How Active Learning Improves Nighttime Pedestrian Detection - NVIDIA DRIVE Labs Ep. 19
25 229
17
NVIDIA1.78 млн
Следующее
12.05.20 – 1 124 6140:28Популярные
28 дней – 11 1533:01
252 дня – 23 6741:48Опубликовано 8 апреля 2020, 15:44
Active learning makes it possible for AI to automatically choose the right training data. An ensemble of dedicated DNNs goes through a pool of image frames, flagging frames that it finds to be confusing. These frames are then labeled and added to the training dataset. This process can improve DNN perception in difficult conditions, such as nighttime pedestrian detection.
Learn more: nvda.ws/39PFYAl
Watch the full series here: nvda.ws/39T4uQT
Learn more about DRIVE Labs: nvda.ws/36r5c6t
Follow us on social
Twitter: nvda.ws/2JR8xCU
LinkedIn: nvda.ws/2XjkJ7e
Learn more: nvda.ws/39PFYAl
Watch the full series here: nvda.ws/39T4uQT
Learn more about DRIVE Labs: nvda.ws/36r5c6t
Follow us on social
Twitter: nvda.ws/2JR8xCU
LinkedIn: nvda.ws/2XjkJ7e
Свежие видео
1 день – 2 5663:31
3 дня – 57 27913:08
4 дня – 336 65315:57
4 дня – 4 2391:00
4 дня – 70 36524:16
5 дней – 12 7401:25Случайные видео
259 дней – 3 1182:21
02.11.23 – 1 3464:52
08.10.22 – 123 0182:21
03.05.22 – 1 939 1100:21
15.07.20 – 4 157 9357:32
28.01.20 – 196 1545:32
3 дня – 504 1662:18:21
4 дня – 3 2351:05:03
7 дней – 7 7241:32
10 дней – 4978:13
13 дней – 159 67613:43
