Impact of Fully Connected Layers on Performance of Convolutional Neural Networks for Image Classification

By S. H. Shabbeer Basha, Shiv Ram Dubey, Viswanath Pulabaigari, Snehasis Mukherjee. Neurocomputing, 2019

496 citations recorded by the source corpus.

Abstract The Convolutional Neural Networks (CNNs), in domains like computer vision, mostly reduced the need for handcrafted features due to its ability to learn the problem-specific features from the raw input data. However, the selection of dataset-specific CNN architecture, which mostly performed by either experience or expertise is a time-consuming and error-prone process. To automate the process of learning a CNN architecture, this paper attempts at finding the relationship between Fully Connected (FC) layers with some of the characteristics of the datasets. The CNN architectures, and recently datasets also, are categorized as deep, shallow, wide, etc. This paper tries to formalize these terms along with answering the following questions. (i) What is the impact of deeper/shallow architectures on the performance of the CNN w.r.t. FC layers?, (ii) How the deeper/wider datasets influence the performance of CNN w.r.t. FC layers?, and (iii) Which kind of architecture (deeper/shallower) is better suitable for which kind of (deeper/wider) datasets. To address these findings, we have performed experiments with four CNN architectures having different depths. The experiments are conducted by varying the number of FC layers. We used four widely used datasets including CIFAR-10, CIFAR-100, Tiny ImageNet, and CRCHistoPhenotypes to justify our findings in the context of image classification problem. The source code of this work is available at https://github.com/shabbeersh/Impact-of-FC-layers .

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b700ac8f9e815c6bfa0e87570c49437f2baf4cb6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Bidyut Baran Chaudhuri
2. Satish Kumar Singh
3. Shiv Ram Dubey

In Computer Vision and Pattern Recognition

1. Bidyut Baran Chaudhuri
2. Satish Kumar Singh
3. Shiv Ram Dubey
4. Atlas Collaboration

Citations in the corpus

• Activation functions in deep learning: A comprehensive survey and benchmark (2021, background): “The important aspects of neural networks include weight initialization [11], loss functions [12], different layers [13], overfitting [14], and optimization [15].”