Recognizing Image Objects by Relational Analysis Using Heterogeneous Superpixels and Deep Convolutional Features

08/02/2019
by   Alex Yang, et al.
1

Superpixel-based methodologies have become increasingly popular in computer vision, especially when the computation is too expensive in time or memory to perform with a large number of pixels or features. However, rarely is superpixel segmentation examined within the context of deep convolutional neural network architectures. This paper presents a novel neural architecture that exploits the superpixel feature space. The visual feature space is organized using superpixels to provide the neural network with a substructure of the images. As the superpixels associate the visual feature space with parts of the objects in an image, the visual feature space is transformed into a structured vector representation per superpixel. It is shown that it is feasible to learn superpixel features using capsules and it is potentially beneficial to perform image analysis in such a structured manner. This novel deep learning architecture is examined in the context of an image classification task, highlighting explicit interpretability (explainability) of the network's decision making. The results are compared against a baseline deep neural model, as well as among superpixel capsule networks with a variety of hyperparameter settings.

READ FULL TEXT

page 1

page 2

page 5

page 8

page 9

research
04/20/2020

Invariant Integration in Deep Convolutional Feature Space

In this contribution, we show how to incorporate prior knowledge to a de...
research
06/26/2018

Deep Feature Factorization For Concept Discovery

We propose Deep Feature Factorization (DFF), a method capable of localiz...
research
10/16/2021

An Acceleration Method Based on Deep Learning and Multilinear Feature Space

Computer vision plays a crucial role in Advanced Assistance Systems. Mos...
research
05/21/2017

Large-Scale Classification of Structured Objects using a CRF with Deep Class Embedding

This paper presents a novel deep learning architecture to classify struc...
research
10/27/2020

Structured Visual Search via Composition-aware Learning

This paper studies visual search using structured queries. The structure...
research
11/15/2018

Exploring the Deep Feature Space of a Cell Classification Neural Network

In this paper, we present contemporary techniques for visualising the fe...
research
12/09/2020

Automatic Diagnosis of Malaria from Thin Blood Smear Images using Deep Convolutional Neural Network with Multi-Resolution Feature Fusion

Malaria, a life-threatening disease, infects millions of people every ye...

Please sign up or login with your details

Forgot password? Click here to reset