Dynamic Zoom-In Network for Fast Object Detection in Large Images

Mingfei Gao, Ruichi Yu, Ang Li, Vlad I. Morariu, Larry S. Davis; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 6926-6935

Abstract


We introduce a generic framework that reduces the computational cost of object detection while retaining accuracy for scenarios where objects with varied sizes appear in high resolution images. Detection progresses in a coarse-to-fine manner, first on a down-sampled version of the image and then on a sequence of higher resolution regions identified as likely to improve the detection accuracy. Built upon reinforcement learning, our approach consists of a model (R-net) that uses coarse detection results to predict the potential accuracy gain for analyzing a region at a higher resolution and another model (Q-net) that sequentially selects regions to zoom in. Experiments on the Caltech Pedestrians dataset show that our approach reduces the number of processed pixels by over 50% without a drop in detection accuracy. The merits of our approach become more significant on a high resolution test set collected from YFCC100M dataset, where our approach maintains high detection performance while reducing the number of processed pixels by about 70% and the detection time by over 50%.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Gao_2018_CVPR,
author = {Gao, Mingfei and Yu, Ruichi and Li, Ang and Morariu, Vlad I. and Davis, Larry S.},
title = {Dynamic Zoom-In Network for Fast Object Detection in Large Images},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}