Learning to See by Moving

被引：250

作者：

Agrawal, Pulkit ^{[1
]}

Carreira, Joao ^{[1
]}

Malik, Jitendra ^{[1
]}

机构：

[1] Univ Calif Berkeley, Berkeley, CA 94720 USA

来源：

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) | 2015年

关键词：

CODE;

D O I：

10.1109/ICCV.2015.13

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The current dominant paradigm for feature learning in computer vision relies on training neural networks for the task of object recognition using millions of hand labelled images. Is it also possible to learn features for a diverse set of visual tasks using any other form of supervision? In biology, living organisms developed the ability of visual perception for the purpose of moving and acting in the world. Drawing inspiration from this observation, in this work we investigated if the awareness of egomotion (i.e. self motion) can be used as a supervisory signal for feature learning. As opposed to the knowledge of class labels, information about egomotion is freely available to mobile agents. We found that using the same number of training images, features learnt using egomotion as supervision compare favourably to features learnt using class-label as supervision on the tasks of scene recognition, object recognition, visual odometry and keypoint matching.

引用

页码：37 / 45

页数：9