Research output per year
Research output per year
Amogh Gudi, Nicolai Van Rosmalen, Marco Loog, Jan Van Gemert
Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review
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 language | English |
---|---|
Title of host publication | British Machine Vision Conference 2017, BMVC 2017 |
Publisher | BMVA Press |
ISBN (Electronic) | 9781901725605 |
DOIs | |
Publication status | Published - 1 Jan 2017 |
Event | 28th British Machine Vision Conference, BMVC 2017 - London, United Kingdom Duration: 4 Sept 2017 → 7 Sept 2017 |
Name | British Machine Vision Conference 2017, BMVC 2017 |
---|
Conference | 28th British Machine Vision Conference, BMVC 2017 |
---|---|
Country/Territory | United Kingdom |
City | London |
Period | 4/09/17 → 7/09/17 |
Research output: Thesis › Dissertation (TU Delft)