Borrow from Anywhere: Pseudo Multi-modal Object Detection in Thermal Imagery

Devaguptapu, Chaitanya and Ninad, Akolekar and Manuj M, Sharma and Balasubramanian, Vineeth N (2019) Borrow from Anywhere: Pseudo Multi-modal Object Detection in Thermal Imagery. arXiv. pp. 1-10.

1905.08789.pdf - Accepted Version

Download (2MB) | Preview


Can we improve detection in the thermal domain by borrowing features from rich domains like visual RGB? In this paper, we propose a ‘pseudo-multimodal’ object detector trained on natural image domain data to help improve the performance of object detection in thermal images. We assume access to a large-scale dataset in the visual RGB domain and relatively smaller dataset (in terms of instances) in the thermal domain, as is common today. We propose the use of well-known image-to-image translation frameworks to generate pseudo-RGB equivalents of a given thermal image and then use a multi-modal architecture for object detection in the thermal image. We show that our framework outperforms existing benchmarks without the explicit need for paired training examples from the two domains. We also show that our framework has the ability to learn with less data from thermal domain when using our approach

[error in script]
IITH Creators:
IITH CreatorsORCiD
Balasubramanian, Vineeth NUNSPECIFIED
Item Type: Article
Subjects: Computer science
Divisions: Department of Computer Science & Engineering
Depositing User: Team Library
Date Deposited: 06 Jun 2019 11:52
Last Modified: 06 Jun 2019 11:54
Publisher URL:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 5444 Statistics for this ePrint Item