Encoding CNN Activations for Writer Recognition

12/21/2017
by   Vincent Christlein, et al.
0

The encoding of local features is an essential part for writer identification and writer retrieval. While CNN activations have already been used as local features in related works, the encoding of these features has attracted little attention so far. In this work, we compare the established VLAD encoding with triangulation embedding. We further investigate generalized max pooling as an alternative to sum pooling and the impact of decorrelation and Exemplar SVMs. With these techniques, we set new standards on two publicly available datasets (ICDAR13, KHATT).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/14/2019

Deep Generalized Max Pooling

Global pooling layers are an essential part of Convolutional Neural Netw...
research
04/15/2016

Bags of Local Convolutional Features for Scalable Instance Search

This work proposes a simple instance retrieval pipeline based on encodin...
research
06/26/2018

Enhancing Sentence Embedding with Generalized Pooling

Pooling is an essential component of a wide variety of sentence represen...
research
05/30/2017

Discriminatively Learned Hierarchical Rank Pooling Networks

In this work, we present novel temporal encoding methods for action and ...
research
02/24/2017

Toward high-performance online HCCR: a CNN approach with DropDistortion, path signature and spatial stochastic max-pooling

This paper presents an investigation of several techniques that increase...
research
12/11/2020

Writer Identification and Writer Retrieval Based on NetVLAD with Re-ranking

This paper addresses writer identification and retrieval which is a chal...

Please sign up or login with your details

Forgot password? Click here to reset