SOTAVerified

Metric Learning

The goal of Metric Learning is to learn a representation function that maps objects into an embedded space. The distance in the embedded space should preserve the objects’ similarity — similar objects get close and dissimilar objects get far away. Various loss functions have been developed for Metric Learning. For example, the contrastive loss guides the objects from the same class to be mapped to the same point and those from different classes to be mapped to different points whose distances are larger than a margin. Triplet loss is also popular, which requires the distance between the anchor sample and the positive sample to be smaller than the distance between the anchor sample and the negative sample.

Source: Road Network Metric Learning for Estimated Time of Arrival

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–200 of 1648 papers

TitleStatusHype
Curvature Augmented Manifold Embedding and LearningCode0
MARTA: a model for the automatic phonemic grouping of the parkinsonian speechCode0
TexTile: A Differentiable Metric for Texture TileabilityCode1
Unsupervised Collaborative Metric Learning with Mixed-Scale Groups for General Object RetrievalCode1
Explore In-Context Segmentation via Latent Diffusion Models—0
A Distance Metric Learning Model Based On Variational Information Bottleneck—0
Unsupervised Distance Metric Learning for Anomaly Detection Over Multivariate Time Series—0
Spatial Cascaded Clustering and Weighted Memory for Unsupervised Person Re-identification—0
A Semantic Distance Metric Learning approach for Lexical Semantic Change DetectionCode0
Simple But Effective: Rethinking the Ability of Deep Learning in fNIRS to Exclude Abnormal Input—0
Polos: Multimodal Metric Learning from Human Feedback for Image CaptioningCode1
Intelligent Known and Novel Aircraft Recognition -- A Shift from Classification to Similarity Learning for Combat Identification—0
Metric-Learning Encoding Models Identify Processing Profiles of Linguistic Features in BERT's RepresentationsCode0
Learning Goal-Conditioned Policies from Sub-Optimal Offline Data via Metric Learning—0
Revisiting Experience Replayable Conditions—0
How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric LearningCode2
Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric LearningCode0
Limited Memory Online Gradient Descent for Kernelized Pairwise Learning with Dynamic Averaging—0
End-to-End Supervised Hierarchical Graph Clustering for Speaker DiarizationCode0
Named Entity Recognition Under Domain Shift via Metric Learning for Life SciencesCode0
Wasserstein Distance-based Expansion of Low-Density Latent Regions for Unknown Class DetectionCode0
Two-stream joint matching method based on contrastive learning for few-shot action recognition—0
Uncertainty-Aware Deep Attention Recurrent Neural Network for Heterogeneous Time Series Imputation—0
Signal Processing in the Retina: Interpretable Graph Classifier to Predict Ganglion Cell Responses—0
Frequency Domain Modality-invariant Feature Learning for Visible-infrared Person Re-Identification—0
Depth-discriminative Metric Learning for Monocular 3D Object Detection—0
Few-Shot Object Detection with Foundation Models—0
Close Imitation of Expert Retouching for Black-and-White PhotographyCode1
Towards Improved Proxy-based Deep Metric Learning via Data-Augmented Domain AdaptationCode0
Prototype-Based Approach for One-Shot Segmentation of Brain Tumors using Few-Shot Learning—0
Misalign, Contrast then Distill: Rethinking Misalignments in Language-Image Pretraining—0
RetailKLIP : Finetuning OpenCLIP backbone using metric learning on a single GPU for Zero-shot retail product image classification—0
Collapse-Aware Triplet Decoupling for Adversarially Robust Image RetrievalCode1
TaskMet: Task-Driven Metric Learning for Model LearningCode1
Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction RepresentationsCode0
DUCK: Distance-based Unlearning via Centroid KinematicsCode0
Quantum Polar Metric Learning: Efficient Classically Learned Quantum Embeddings—0
Beyond Accuracy: Statistical Measures and Benchmark for Evaluation of Representation from Self-Supervised Learning—0
Deep Metric Learning for Computer Vision: A Brief Overview—0
Robust Concept Erasure via Kernelized Rate-Distortion MaximizationCode0
SEINE: SEgment-based Indexing for NEural information retrieval—0
VehicleGAN: Pair-flexible Pose Guided Image Synthesis for Vehicle Re-identification—0
Enhancing mTBI Diagnosis with Residual Triplet Convolutional Neural Network Using 3D CT—0
Shadow: A Novel Loss Function for Efficient Training in Siamese Networks—0
Exploring Graph Classification Techniques Under Low Data Constraints: A Comprehensive Study—0
Image Patch-Matching with Graph-Based Learning in Street Scenes—0
Deep Hashing via Householder QuantizationCode0
ProcSim: Proxy-based Confidence for Robust Similarity Learning—0
Causal Fair Metric: Bridging Causality, Individual Fairness, and Adversarial Robustness—0
Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot FillingCode0
Show:102550
← PrevPage 4 of 33Next →
All datasetsCARS196Stanford Online ProductsCUB-200-2011In-ShopDyML-AnimalDyML-ProductDyML-Vehicle

