Learn to focus on objects for visual detection

Zijing Chen

doi:10.1016/j.neucom.2018.06.082

Return

Learn to focus on objects for visual detection

2019-07-01

PRE

Zijing Chen

Jun Li

尤新华 (Xinhua You) *

DOI：10.1016/j.neucom.2018.06.082

Original

Original request for help

Save

Abstract

En 中文

State-of-art visual detectors utilize object proposals as the reference of objects to achieve higher efficiency. However, the number of the proposal to ensure full coverage of potential objects is still large because the proposals are generated with thread and thrum, exposing proposal computation as a bottleneck. This paper presents a complementary technique that aims to work with any existing proposal generating system, amending the work-flow from propose-assess to propose-adjust-assess. Inspired by the biological processing, we propose to improve the quality of object proposals by analyzing visual contexts and gradually focusing proposals on targets. In particular, the proposed method can be employed with existing proposals generation algorithms based on both hand-crafted features and Convolutional Neural Network (CNN) features. For the former, we realize the focusing function by two learning-based transformation models, which are trained for identifying generic objects using image cues. For the latter, a Focus Proposal Net (FoPN) with cascaded layers, which can be directly injected into CNN models in an end-to-end manner, is developed as the implementation of focusing operation. Experiments on real-life image data sets demonstrate that the quality of the proposal is improved by the proposed technique. Besides, it can reduce the number of proposals to achieve high recall rate of the objects based on both hand-crafted features and CNN-features, and can boost the performance of state-of-art detectors. (C) 2018 Published by Elsevier B.V.

Keywords:

Object proposal

Detection

Deep Learning

Saliency

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.