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

  title={Impact of Fully Connected Layers on Performance of Convolutional Neural Networks for Image Classification},
  author={S. H. Shabbeer Basha and S. Dubey and Viswanath Pulabaigari and Snehasis Mukherjee},
  • S. H. Shabbeer Basha, S. Dubey, +1 author Snehasis Mukherjee
  • Published 2020
  • Computer Science, Engineering, Mathematics
  • ArXiv
  • 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… CONTINUE READING
    20 Citations
    AutoFCL: Automatically Tuning Fully Connected Layers for Transfer Learning
    • 1
    • PDF
    On the Performance of Convolutional Neural Networks under High and Low Frequency Information
    DenseNet Models for Tiny ImageNet Classification
    Person Re-Identification via Group Symmetry Theory
    Artificial Intelligence Image Recognition Method Based on Convolutional Neural Network Algorithm
    Bibliometric Analysis of the Application of Convolutional Neural Network in Computer Vision
    Analyzing Malaria Disease Using Effective Deep Learning Approach


    Very deep convolutional neural network based image classification using small training sample size
    • Shuying Liu, W. Deng
    • Computer Science
    • 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)
    • 2015
    • 184
    • Highly Influential
    ImageNet classification with deep convolutional neural networks
    • 55,155
    • Highly Influential
    • PDF
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 41,287
    • PDF
    Going deeper with convolutions
    • 20,857
    • Highly Influential
    • PDF
    A systematic study of the class imbalance problem in convolutional neural networks
    • 534
    • PDF
    Overfitting remedy by sparsifying regularization on fully-connected layers of CNNs
    • 19
    Deep Residual Learning for Image Recognition
    • 53,640
    • PDF
    Tiny ImageNet Challenge
    • 7
    • Highly Influential
    • PDF
    Visualizing and Understanding Convolutional Networks
    • 8,595
    • Highly Influential
    • PDF
    The Do’s and Don’ts for CNN-Based Face Verification
    • 63
    • Highly Influential
    • PDF