Kernelized Deep Convolutional Neural Network for Describing Complex Images

09/15/2015
by   Zhen Liu, et al.
0

With the impressive capability to capture visual content, deep convolutional neural networks (CNN) have demon- strated promising performance in various vision-based ap- plications, such as classification, recognition, and objec- t detection. However, due to the intrinsic structure design of CNN, for images with complex content, it achieves lim- ited capability on invariance to translation, rotation, and re-sizing changes, which is strongly emphasized in the s- cenario of content-based image retrieval. In this paper, to address this problem, we proposed a new kernelized deep convolutional neural network. We first discuss our motiva- tion by an experimental study to demonstrate the sensitivi- ty of the global CNN feature to the basic geometric trans- formations. Then, we propose to represent visual content with approximate invariance to the above geometric trans- formations from a kernelized perspective. We extract CNN features on the detected object-like patches and aggregate these patch-level CNN features to form a vectorial repre- sentation with the Fisher vector model. The effectiveness of our proposed algorithm is demonstrated on image search application with three benchmark datasets.

READ FULL TEXT

page 3

page 4

page 7

research
04/24/2015

Object Level Deep Feature Pooling for Compact Image Representation

Convolutional Neural Network (CNN) features have been successfully emplo...
research
03/31/2016

Large Scale Deep Convolutional Neural Network Features Search with Lucene

In this work, we propose an approach to index Deep Convolutional Neural ...
research
11/28/2019

Patch Reordering: a Novel Way to Achieve Rotation and Translation Invariance in Convolutional Neural Networks

Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art ...
research
05/11/2018

A volumetric deep Convolutional Neural Network for simulation of dark matter halo catalogues

For modern large-scale structure survey techniques it has become standar...
research
07/16/2019

Caching as an Image Characterization Problem using Deep Convolutional Neural Networks

Optimizing caching locations of popular content has received significant...
research
11/21/2014

Understanding image representations by measuring their equivariance and equivalence

Despite the importance of image representations such as histograms of or...
research
07/05/2020

Deep Convolutional Neural Network for Identifying Seam-Carving Forgery

Seam carving is a representative content-aware image retargeting approac...

Please sign up or login with your details

Forgot password? Click here to reset