• Home
  • Search
  • Understanding Convolutional Neural Networks in Terms of Category-Level Attributes
  • Open Access IconOpen Access
  • Cite Icon26
  • https://doi.org/10.1007/978-3-319-16808-1_25Copy DOI Icon

Understanding Convolutional Neural Networks in Terms of Category-Level Attributes

  • Jan 1, 2015
  • Makoto Ozeki +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

It has been recently reported that convolutional neural networks (CNNs) show good performances in many image recognition tasks. They significantly outperform the previous approaches that are not based on neural networks particularly for object category recognition. These performances are arguably owing to their ability of discovering better image features for recognition tasks through learning, resulting in the acquisition of better internal representations of the inputs. However, in spite of the good performances, it remains an open question why CNNs work so well and/or how they can learn such good representations. In this study, we conjecture that the learned representation can be interpreted as category-level attributes that have good properties. We conducted several experiments by using the dataset AwA (Animals with Attributes) and a CNN trained for ILSVRC-2012 in a fully supervised setting to examine this conjecture. We report that there exist units in the CNN that can predict some of the 85 semantic attributes fairly accurately, along with a detailed observation that this is true only for visual attributes and not for non-visual ones. It is more natural to think that the CNN may discover not only semantic attributes but non-semantic ones (or ones that are difficult to represent as a word). To explore this possibility, we perform zero-shot learning by regarding the activation pattern of upper layers as attributes describing the categories. The result shows that it outperforms the state-of-the-art with a significant margin.

Similar Papers
  • Research Article
  • Citations27

FitCNN: A cloud-assisted and low-cost framework for updating CNNs on IoT devices

  • Sep 10, 2018
  • Future Generation Computer Systems
  • Duo Liu +8
  • Research Article
  • Citations41

OMNI: A Framework for Integrating Hardware and Software Optimizations for Sparse CNNs

  • Sep 14, 2020
  • IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
  • Yun Liang +2
  • Conference Article
  • Citations40

Combining CNN with Hand-Crafted Features for Image Classification

  • Aug 01, 2018
  • Zhou Tianyu +2
  • Conference Article
  • Citations7

Multi-modal Information Extraction and Fusion with Convolutional Neural Networks

  • Jul 01, 2020
  • Dinesh Kumar +1
  • Book Chapter
  • Citations1

Visualizing the Behavior of Convolutional Neural Networks for Time Series Forecasting

  • Jan 01, 2021
  • Janosch Henze +1
  • PDF
  • Research Article

Low Latency Based Convolutional Recurrent Neural Network Model for Speech Command Recognition

  • Dec 16, 2021
  • Information Technology and Control
  • Chhayarani Ram Kinkar +1
  • Book Chapter

LB-CNN: Convolutional Neural Network with Latent Binarization for Large Scale Multi-class Classification

  • Nov 13, 2021
  • Timothy Reese +1
  • Research Article
  • Citations42

Automated Defect Recognition on X-ray Radiographs of Solid Propellant Using Deep Learning Based on Convolutional Neural Networks

  • Jan 28, 2021
  • Journal of Nondestructive Evaluation
  • Dhruv Gamdha +6
  • PDF
  • Research Article
  • Citations28

Convolutional Neural Network Based on Crossbar Arrays of (Co-Fe-B)x(LiNbO3)100−x Nanocomposite Memristors

  • Oct 03, 2022
  • Nanomaterials
  • Anna N Matsukatova +11
  • Conference Article
  • Citations1

DEEP LEARNING FRAMEWORK FOR WOVEN COMPOSITE ANALYSIS

  • Sep 20, 2021
  • Haotian Feng +2
  • Research Article

INTELLIGENT MODEL FOR CLASSIFYING HEMODYNAMIC PATTERNS OF BRAIN ACTIVATION TO IDENTIFY NEUROCOGNITIVE MECHANISMS OF SPATIAL-NUMERICAL ASSOCIATIONS

  • Jan 01, 2024
  • Vestnik komp'iuternykh i informatsionnykh tekhnologii
  • R G Asadullaev +1
  • PDF
  • Research Article
  • Citations520

Convolutional Neural Networks: A Survey

  • Jul 28, 2023
  • Computers
  • Moez Krichen
  • Research Article
  • Citations43

Evaluation of CNN model by comparing with convolutional autoencoder and deep neural network for crop classification on hyperspectral imagery

  • Mar 18, 2020
  • Geocarto International
  • Kavita Bhosle +1
  • Conference Article
  • Citations1

A Convolutional Hierarchical Neural Network Classifier

  • Dec 06, 2021
  • Ismail Gadzhiev +1
  • Conference Article
  • Citations35

Direction Finding Using Convolutional Neural Networks and Convolutional Recurrent Neural Networks

  • Oct 05, 2020
  • Fehmi Ayberk Uçkun +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.