ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Effects of Modifying the Input Features and the Loss Function on Improving Emotion Classification

Pandey, RK and Ramakrishnan, AG and Karmakar, S (2019) Effects of Modifying the Input Features and the Loss Function on Improving Emotion Classification. In: IEEE Region 10 Conference: Technology, Knowledge, and Society, TENCON 2019, 17-20 October 2019, Hotel Grand HyattKerala; India, pp. 1159-1162.

[img] PDF
TENCON 2019.pdf - Published Version
Restricted to Registered users only

Download (236kB) | Request a copy
Official URL: http://dx.doi.org/10.1109/TENCON.2019.8929485


In this work, we show that the discriminative power of a deep neural network can be improved at three different levels: (i) inputting discriminative features, (ii) designing an optimal network architecture and (iii) changing the loss function. This work suggests that only increasing the depth or the width of a deep network may not always be the best solution while requiring computationally efficient models. Here, we show that there is scope for improving the classifier accuracy at each of the three levels. We have carried out all our experiments on the FERplus dataset and show that the facial emotion recognition accuracy can be independently improved up to 2.5 by adding better features, 1.8 by modifying the loss function and up to 3.1 by combining the two ideas. In separate experiments, we show that the computational complexity can be reduced by a factor of 24.3, while simultaneously increasing the FER by 0.95 by modifying the architecture of the model, input features and the loss function. © 2019 IEEE.

Item Type: Conference Paper
Publication: IEEE Region 10 Annual International Conference, Proceedings/TENCON
Publisher: Institute of Electrical and Electronics Engineers Inc.
Additional Information: Copyright of this article belongs to IEEE
Keywords: Deep neural networks, Computationally efficient; Discriminative features; Discriminative power; Emotion classification; Facial emotions; Input features; Loss functions; Optimal network architecture, Network architecture
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 25 Feb 2020 10:34
Last Modified: 25 Feb 2020 10:34
URI: http://eprints.iisc.ac.in/id/eprint/64439

Actions (login required)

View Item View Item