Sorry, you need to enable JavaScript to visit this website.

IMPROVING PROPOSAL-BASED OBJECT DETECTION USING CONVOLUTIONAL CONTEXT FEATURES

Citation Author(s):
Emre Can Kaya, A. Aydın Alatan
Submitted by:
emre can kaya
Last updated:
7 October 2018 - 2:01pm
Document Type:
Poster
Document Year:
2018
Event:
Presenters:
A. Aydın Alatan
Paper Code:
2673
 

A novel extension to proposal-based detection is proposed in order to learn convolutional context features for determining boundaries of objects better. Objects and their context are aimed to be learned through parallel convolutional stages. The resulting object and context feature maps are combined in such a way that they preserve their spatial relationship. The proposed algorithm is trained and evaluated on PASCAL VOC 2007 detection benchmark dataset and yielded improvements in performance over baseline, for all classes, especially the ones with distinctive context.

up
0 users have voted: