Multilayer Dense Connections for Hierarchical Concept Classification

03/19/2020
by   Toufiq Parag, et al.
0

Classification is a pivotal function for many computer vision tasks such as object classification, detection, scene segmentation. Multinomial logistic regression with a single final layer of dense connections has become the ubiquitous technique for CNN-based classification. While these classifiers learn a mapping between the input and a set of output category classes, they do not typically learn a comprehensive knowledge about the category. In particular, when a CNN based image classifier correctly identifies the image of a Chimpanzee, it does not know that it is a member of Primate, Mammal, Chordate families and a living thing. We propose a multilayer dense connectivity for a CNN to simultaneously predict the category and its conceptual superclasses in hierarchical order. We experimentally demonstrate that our proposed dense connections, in conjunction with popular convolutional feature layers, can learn to predict the conceptual classes with minimal increase in network size while maintaining the categorical classification accuracy.

READ FULL TEXT

page 2

page 12

research
09/28/2017

B-CNN: Branch Convolutional Neural Network for Hierarchical Classification

Convolutional Neural Network (CNN) image classifiers are traditionally d...
research
04/09/2018

HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentation

Recently, dense connections have attracted substantial attention in comp...
research
06/03/2019

Hierarchical Auxiliary Learning

Conventional application of convolutional neural networks (CNNs) for ima...
research
04/30/2018

Towards Deeper Generative Architectures for GANs using Dense connections

In this paper, we present the result of adopting skip connections and de...
research
07/23/2017

Detecting and Grouping Identical Objects for Region Proposal and Classification

Often multiple instances of an object occur in the same scene, for examp...
research
07/05/2018

Logistic Regression, Neural Networks and Dempster-Shafer Theory: a New Perspective

We revisit logistic regression and its nonlinear extensions, including m...
research
11/17/2022

DeepVoxNet2: Yet another CNN framework

We know that both the CNN mapping function and the sampling scheme are o...

Please sign up or login with your details

Forgot password? Click here to reset