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 2151–2200 of 6661 papers

TitleStatusHype
Benchmarking Image Embeddings for E-Commerce: Evaluating Off-the Shelf Foundation Models, Fine-Tuning Strategies and Practical Trade-offs—0
RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Radiology with Zero-Shot Multi-Task Capability—0
Leveraging LLMs for Multimodal Retrieval-Augmented Radiology Report Generation via Key Phrase Extraction—0
CHIME: A Compressive Framework for Holistic Interest Modeling—0
Unifying Search and Recommendation: A Generative Paradigm Inspired by Information Theory—0
AMAD: AutoMasked Attention for Unsupervised Multivariate Time Series Anomaly Detection—0
Large Language Models Enhanced Hyperbolic Space Recommender Systems—0
Contrastive Decoupled Representation Learning and Regularization for Speech-Preserving Facial Expression Manipulation—0
TC-MGC: Text-Conditioned Multi-Grained Contrastive Learning for Text-Video RetrievalCode0
Sub-Clustering for Class Distance Recalculation in Long-Tailed Drug Classification—0
MSA-UNet3+: Multi-Scale Attention UNet3+ with New Supervised Prototypical Contrastive Loss for Coronary DSA Image SegmentationCode0
Squeeze and Excitation: A Weighted Graph Contrastive Learning for Collaborative FilteringCode0
QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors—0
ADA-Net: Attention-Guided Domain Adaptation Network with Contrastive Learning for Standing Dead Tree Segmentation Using Aerial ImageryCode0
ATM-Net: Anatomy-Aware Text-Guided Multi-Modal Fusion for Fine-Grained Lumbar Spine Segmentation—0
FontGuard: A Robust Font Watermarking Approach Leveraging Deep Font KnowledgeCode0
Decentralized Collective World Model for Emergent Communication and Coordination—0
AutoSSVH: Exploring Automated Frame Sampling for Efficient Self-Supervised Video HashingCode0
Comparative Analysis of Unsupervised and Supervised Autoencoders for Nuclei Classification in Clear Cell Renal Cell Carcinoma Images—0
SCMPPI: Supervised Contrastive Multimodal Framework for Predicting Protein-Protein Interactions—0
SLACK: Attacking LiDAR-based SLAM with Adversarial Point Injections—0
Group-based Distinctive Image Captioning with Memory Difference Encoding and Attention—0
All-day Depth Completion via Thermal-LiDAR Fusion—0
Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation—0
Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimation—0
Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-DiversityCode0
LL4G: Self-Supervised Dynamic Optimization for Graph-Based Personality Detection—0
All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning—0
SPF-Portrait: Towards Pure Portrait Customization with Semantic Pollution-Free Fine-tuning—0
CIBR: Cross-modal Information Bottleneck Regularization for Robust CLIP Generalization—0
Node Embeddings via Neighbor Embeddings—0
Consistent Subject Generation via Contrastive Instantiated Concepts—0
Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering—0
CrossMuSim: A Cross-Modal Framework for Music Similarity Retrieval with LLM-Powered Text Description Sourcing and Mining—0
Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of RelevanceCode0
Fuzzy Cluster-Aware Contrastive Clustering for Time SeriesCode0
Exploring the Effectiveness of Multi-stage Fine-tuning for Cross-encoder Re-rankersCode0
Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach—0
FakeReasoning: Towards Generalizable Forgery Detection and Reasoning—0
Retrieving Time-Series Differences Using Natural Language Queries—0
NeuroLIP: Interpretable and Fair Cross-Modal Alignment of fMRI and Phenotypic Text—0
Prompting Vision-Language Model for Nuclei Instance Segmentation and ClassificationCode0
DINeMo: Learning Neural Mesh Models with no 3D Annotations—0
Learnable Sequence Augmenter for Triplet Contrastive Learning in Sequential Recommendation—0
Deep Learning for Forensic Identification of SourceCode0
TAR: Teacher-Aligned Representations via Contrastive Learning for Quadrupedal Locomotion—0
Contrastive Learning Guided Latent Diffusion Model for Image-to-Image Translation—0
Taxonomy Inference for Tabular Data Using Large Language Models—0
SeLIP: Similarity Enhanced Contrastive Language Image Pretraining for Multi-modal Head MRI—0
Large Language Models Meet Contrastive Learning: Zero-Shot Emotion Recognition Across LanguagesCode0
Show:102550
← PrevPage 44 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