Object extent pooling for weakly supervised single-shot localization

Amogh Gudi, Nicolai Van Rosmalen, Marco Loog, Jan Van Gemert

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

9 Citations (Scopus)
13 Downloads (Pure)


In the face of scarcity in detailed training annotations, the ability to perform object localization tasks in real-time with weak-supervision is very valuable. However, the computational cost of generating and evaluating region proposals is heavy. We adapt the concept of Class Activation Maps (CAM) [28] into the very first weakly-supervised ‘single-shot’ detector that does not require the use of region proposals. To facilitate this, we propose a novel global pooling technique called Spatial Pyramid Averaged Max (SPAM) pooling for training this CAM-based network for object extent localisation with only weak image-level supervision. We show this global pooling layer possesses a near ideal flow of gradients for extent localization, that offers a good trade-off between the extremes of max and average pooling. Our approach only requires a single network pass and uses a fast-backprojection technique, completely omitting any region proposal steps. To the best of our knowledge, this is the first approach to do so. Due to this, we are able to perform inference in real-time at 35fps, which is an order of magnitude faster than all previous weakly supervised object localization frameworks.

Original languageEnglish
Title of host publicationBritish Machine Vision Conference 2017, BMVC 2017
PublisherBMVA Press
ISBN (Electronic)9781901725605
Publication statusPublished - 1 Jan 2017
Event28th British Machine Vision Conference, BMVC 2017 - London, United Kingdom
Duration: 4 Sep 20177 Sep 2017

Publication series

NameBritish Machine Vision Conference 2017, BMVC 2017


Conference28th British Machine Vision Conference, BMVC 2017
Country/TerritoryUnited Kingdom


Dive into the research topics of 'Object extent pooling for weakly supervised single-shot localization'. Together they form a unique fingerprint.

Cite this