Papers Metric Learning
“Metric Learning” 태그가 달린 논문 1,753편 · 필터 해제
Hyperbolic Geometry for Open-World Object Detection in Remote Sensing Imagery
Open-world object detection (OWOD) extends closed-set detection by requiring models to identify unknown objects and incrementally learn them once annotations become available. In remote sensing imagery, object categories…
Incremental LearningObject DetectionMetric LearningFew-Shot Video Recognition via Hierarchical Metric Learning
Few-shot action recognition (FSAR) aims to recognize unseen action categories with only a small number of annotated video samples. Recent works typically apply single-prototype supervision at the network output and fail …
Action RecognitionMetric LearningDynamic Frechet Regression with Feature Selection for Distributional Data
Many scientific and engineering applications generate responses that are not scalars or vectors, but statistical objects whose form evolves over an ordered index such as time, depth. Probability distributions are a promi…
Metric LearningLarge-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition
Personality recognition has traditionally been constrained by theory-dependent formulations, where models are trained to fit predefined psychological taxonomies rather than uncovering shared underlying behavioral structu…
Metric LearningConservative Subject Invariant EMG-based Gesture Recognition
Cross-subject generalization remains a fundamental challenge in surface electromyography (sEMG)-based gesture recognition. Although deep learning methods have improved within-subject performance, they often rely on subje…
Gesture RecognitionMetric LearningMABLE: Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning
We propose MABLE (Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning), a self-supervised framework for learning node and graph embeddings from large, heterogeneous graphs, demonstrate…
Metric LearningCouCE: A Unified Causal Framework for Debiased Deep Metric Learning
Deep Metric Learning (DML) often struggles with zero-shot generalization because standard objectives inherently capture what co-occurs rather than what causes similarity. Consequently, DML models are vulnerable to shortc…
Zero-shot GeneralizationMetric LearningHalfNet: Randomized Neural Networks with Learned Subspace Geometry
Many researchers investigated neural networks with some of their weights fixed to values randomly drawn from a given distribution, e.g., $N(0, I)$. Our proposed HalfNet draws random weights from $N(0, Σ)$, where $Σ$, whi…
Metric LearningST-ColoNet: Spatio-Temporal Colon Segment Recognition via Hybrid Attention and Edge-Guided Feature Learning
Colo-segment recognition in colonoscopy videos is a key requirement for many downstream tasks, but existing automatic recognition methods only use colonoscopy images without fully exploiting the use of temporal informati…
Metric LearningThe Matching Principle: A Geometric Theory of Loss Functions for Nuisance-Robust Representation Learning
Robustness, domain adaptation, photometric/occlusion invariance, sensor drift, and alignment style are treated as separate literatures with separate method families. Under label-preserving deployment shift they share one…
Representation LearningDomain AdaptationMetric LearningWhen Latent Geometry Is Not Enough: Draft-Conditioned Latent Refinement for Non-Autoregressive Text Generation
Continuous diffusion and flow models are attractive for non-autoregressive text generation because they can update all positions in parallel. A major difficulty is the interface between continuous latent states and discr…
Text GenerationMetric LearningRAPT: Retrieval-Augmented Post-hoc Thresholding for Multi-Label Classification
Industrial multi-label document understanding pipelines score candidate labels and threshold or rank them to form a label set per document. This early selection step directly affects the accuracy of downstream informatio…
Multi-Label ClassificationInformation ExtractionMetric LearningMARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection
Software vulnerability detection is critical for ensuring software security and reliability. Despite recent advances in deep learning, real-world vulnerability datasets suffer from two severe challenges: frequency imbala…
Vulnerability DetectionMetric LearningConditional anomaly detection methods for patient-management alert systems
Anomaly detection methods can be very useful in identifying unusual or interesting patterns in data. A recently proposed conditional anomaly detection framework extends anomaly detection to the problem of identifying ano…
Anomaly DetectionMetric LearningEnhancing Federated Quadruplet Learning: Stochastic Client Selection and Embedding Stability Analysis
Federated Learning (FL) enables decentralised model training across distributed clients without requiring data centralisation. However, the generalisation performance of the global model is usually degraded by data heter…
Federated LearningMetric LearningDPM++: Dynamic Masked Metric Learning for Occluded Person Re-identification
Although person re-identification has made impressive progress, occlusion caused by obstacles remains an unsettled issue in real applications. The difficulty lies in the mismatch between incomplete occluded samples and h…
Person Re-IdentificationData AugmentationMetric LearningQuantifying Multimodal Capabilities: Formal Generalization Guarantees in Pairwise Metric Learning
Multimodal learning leverages the integration of diverse data modalities to enhance performance in complex tasks. Yet, it frequently encounters incomplete or redundant modality data in real-world scenarios. This paper pr…
Metric LearningDistance metric learning for conditional anomaly detection
Anomaly detection methods can be very useful in identifying unusual or interesting patterns in data. A recently proposed conditional anomaly detection framework extends anomaly detection to the problem of identifying ano…
Anomaly DetectionMetric LearningGeneralized Disguise Makeup Presentation Attack Detection Using an Attention-Guided Patch-Based Framework
Despite significant advances in facial recognition systems, they remain vulnerable to face presentation attacks. Among them, disguise makeup attacks are particularly challenging, as they use advanced cosmetics, prostheti…
Metric LearningLayout-Aware Representation Learning for Open-Set ID Fraud Discovery
Identity-document fraud detection is not a stationary binary classification problem. Adaptive attackers modify templates and fabrication pipelines, making historical fraud labels stale, and successful forgeries recur at …
Representation LearningBinary ClassificationFraud DetectionMetric Learning