the archive

#metric learning

10 results

cs.IR2019

Personalized Music Recommendation with Triplet Network

Haoting Liang, Donghuo Zeng, Yi Yu +1

The paper proposes a triplet neural network that uses positive and negative samples to learn user and item representations and a distance measure for personalized music recommendat…

#music recommendation#triplet network#representation learning#cold start

cs.CV2019

Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings

Pierre Jacob, David Picard, Aymeric Histace +1

The paper introduces HORDE, a distribution-aware regularizer that reduces scattering of deep image features by enforcing locally consistent feature distributions, improving metric…

#metric learning#deep embeddings#regularization#image retrieval

cs.CV2019

Multiple Riemannian Manifold-valued Descriptors based Image Set Classification with Multi-Kernel Metric Learning

Rui Wang, XiaoJun Wu, Josef Kittler

The paper proposes a method that represents each image set simultaneously by covariance matrices, linear subspaces, and Gaussian distributions, maps these manifold-valued descripto…

#image set classification#riemannian manifolds#multi-kernel learning#metric learning

cs.CV2019

Attention Control with Metric Learning Alignment for Image Set-based Recognition

Xiaofeng Liu, Zhenhua Guo, Jane You +1

The paper proposes a reinforcement‑learning based attention control network that models dependencies among unordered images in a set for face verification and identification, and i…

#face recognition#image set recognition#attention control#reinforcement learning

cs.LG2019

Learning to Generalize to Unseen Tasks with Bilevel Optimization

Hayeon Lee, Donghyun Na, Hae Beom Lee +1

The paper introduces L2G, a bilevel optimization framework that explicitly encourages metric‑based meta‑learning models to generalize to unseen classification tasks, leading to imp…

#meta-learning#few-shot classification#metric learning#bilevel optimization

cs.CV2019

Learning a Unified Embedding for Visual Search at Pinterest

Andrew Zhai, Hao-Yu Wu, Eric Tzeng +2

The paper presents a multi‑task deep metric learning system that learns a single unified image embedding for Pinterest’s visual search and recommendation products, handling diverse…

#visual search#image embedding#multi-task learning#metric learning

cs.CV2019

Improved Hard Example Mining by Discovering Attribute-based Hard Person Identity

Xiao Wang, Ziliang Chen, Rui Yang +2

The paper proposes Hard Person Identity Mining (HPIM), which uses attribute-based probabilistic descriptions and statistical moment discrepancies to identify hard identities for mo…

#person re-identification#hard example mining#attribute learning#deep learning

cs.LG2019

Nonparametric Contextual Bandits in an Unknown Metric Space

Nirandika Wanigasekara, Christina Lee Yu

The paper proposes an algorithm for contextual multi-armed bandits where each arm’s reward function is nonparametric and the similarity structure among arms is unknown, learning th…

#contextual bandits#nonparametric learning#metric learning#adaptive partitioning

cs.CV2019

Deep Metric Transfer for Label Propagation with Limited Annotated Data

Bin Liu, Zhirong Wu, Han Hu +1

The paper introduces a framework that transfers similarity metrics from related domains to propagate labels from a few annotated examples to large unlabeled image collections, impr…

#few-shot learning#semi-supervised learning#label propagation#metric learning

cs.CV2019

Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrieval

Binghui Chen, Weihong Deng

The paper introduces a Decoupled Metric Learning framework that splits the metric into object‑attention and channel‑attention components to improve discrimination and generalizatio…

#zero-shot image retrieval#metric learning#attention mechanisms#graph propagation