal graph attention framework for short-term metro OD flow prediction with asynchronous inflow tracking—0
Neuron Abandoning Attention Flow: Visual Explanation of Dynamics inside CNN Models—0
Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries—0
Multi-View Incongruity Learning for Multimodal Sarcasm Detection—0
Exploring Large Vision-Language Models for Robust and Efficient Industrial Anomaly Detection—0
AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer—0
Table Integration in Data Lakes Unleashed: Pairwise Integrability Judgment, Integrable Set Discovery, and Multi-Tuple Conflict Resolution—0
Train Once for All: A Transitional Approach for Efficient Aspect Sentiment Triplet ExtractionCode0
Retrieval-guided Cross-view Image Synthesis—0
FlowCLAS: Enhancing Normalizing Flow Via Contrastive Learning For Anomaly Segmentation—0
Effective Fine-Tuning of Vision-Language Models for Accurate Galaxy Morphology Analysis—0
RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation—0
Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures—0
SAMa: Material-aware 3D Selection and Segmentation—0
Z-STAR+: A Zero-shot Style Transfer Method via Adjusting Style Distribution—0
FedRGL: Robust Federated Graph Learning for Label Noise—0
SADG: Segment Any Dynamic Gaussian Without Object TrackersCode2
Multi-Label Contrastive Learning : A Comprehensive StudyCode0
3D Scene Graph Guided Vision-Language Pre-training—0
The Last Mile to Supervised Performance: Semi-Supervised Domain Adaptation for Semantic Segmentation—0
Novel Class Discovery for Open Set Raga Classification—0
RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable DataCode1
Manual-PA: Learning 3D Part Assembly from Instruction Diagrams—0
Show:102550
← PrevPage 36 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