Adaptive Object Detection Using Adjacency and Zoom Prediction

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2016)

引用 95|浏览87
暂无评分
摘要
State-of-the-art object detection systems rely on an accurate set of region proposals. Several recent methods use a neural network architecture to hypothesize promising object locations. While these approaches are computationally efficient, they rely on fixed image regions as anchors for predictions. In this paper we propose to use a search strategy that adaptively directs computational resources to sub-regions likely to contain objects. Compared to methods based on fixed anchor locations, our approach naturally adapts to cases where object instances are sparse and small. Our approach is comparable in terms of accuracy to the state-of-the-art Faster R-CNN approach while using two orders of magnitude fewer anchors on average. Code is publicly available.
更多
查看译文
关键词
adaptive object detection,adjacency prediction,zoom prediction,neural architecture network fixed image regions,search strategy,computational resources,object instances,faster-R-CNN approach
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要