King's College London

Research portal

Weakly Supervised Object Localization Using Things and Stuff Transfer

Research output: Contribution to journalConference paperpeer-review

Miaojing Shi, Holger Caesar, Vittorio Ferrari

Original languageEnglish
Pages (from-to)3401-3410
Journal2017 IEEE International Conference on Computer Vision (ICCV)
Volume1
Early online date25 Dec 2017
DOIs
E-pub ahead of print25 Dec 2017
Published2017

Documents

  • Weakly Supervised Object Localization_SHI_Epub25Dec2017 GREEN AAM

    shi17iccv_1_.pdf, 1.91 MB, application/pdf

    Uploaded date:11 May 2020

    Version:Accepted author manuscript

    © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

King's Authors

Abstract

We propose to help weakly supervised object localization for classes where location annotations are not available, by transferring things and stuff knowledge from a source set with available annotations. The source and target classes might share similar appearance (e.g. bear fur is similar to cat fur) or appear against similar background (e.g. horse and sheep appear against grass). To exploit this, we acquire three types of knowledge from the source set: a segmentation model trained on both thing and stuff classes; similarity relations between target and source classes; and cooccurrence relations between thing and stuff classes in the source. The segmentation model is used to generate thing and stuff segmentation maps on a target image, while the class similarity and co-occurrence knowledge help refining them. We then incorporate these maps as new cues into a multiple instance learning framework (MIL), propagating the transferred knowledge from the pixel level to the object proposal level. In extensive experiments, we conduct our transfer from the PASCAL Context dataset (source) to the ILSVRC, COCO and PASCAL VOC 2007 datasets (targets). We evaluate our transfer across widely different thing classes, including some that are not similar in appearance, but appear against similar background. The results demonstrate significant improvement over standard MIL, and we outperform the state-of-the-art in the transfer setting

Download statistics

No data available

View graph of relations

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454