paper-with-me

홈 › Papers

Working hard to know your neighbor's margins: Local descriptor learning loss

2017-05-30 · NeurIPS 2017 12 · Anastasiya Mishchuk, Dmytro Mishkin, Filip Radenovic, Jiri Matas

We introduce a novel loss for learning local feature descriptors which is inspired by the Lowe's matching criterion for SIFT. We show that the proposed loss that maximizes the distance between the closest positive and closest negative patch in the batch is better than complex regularization methods; it works well for both shallow and deep convolution network architectures. Applying the novel loss to the L2Net CNN architecture results in a compact descriptor -- it has the same dimensionality as SIFT (128) that shows state-of-art performance in wide baseline stereo, patch verification and instance retrieval benchmarks. It is fast, computing a descriptor takes about 1 millisecond on a low-end GPU.

📄 PDF Abstract BibTeX arXiv:1705.10872

Code (4)

DagnyT/hardnet 공식 구현 pytorch
empty16/hardnet.pytorch pytorch
kornia/kornia pytorch
oskyhn/CNNs-Without-Borders pytorch

Tasks

GPUImage RetrievalPatch MatchingRetrieval

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory (and its Loss' Convexity is Dispensable)

2025-07-10 · Wenxuan Zhou, Shujian Zhang, Brice Magdalou, John Lambert 외 arxiv

Normative theories allow one to elicit key parts of a ML algorithm from first principles, which is crucial at a time of championed scrutiny for ML work. Direct Preference Optimization (DPO) cleverly bypasses reward model…

Unleashing Graph Partitioning for Large-Scale Nearest Neighbor Search

2024-03-04 · Lars Gottesbüren, Laxman Dhulipala, Rajesh Jayaram, Jakub Lacki

We consider the fundamental problem of decomposing a large-scale approximate nearest neighbor search (ANNS) problem into smaller sub-problems. The goal is to partition the input points into neighborhood-preserving shards…

graph partitioning

Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class Discovery

2023-01-01 · CVPR 2023 1 · Muli Yang, Liancheng Wang, Cheng Deng, Hanwang Zhang

Novel Class Discovery (NCD) aims to discover unknown classes without any annotation, by exploiting the transferable knowledge already learned from a base set of known classes. Existing works hold an impractical assum…

Novel Class Discovery

A Center in Your Neighborhood: Fairness in Facility Location

2019-08-23 · Christopher Jung, Sampath Kannan, Neil Lutz

When selecting locations for a set of facilities, standard clustering algorithms may place unfair burden on some individuals and neighborhoods. We formulate a fairness concept that takes local population densities into a…

ClusteringFairness

Teaching Yourself: Graph Self-Distillation on Neighborhood for Node Classification

2022-10-05 · Lirong Wu, Jun Xia, Haitao Lin, Zhangyang Gao 외

Recent years have witnessed great success in handling graph-related tasks with Graph Neural Networks (GNNs). Despite their great academic success, Multi-Layer Perceptrons (MLPs) remain the primary workhorse for practical…

ClassificationNode Classification