Paper Info
Title
Look-Ahead Before You Leap: End-To-End Active Recognition By Forecasting The Effect Of Motion
Abstract
Visual recognition systems mounted on autonomous moving agents face the challenge of unconstrained data, but simultaneously have the opportunity to improve their performance by moving to acquire new views of test data. In this work, we first show how a recurrent neural network-based system may be trained to perform end-to-end learning of motion policies suited for this "active recognition" setting. Further, we hypothesize that active vision requires an agent to have the capacity to reason about the effects of its motions on its view of the world. To verify this hypothesis, we attempt to induce this capacity in our active recognition pipeline, by simultaneously learning to forecast the effects of the agent's motions on its internal representation of the environment conditional on all past views. Results across two challenging datasets confirm both that our end-to-end system successfully learns meaningful policies for active category recognition, and that "learning to look ahead" further boosts recognition performance.
Year
DOI
Venue
2016
10.1007/978-3-319-46454-1_30
COMPUTER VISION - ECCV 2016, PT V
Keywords
DocType
Volume
Active Recognition,Camera Motion,Active Vision,Partially Observable Markov Decision Process,Object Instance
Conference
9909
ISSN
Citations 
PageRank 
0302-9743
16
0.71
References 
Authors
34
2
Name
Order
Citations
PageRank
Dinesh Jayaraman131815.69
Kristen Grauman26258326.34