Weakly Supervised Object Localization Using Size Estimates

Miaojing Shi, Vittorio Ferrari

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


We present a technique for weakly supervised object localization (WSOL), building on the observation that WSOL algorithms usually work better on images with bigger objects. Instead of training the object detector on the entire training set at the same time, we propose a curriculum learning strategy to feed training images into the WSOL learning loop in an order from images containing bigger objects down to smaller ones. To automatically determine the order, we train a regressor to estimate the size of the object given the whole image as input. Furthermore, we use these size estimates to further improve the re-localization step of WSOL by assigning weights to object proposals according to how close their size matches the estimated object size. We demonstrate the effectiveness of using size order and size weighting on the challenging PASCAL VOC 2007 dataset, where we achieve a signicant improvement over existing state-of-the-art WSOL techniques.
Original languageEnglish
Title of host publicationThe 14th European Conference on Computer Vision (ECCV 2016)
PublisherSpringer, Cham
Number of pages17
ISBN (Electronic)978-3-319-46454-1
ISBN (Print)978-3-319-46453-4
Publication statusPublished - 16 Sep 2016
EventThe 14th European Conference on Computer Vision - Amsterdam, Netherlands
Duration: 8 Oct 201616 Oct 2016

Publication series

NameLecture Notes in Computer Science
PublisherSpringer, Cham
ISSN (Print)0302-9743


ConferenceThe 14th European Conference on Computer Vision
Abbreviated titleECCV'16
Internet address

Fingerprint Dive into the research topics of 'Weakly Supervised Object Localization Using Size Estimates'. Together they form a unique fingerprint.

Cite this