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Unicom+ViT-L@336pxR@198.2—Unverified
2Hyp-DINO 8x8R@192.8—Unverified
3ResNet-50 + AVSLR@191.5—Unverified
4NEDR@191.5—Unverified
5ResNet-50 + Intra-Batch (ensemble of 5)R@191.5—Unverified
6EfficientDML-VPTSP-G/512R@191.2—Unverified
7CCL (ResNet-50)R@191.02—Unverified
8ResNet50 + LanguageR@190.2—Unverified
9ResNet-50 + MetrixR@189.6—Unverified
10ResNet50 + S2SDR@189.5—Unverified
#ModelMetricClaimedVerifiedStatus
1Unicom+ViT-L@336pxR@191.2—Unverified
2STIRR@188.3—Unverified
3Recall@k Surrogate Loss (ViT-B/16)R@188—Unverified
4ViT-TripletR@186.5—Unverified
5ROADMAP (DeiT-S)R@186—Unverified
6Hyp-ViTR@185.9—Unverified
7Hyp-DINOR@185.1—Unverified
8Recall@k Surrogate Loss (ViT-B/32)R@185.1—Unverified
9CCL (ResNet-50)R@183.1—Unverified
10ROADMAP (ResNet-50)R@183.1—Unverified
#ModelMetricClaimedVerifiedStatus
1Unicom+ViT-L@336pxR@190.1—Unverified
2EfficientDML-VPTSP-G/512R@188.5—Unverified
3Hyp-ViTR@185.6—Unverified
4Hyp-DINOR@180.9—Unverified
5NEDR@174.9—Unverified
6CCL (ResNet-50)R@173.45—Unverified
7ResNet-50 + AVSLR@171.9—Unverified
8ResNet-50 + Intra-Batch ConnectionsR@171.8—Unverified
9ResNet50 + LanguageR@171.4—Unverified
10ResNet-50 + MetrixR@171.4—Unverified
#ModelMetricClaimedVerifiedStatus
1Unicom+ViT-L@336pxR@196.7—Unverified
2STIRR@195—Unverified
3MGAR@194.3—Unverified
4Hyp-ViTR@192.5—Unverified
5Hyp-DINOR@192.4—Unverified
6CCL (ResNet-50)R@192.31—Unverified
7Gradient SurgeryR@192.21—Unverified
8ResNet-50 + MetrixR@192.2—Unverified
9EfficientDML-VPTSP-G/512R@192.1—Unverified
10ViT-TripletR@192.1—Unverified
#ModelMetricClaimedVerifiedStatus
1HAPPIERAverage-mAP43.8—Unverified
2CSLAverage-mAP31—Unverified
#ModelMetricClaimedVerifiedStatus
1HAPPIERAverage-mAP38—Unverified
2CSLAverage-mAP28.7—Unverified
#ModelMetricClaimedVerifiedStatus
1HAPPIERAverage-mAP37—Unverified
2CSLAverage-mAP12.1—Unverified