Metric Learning
8개 벤치마크 · 논문 1,753편 · 이 태스크의 논문 보기 →
Benchmarks
CARS196
Stanford Online Products
CUB-200-2011
In-Shop
CUB-200-2011
DyML-Animal
DyML-Product
DyML-Vehicle
Most implemented
In Defense of the Triplet Loss for Person Re-Identification
Matching Networks for One Shot Learning
Circle Loss: A Unified Perspective of Pair Similarity Optimization
Additive Margin Softmax for Face Verification
Revisiting Training Strategies and Generalization Performance in Deep Metric Learning
Semantic Instance Segmentation with a Discriminative Loss Function
Papers
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 Learning