paper-with-me

Papers

DeepKSPD: Learning Kernel-matrix-based SPD Representation for Fine-grained Image Recognition

2017-11-11 · ECCV 2018 9 · Melih Engin, Lei Wang, Luping Zhou, Xinwang Liu

Being symmetric positive-definite (SPD), covariance matrix has traditionally been used to represent a set of local descriptors in visual recognition. Recent study shows that kernel matrix can give considerably better representation by modelling the nonlinearity in the local descriptor set. Nevertheless, neither the descriptors nor the kernel matrix is deeply learned. Worse, they are considered separately, hindering the pursuit of an optimal SPD representation. This work proposes a deep network that jointly learns local descriptors, kernel-matrix-based SPD representation, and the classifier via an end-to-end training process. We derive the derivatives for the mapping from a local descriptor set to the SPD representation to carry out backpropagation. Also, we exploit the Daleckii-Krein formula in operator theory to give a concise and unified result on differentiating SPD matrix functions, including the matrix logarithm to handle the Riemannian geometry of kernel matrix. Experiments not only show the superiority of kernel-matrix-based SPD representation with deep local descriptors, but also verify the advantage of the proposed deep network in pursuing better SPD representations for fine-grained image recognition tasks.

📄 PDF Abstract BibTeX arXiv:1711.04047

Code (0)

등록된 구현이 없습니다.

Tasks

Fine-Grained Image Recognition

Similar Papers 제목 키워드 기반

Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM

2023-10-07 · Luoming Zhang, Wen Fei, Weijia Wu, Yefei He 외

Large Language Models (LLMs) pose significant hardware challenges related to memory requirements and computational ability. There are two mainstream quantization schemes for LLMs: coarse-grained ($\textit{e.g.,}$ channel…

Quantization

AKBR: Learning Adaptive Kernel-based Representations for Graph Classification

2024-03-24 · Feifei Qian, Lixin Cui, Ming Li, Yue Wang 외

In this paper, we propose a new model to learn Adaptive Kernel-based Representations (AKBR) for graph classification. Unlike state-of-the-art R-convolution graph kernels that are defined by merely counting any pair of is…

Graph ClassificationRepresentation Learning

Class Mean Vector Component and Discriminant Analysis

2018-12-14 · Alexandros Iosifidis

The kernel matrix used in kernel methods encodes all the information required for solving complex nonlinear problems defined on data representations in the input space using simple, but implicitly defined, solutions. Spe…

Dimensionality Reduction

Low-rank Kernel Learning for Graph-based Clustering

2019-03-14 · Zhao Kang, Liangjian Wen, Wenyu Chen, Zenglin Xu

Constructing the adjacency graph is fundamental to graph-based clustering. Graph learning in kernel space has shown impressive performance on a number of benchmark data sets. However, its performance is largely determine…

Clusteringgraph constructionGraph Learning

Adaptive Graph via Multiple Kernel Learning for Nonnegative Matrix Factorization

2012-08-19 · Jing-Yan Wang, Mustafa Abduljabbar

Nonnegative Matrix Factorization (NMF) has been continuously evolving in several areas like pattern recognition and information retrieval methods. It factorizes a matrix into a product of 2 low-rank non-negative matrices…

ClusteringInformation RetrievalRetrieval