Zobrazeno 1 - 10
of 229
pro vyhledávání: '"Kim, Namil"'
Typical LiDAR-based 3D object detection models are trained in a supervised manner with real-world data collection, which is often imbalanced over classes (or long-tailed). To deal with it, augmenting minority-class examples by sampling ground truth (
Externí odkaz:
http://arxiv.org/abs/2403.11573
Object detectors are typically trained once and for all on a fixed set of classes. However, this closed-world assumption is unrealistic in practice, as new classes will inevitably emerge after the detector is deployed in the wild. In this work, we lo
Externí odkaz:
http://arxiv.org/abs/2402.17420
We study how humans learn from AI, exploiting an introduction of an AI-powered Go program (APG) that unexpectedly outperformed the best professional player. We compare the move quality of professional players to that of APG's superior solutions aroun
Externí odkaz:
http://arxiv.org/abs/2310.08704
Publikováno v:
In Research Policy October 2024 53(8)
Publikováno v:
In Journal of Business Venturing January 2024 39(1)
Recent works on domain adaptation exploit adversarial training to obtain domain-invariant feature representations from the joint learning of feature extractor and domain discriminator networks. However, domain adversarial methods render suboptimal pe
Externí odkaz:
http://arxiv.org/abs/1910.05562
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Lee, Seokju, Kim, Junsik, Yoon, Jae Shin, Shin, Seunghak, Bailo, Oleksandr, Kim, Namil, Lee, Tae-Hee, Hong, Hyun Seok, Han, Seung-Hoon, Kweon, In So
In this paper, we propose a unified end-to-end trainable multi-task network that jointly handles lane and road marking detection and recognition that is guided by a vanishing point under adverse weather conditions. We tackle rainy and low illuminatio
Externí odkaz:
http://arxiv.org/abs/1710.06288
Autor:
Kwak, Kiho, Kim, Namil
Publikováno v:
In Technological Forecasting & Social Change July 2022 180