Zobrazeno 1 - 10
of 98
pro vyhledávání: '"Prahlad Vadakkepat"'
Autor:
Yiting Li, Sichao Tian, Haiyue Zhu, Yeying Jin, Keqing Wang, Jun Ma, Cheng Xiang, Prahlad Vadakkepat
Publikováno v:
Frontiers in Artificial Intelligence, Vol 7 (2024)
This study aims at addressing the challenging incremental few-shot object detection (iFSOD) problem toward online adaptive detection. iFSOD targets to learn novel categories in a sequential manner, and eventually, the detection is performed on all le
Externí odkaz:
https://doaj.org/article/4fcfa7fe9e504f388b09ea2a8e6d2980
Autor:
Wang, Jiahui, Zhu, Haiyue, Guo, Haoren, Mamun, Abdullah Al, Prahlad, Vadakkepat, Lee, Tong Heng
3D part segmentation is an essential step in advanced CAM/CAD workflow. Precise 3D segmentation contributes to lower defective rate of work-pieces produced by the manufacturing equipment (such as computer controlled CNCs), thereby improving work effi
Externí odkaz:
http://arxiv.org/abs/2207.01218
Prediction of Remaining Useful Lifetime(RUL) in the modern manufacturing and automation workplace for machines and tools is essential in Industry 4.0. This is clearly evident as continuous tool wear, or worse, sudden machine breakdown will lead to va
Externí odkaz:
http://arxiv.org/abs/2207.01219
Prediction of Remaining Useful Lifetime(RUL) in the modern manufacturing and automation workplace for machines and tools is essential in Industry 4.0. This is clearly evident as continuous tool wear, or worse, sudden machine breakdown will lead to va
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::125fb275b2d7832094987b311f729afa
http://arxiv.org/abs/2207.01219
http://arxiv.org/abs/2207.01219
Publikováno v:
Journal of Intelligent Manufacturing. 33:1665-1680
Prognostic health management minimizes system downtime and improves overall equipment effectiveness. Accurate prediction of remaining useful life (RUL) is key to prognostics. Prominent machine learning algorithms implement handcrafted feature extract
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b91681a5f04583a547645e03aabd33e5
https://doi.org/10.1007/s10845-021-01747-6
https://doi.org/10.1007/s10845-021-01747-6
Publikováno v:
IEEE Transactions on Cybernetics. 50:5099-5112
Dynamic multiobjective optimization requires the robust tracking of varying Pareto-optimal solutions (POS) in a changing environment. When a change is detected in the environment, prediction mechanisms estimate the POS by utilizing information from p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c0f57706a8385a3a8647f64a0a3386b4
https://doi.org/10.1109/tcyb.2019.2909806
https://doi.org/10.1109/tcyb.2019.2909806
Autor:
Yiting Li, Haiyue Zhu, Sichao Tian, Fan Feng, Jun Ma, Chek Sing Teo, Cheng Xiang, Prahlad Vadakkepat, Tong Heng Lee
Publikováno v:
2022 International Conference on Robotics and Automation (ICRA).
Incremental few-shot learning is highly expected for practical robotics applications. On one hand, robot is desired to learn new tasks quickly and flexibly using only few annotated training samples; on the other hand, such new additional tasks should
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b53b499565f1ca91fa753efc837a358e
https://doi.org/10.1109/icra46639.2022.9811856
https://doi.org/10.1109/icra46639.2022.9811856
Publikováno v:
IECON
In high volume production processes such as injection molding, inline inspection of parts is generally not feasible due to additional sensor requirements that incur costs. Production facilities often inspect for defective parts at the lot-level after
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9cf60c31fb46ce22d1ad7c7af5927748
https://doi.org/10.1109/iecon48115.2021.9589245
https://doi.org/10.1109/iecon48115.2021.9589245
Publikováno v:
ISIE
Path planning relies on free-space expansions. The Ray Path Finder (RPF) and RayScan algorithms solve the Euclidean shortest path problem. Both rely on free-space expansions by basing on the bug concept, which is to cast rays to a desired target and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::becba8ef7ba943549d76eb65440811d6
https://doi.org/10.1109/isie45552.2021.9576191
https://doi.org/10.1109/isie45552.2021.9576191
Autor:
Prahlad Vadakkepat, Haiyue Zhu, Tong Heng Lee, Chek Sing Teo, Cheng Xiang, Wenxin Wang, Yiting Li, Yu Cheng
Publikováno v:
CVPR
We aim to tackle the challenging Few-Shot Object Detection (FSOD), where data-scarce categories are presented during the model learning. The failure modes of FasterRCNN in FSOD are investigated, and we find that the performance degradation is mainly
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5f114afb07cb974c9f70bedb676e1ccb
https://doi.org/10.1109/cvpr46437.2021.01514
https://doi.org/10.1109/cvpr46437.2021.01514