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

Weighted Robinson Compass Gradient and Charbonnier Penalty Function as a Loss Function

Rachna, U and Dhruv Shindhe, S and Omkar, SN (2022) Weighted Robinson Compass Gradient and Charbonnier Penalty Function as a Loss Function. In: 7th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2022, 1-3 December 2022, Mangalore, pp. 132-137.

[img] PDF
icraie_2022.pdf - Published Version
Restricted to Registered users only

Download (4MB) | Request a copy
Official URL: https://doi.org/10.1109/ICRAIE56454.2022.10054293

Abstract

Loss function quantifies how well a machine learning model is performing, it computes the difference between the ground truth and the reconstructed outcomes. In image processing tasks such as image dehazing, image deblurring and image denoising the most popular loss functions used are Mean Squared error(MSE) and perceptual loss. MSE is less computationally expensive but fails to recreate precise boundaries whereas perceptual loss is more computationally expensive as they use feature vectors from a pre-trained model like VGG-net. In smaller on the edge systems like autonomous navigation systems, one of the most critical tasks is relying on visual cues, the take in the video feed from the environment and make decision on it after a few prepossessing steps to eliminate things like physical barriers, blurr, and smoke that clutter a robot's environment are one of the several factors that affect autonomous navigation. We need systems that aren't computationally expensive but also have a good reconstruction. For this we propose a loss function that incorporates gradients along with MSE for faster and better reconstruction. © 2022 IEEE.

Item Type: Conference Paper
Publication: 7th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2022 - Proceedings
Publisher: Institute of Electrical and Electronics Engineers Inc.
Additional Information: The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc.
Keywords: Demulsification; Image denoising; Image enhancement; Mean square error; Navigation systems; Robots, Dehazing; Ground truth; Image deblurring; Image dehazing; Images processing; Loss functions; Machine learning models; Mean squared error; Penalty function; Robinson, Smoke
Department/Centre: Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering)
Date Deposited: 28 Mar 2023 09:44
Last Modified: 28 Mar 2023 09:44
URI: https://eprints.iisc.ac.in/id/eprint/81197

Actions (login required)

View Item View Item