IMPROVING PROPOSAL-BASED OBJECT DETECTION USING CONVOLUTIONAL CONTEXT FEATURES


Kaya E. C. , ALATAN A. A.

25th IEEE International Conference on Image Processing (ICIP), Athens, Greece, 7 - 10 October 2018, pp.1308-1312 identifier

  • Publication Type: Conference Paper / Full Text
  • City: Athens
  • Country: Greece
  • Page Numbers: pp.1308-1312
  • Keywords: CNN, Region Proposal Network, Object Detection, Context, Deep Learning

Abstract

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.