TY - GEN
T1 - Detectors++
T2 - 8th IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2021
AU - Akhyar, Fityanul
AU - Lin, Chih Yang
AU - Kathiresan, Gugan S.
AU - Surianarayanan, Bharath
AU - Hsu, Chao Yung
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Focusing on the task of steel surface defect localization, this study employs the latest state-of-the-art RCNN family, Cascade RCNN, on top of the current FPN model called DetectoRS-ResNeXt. The baseline was tested individually using Side Aware Boundary Localization (SABL) plus pixel domain augmentation to obtain the precision of predictions. Trained on a well-known real-world dataset, Severstal, our proposal achieves a mAP of 82.5% which offers the potential to serve as a high-quality defect detection baseline.
AB - Focusing on the task of steel surface defect localization, this study employs the latest state-of-the-art RCNN family, Cascade RCNN, on top of the current FPN model called DetectoRS-ResNeXt. The baseline was tested individually using Side Aware Boundary Localization (SABL) plus pixel domain augmentation to obtain the precision of predictions. Trained on a well-known real-world dataset, Severstal, our proposal achieves a mAP of 82.5% which offers the potential to serve as a high-quality defect detection baseline.
UR - http://www.scopus.com/inward/record.url?scp=85123055335&partnerID=8YFLogxK
U2 - 10.1109/ICCE-TW52618.2021.9603063
DO - 10.1109/ICCE-TW52618.2021.9603063
M3 - 會議論文篇章
AN - SCOPUS:85123055335
T3 - 2021 IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2021
BT - 2021 IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 15 September 2021 through 17 September 2021
ER -