Object Level Deep Feature Pooling for Compact Image Representation

04/24/2015
by   Konda Reddy Mopuri, et al.
0

Convolutional Neural Network (CNN) features have been successfully employed in recent works as an image descriptor for various vision tasks. But the inability of the deep CNN features to exhibit invariance to geometric transformations and object compositions poses a great challenge for image search. In this work, we demonstrate the effectiveness of the objectness prior over the deep CNN features of image regions for obtaining an invariant image representation. The proposed approach represents the image as a vector of pooled CNN features describing the underlying objects. This representation provides robustness to spatial layout of the objects in the scene and achieves invariance to general geometric transformations, such as translation, rotation and scaling. The proposed approach also leads to a compact representation of the scene, making each image occupy a smaller memory footprint. Experiments show that the proposed representation achieves state of the art retrieval results on a set of challenging benchmark image datasets, while maintaining a compact representation.

READ FULL TEXT

page 2

page 5

page 6

research
09/15/2015

Kernelized Deep Convolutional Neural Network for Describing Complex Images

With the impressive capability to capture visual content, deep convoluti...
research
03/30/2019

Exploiting SIFT Descriptor for Rotation Invariant Convolutional Neural Network

This paper presents a novel approach to exploit the distinctive invarian...
research
06/18/2015

A Spatial Layout and Scale Invariant Feature Representation for Indoor Scene Classification

Unlike standard object classification, where the image to be classified ...
research
08/09/2016

Mean Box Pooling: A Rich Image Representation and Output Embedding for the Visual Madlibs Task

We present Mean Box Pooling, a novel visual representation that pools ov...
research
03/15/2016

Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval

The goal of this work is the computation of very compact binary hashes f...
research
12/04/2020

An Empirical Method to Quantify the Peripheral Performance Degradation in Deep Networks

When applying a convolutional kernel to an image, if the output is to re...
research
07/24/2017

Traffic scene recognition based on deep cnn and vlad spatial pyramids

Traffic scene recognition is an important and challenging issue in Intel...

Please sign up or login with your details

Forgot password? Click here to reset