Sequential optimization for efficient high-quality object proposal generation
Files
Accepted manuscript
Date
2018-05-01
Authors
Zhang, Ziming
Liu, Yun
Chen, Xi
Zhu, Yanjun
Cheng, Ming-Ming
Saligrama, Venkatesh
Torr, Philip H.S.
Version
OA Version
Citation
Ziming Zhang, Yun Liu, Xi Chen, Yanjun Zhu, Ming-Ming Cheng, Venkatesh Saligrama, Philip HS Torr. 2018. "Sequential Optimization for Efficient High-Quality Object Proposal Generation." IEEE Transactions On Pattern Analysis And Machine Intelligence, Volume 40, Issue 5, pp. 1209 - 1223 (15). https://doi.org/10.1109/TPAMI.2017.2707492
Abstract
We are motivated by the need for a generic object proposal generation algorithm which achieves good balance between object detection recall, proposal localization quality and computational efficiency. We propose a novel object proposal algorithm, BING ++, which inherits the virtue of good computational efficiency of BING [1] but significantly improves its proposal localization quality. At high level we formulate the problem of object proposal generation from a novel probabilistic perspective, based on which our BING++ manages to improve the localization quality by employing edges and segments to estimate object boundaries and update the proposals sequentially. We propose learning the parameters efficiently by searching for approximate solutions in a quantized parameter space for complexity reduction. We demonstrate the generalization of BING++ with the same fixed parameters across different object classes and datasets. Empirically our BING++ can run at half speed of BING on CPU, but significantly improve the localization quality by 18.5 and 16.7 percent on both VOC2007 and Microhsoft COCO datasets, respectively. Compared with other state-of-the-art approaches, BING++ can achieve comparable performance, but run significantly faster.