Discriminative Region Mining for Object Detection
Lvran Chen, Huicheng Zheng, Zhiwei Yan, Ye Li
Abstract
In generic object detection, detectors are often susceptible to foreground objects and background regions that share similar appearances. In this paper, we propose a novel discriminative region mining (DRM) module for object detection, which enables discriminative region localization and representation for accurate object identification. The DRM module is collaboratively optimized by an extra intramodule classification loss in addition to the usual detection loss, which ensures its adequate discriminative capability. Specifically, two derivatives of the DRM module, namely a local DRM module and a contextual DRM module are proposed to excavate local and contextual discriminative regions, respectively. Furthermore, we extend the local DRM module to capture multiple local discriminative regions with a diversity constraint. To explore informative local features, an image upsampling branch is introduced to generate fine-grained representation for the local DRM module. Extensive experiments on the PASCAL VOC and MS COCO datasets demonstrate the effectiveness of the proposed method. Simple baseline detectors with the built-in DRM can achieve state-of-the-art detection performance. For example, the proposed detector achieves a mean average precision of 81.0% on PASCAL VOC 2007 with an input size of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\text{300} \times \text{300}$</tex-math></inline-formula> using a ResNet-18 backbone, which runs at 24.2 fps on an Nvidia Titan X GPU.