• Home
  • Search
  • Hierarchical feature learning for image categorization
  • https://doi.org/10.32657/10356/65659Copy DOI Icon

Hierarchical feature learning for image categorization

  • Jan 1, 2015
  • Zhen Zuo
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Extracting informative, robust, and compact data representation (feature) has been considered as one of the key factors for good performance in computer vision, and image categorization is one of the most fundamental computer vision problems. Traditionally, hand-crafted features like SIFT and HOG have been widely used, however, these features cannot adapt to data and need to be well designed. In contrast, feature learning methods have been proposed to encode data-adaptive information in data representation, which have outperformed hand-crafted features with big gaps, and brought a rapid progress in image categorization. The goal of this thesis is to present various feature learning architectures for the problem of object/scene image categorization. In the first part of the thesis, a discriminative hierarchical feature learning framework will be presented for object image categorization. This work aims to learn non-linear transformation matrices to transform image patches to local features. Current features learned by unsupervised learning methods can hardly capture the differences between different classes, which are crucial for object categorization. To capture such information, a discriminative constraint is proposed to force the local feature patches extracted from the same categories to be locally similar, while local feature patches from different classes to be separable. In the second part, discriminative and shareable information will be encoded in features for scene image categorization. Different from object images, scene images do not have clear foreground/background. Some patterns are shared among several classes, some patterns are class-specific. While some patterns represent noisy data, which is not helpful and should be excluded. In order to encode such information, the exemplar based deep discriminative and shareable feature learning framework will be proposed to learn compact filter banks, and hierarchically transfer local image patches to features. In the third part, a class of end-to-end neural networks, called convolutional and hierarchical recurrent neural networks (C-HRNNs), will be presented for large- scale object/scene image categorization. In existing convolutional neural networks (CNNs), both convolution and pooling are locally performed for image regions separately, no contextual dependencies between different image regions have been taken into consideration. Such dependencies represent useful spatial structure information in images. In contrast, recurrent neural networks (RNNs) are well known for their capability of learning contextual dependencies of sequential data by using the recurrent (feed-back) connections. In this work, C-HRNNs aim to encode both spatial and scale dependencies among different image regions to enhance the global discriminative power of image representation. Where CNN layers are firstly processed to generate middle level features. HRNN layers are then processed to learn spatial and scale dependencies.

Similar Papers
  • Conference Article
  • Citations206

Convolutional recurrent neural networks: Learning spatial dependencies for image representation

  • Jun 01, 2015
  • Zhen Zuo +6
  • Conference Article
  • Citations6

Non-deep CNN for multi-modal image classification and feature learning: An Azure-based model

  • Dec 01, 2016
  • Sohini Roychowdhury +1
  • PDF
  • Research Article
  • Citations25

Research on improved convolutional wavelet neural network

  • Sep 09, 2021
  • Scientific Reports
  • Jingwei Liu +4
  • PDF
  • Research Article
  • Citations36

Research on Medical Data Feature Extraction and Intelligent Recognition Technology Based on Convolutional Neural Network

  • Jan 01, 2019
  • IEEE Access
  • Weidong Liu +6
  • Research Article
  • Citations81

CerCan·Net: Cervical cancer classification model via multi-layer feature ensembles of lightweight CNNs and transfer learning

  • Nov 01, 2023
  • Expert Systems with Applications
  • Omneya Attallah
  • Research Article
  • Citations82

Discriminative feature learning using a multiscale convolutional capsule network from attitude data for fault diagnosis of industrial robots

  • Jul 17, 2022
  • Mechanical Systems and Signal Processing
  • Jianyu Long +4
  • Dissertation

Multi-Modal Biometric-based Human Identification Using Deep Convolutional Siamese Neural Network

  • Jan 01, 2021
  • Hsu Aung
  • Research Article
  • Citations78

Orthogonal Representations of Object Shape and Category in Deep Convolutional Neural Networks and Human Visual Cortex

  • Feb 12, 2020
  • Scientific reports
  • Astrid A Zeman +3
  • PDF
  • Research Article
  • Citations30

Image Denoising With Deep Convolutional Neural and Multi-Directional Long Short-Term Memory Networks Under Poisson Noise Environments

  • Jan 01, 2020
  • IEEE Access
  • Wuttipong Kumwilaisak +3
  • Conference Article
  • Citations3

Assessing learned features of Deep Learning applied to EEG

  • Dec 09, 2021
  • Dung Truong +2
  • Research Article
  • Citations1

INTERPRETING CONVOLUTIONAL NEURAL NETWORKS IN POPULATION GENETICS

  • Dec 09, 2025
  • bioRxiv
  • Huiting Xu +6
  • Research Article
  • Citations7

On Classification of the Human Emotions from Facial Thermal Images: A Case Study Based on Machine Learning

  • Mar 25, 2025
  • Machine Learning and Knowledge Extraction
  • Marius Pavel +2
  • Research Article
  • Citations48

Convolutional sparse kernel network for unsupervised medical image analysis.

  • Jun 12, 2019
  • Medical Image Analysis
  • Euijoon Ahn +4
  • PDF
  • Research Article
  • Citations25

Constraint-Free Natural Image Reconstruction From fMRI Signals Based on Convolutional Neural Network.

  • Jun 22, 2018
  • Frontiers in Human Neuroscience
  • Chi Zhang +5
  • Research Article
  • Citations7

A modified U-Net convolutional neural network for segmenting periprostatic adipose tissue based on contour feature learning

  • Jan 20, 2024
  • Heliyon
  • Gang Wang +7
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.