Geometry Constrained Weakly Supervised Object Localization

Weizeng Lu, Xi Jia, Weicheng Xie, Linlin Shen, Yicong Zhou, Jinming Duan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

81 Downloads (Pure)


We propose a geometry constrained network, termed GC-Net, for weakly supervised object localization (WSOL). GC-Net consists of three modules: a detector, a generator and a classifier. The detector predicts the object location defined by a set of coefficients describing a geometric shape (i.e. ellipse or rectangle), which is geometrically constrained by the mask produced by the generator. The classifier takes the resulting masked images as input and performs two complementary classification tasks for the object and background. To make the mask more compact and more complete, we propose a novel multi-task loss function that takes into account area of the geometric shape, the categorical cross-entropy and the negative entropy. In contrast to previous approaches, GC-Net is trained end-to-end and predict object location without any post-processing (e.g. thresholding) that may require additional tuning. Extensive experiments on the CUB-200-2011 and ILSVRC2012 datasets show that GC-Net outperforms state-of-the-art methods by a large margin. Our source code is available at
Original languageEnglish
Title of host publication16th European Conference Computer Vision – ECCV 2020
Publication statusPublished - 19 Jul 2020

Bibliographical note

This paper (ID 5424) is accepted to ECCV 2020


  • cs.CV


Dive into the research topics of 'Geometry Constrained Weakly Supervised Object Localization'. Together they form a unique fingerprint.

Cite this