NDLI: Mixture separability loss in a deep convolutional network for image classification

Content Provider	IET Digital Library
Author	Do, Trung Dung Jin, Cheng Bin Nguyen, Van Huan Kim, Hakil
Abstract	In machine learning, the cost function is crucial because it measures how good or bad a system is. In image classification, well-known networks only consider modifying the network structures and applying cross-entropy loss at the end of the network. However, using only cross-entropy loss causes a network to stop updating weights when all training images are correctly classified. This is the problem of early saturation. This study proposes a novel cost function, called mixture separability loss (MSL), which updates the weights of the network even when most of the training images are accurately predicted. MSL consists of between-class and within-class loss. Between-class loss maximises the differences between inter-class images, whereas within-class loss minimises the similarities between intra-class images. They designed the proposed loss function to attach to different convolutional layers in the network in order to utilise intermediate feature maps. Experiments show that a network with MSL deepens the learning process and obtains promising results with some public datasets, such as Street View House Number, Canadian Institute for Advanced Research, and the authors’ self-collected Inha Computer Vision Lab gender dataset.
Starting Page	135
Ending Page	141
Page Count	7
ISSN	17519659
Volume Number	13
e-ISSN	17519667
Issue Number	Issue 1, Jan (2019)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/iet-ipr/13/1
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/iet-ipr.2018.5613
Journal	IET Image Processing
Publisher Date	2018-10-25
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Applying Cross-entropy Loss Between-class Loss Canadian Institute For Advanced Research Computer Vision Computer Vision And Image Processing Technique Convolutional Layer Deep Convolutional Network Entropy Feedforward Neural Network Image Classification Image Recognition Image Representation Inter-class Image Intra-class Image Knowledge Engineering Technique Learning in AI Loss Function Machine Learning Mixture Separability Loss MSL Network Structure Neural Computing Technique Novel Cost Function Self-collected Inha Computer Vision Lab Gender Dataset Street View House Number Training Image Well-known Network Within-class Loss
Content Type	Text
Resource Type	Article
Subject	Signal Processing Electrical and Electronic Engineering Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Flower classification using deep convolutional neural networks

Improved deep face identification with multi-class pairwise discriminant loss

Deep learning-based approach to latent overlapped fingerprints mask segmentation

Deep learning approach to generate offline handwritten signatures based on online samples

Image ordinal classification with deep multi-view learning

Learning pairwise SVM on hierarchical deep features for ear recognition

Mixture separability loss in a deep convolutional network for image classification

Improved softmax loss for deep learning-based face and expression recognition

Chinese vehicle license plate recognition using kernel-based extreme learning machine with deep convolutional features

Mixture separability loss in a deep convolutional network for image classification

Similar Documents

Flower classification using deep convolutional neural networks

Improved deep face identification with multi-class pairwise discriminant loss

Deep learning-based approach to latent overlapped fingerprints mask segmentation

Deep learning approach to generate offline handwritten signatures based on online samples

Image ordinal classification with deep multi-view learning

Learning pairwise SVM on hierarchical deep features for ear recognition

Mixture separability loss in a deep convolutional network for image classification

Improved softmax loss for deep learning-based face and expression recognition

Chinese vehicle license plate recognition using kernel-based extreme learning machine with deep convolutional features

Mixture separability loss in a deep convolutional network for image classification