Název:	Designing a Lightweight Edge-Guided Convolutional Neural Network for Segmenting Mirrors and Reflective Surfaces
Autoři:	Gonzales, Mark Edward M. Uy, Lorene C. Ilao, Joel P.
Citace zdrojového dokumentu:	WSCG 2023: full papers proceedings: 1. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 107-116.
Datum vydání:	2023
Nakladatel:	Václav Skala - UNION Agency
Typ dokumentu:	konferenční příspěvek conferenceObject
URI:	http://hdl.handle.net/11025/54416
ISBN:	978-80-86943-32-9
ISSN:	2464–4617 (print) 2464–4625 (CD/DVD)
Klíčová slova:	zrcadlová segmentace;detekce objektu;konvoluční neuronové sítě;prořezávání CNN filtru
Klíčová slova v dalším jazyce:	mirror segmentation;object detection;convolutional neural network;CNN filter pruning
Abstrakt v dalším jazyce:	The detection of mirrors is a challenging task due to their lack of a distinctive appearance and the visual similarity of reflections with their surroundings. While existing systems have achieved some success in mirror segmentation, the design of lightweight models remains unexplored, and datasets are mostly limited to clear mirrors in indoor scenes. In this paper, we propose a new dataset consisting of 454 images of outdoor mirrors and reflective surfaces. We also present a lightweight edge-guided convolutional neural network based on PMDNet. Our model uses EfficientNetV2-Medium as its backbone and employs parallel convolutional layers and a lightweight convolutional block attention module to capture both low-level and high-level features for edge extraction. It registered Fβ scores of 0.8483, 0.8117, and 0.8388 on the Mirror Segmentation Dataset (MSD), Progressive Mirror Detection (PMD) dataset, and our proposed dataset, respectively. Applying filter pruning via geometric median resulted in Fβ scores of 0.8498, 0.7902, and 0.8456, respectively, performing competitively with the state-of-the-art PMDNet but with 78.20× fewer floating-point operations per second and 238.16× fewer parameters. The code and dataset are available at https://github.com/memgonzales/mirror-segmentation.
Práva:	© Václav Skala - UNION Agency
Vyskytuje se v kolekcích:	WSCG 2023: Full Papers Proceedings

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.