Saliency Guided End-to-End Learning for Weakly Supervised Object Detection

06/21/2017
by   Baisheng Lai, et al.
0

Weakly supervised object detection (WSOD), which is the problem of learning detectors using only image-level labels, has been attracting more and more interest. However, this problem is quite challenging due to the lack of location supervision. To address this issue, this paper integrates saliency into a deep architecture, in which the location in- formation is explored both explicitly and implicitly. Specifically, we select highly confident object pro- posals under the guidance of class-specific saliency maps. The location information, together with semantic and saliency information, of the selected proposals are then used to explicitly supervise the network by imposing two additional losses. Meanwhile, a saliency prediction sub-network is built in the architecture. The prediction results are used to implicitly guide the localization procedure. The entire network is trained end-to-end. Experiments on PASCAL VOC demonstrate that our approach outperforms all state-of-the-arts.

READ FULL TEXT

page 3

page 6

research
09/09/2019

Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentation

Existing weakly supervised semantic segmentation (WSSS) methods usually ...
research
03/03/2017

Bridging Saliency Detection to Weakly Supervised Object Detection Based on Self-paced Curriculum Learning

Weakly-supervised object detection (WOD) is a challenging problems in co...
research
11/16/2016

Weakly Supervised Top-down Salient Object Detection

Top-down saliency models produce a probability map that peaks at target ...
research
02/10/2018

Collaborative Learning for Weakly Supervised Object Detection

Weakly supervised object detection has recently received much attention,...
research
10/12/2019

Saliency Guided Self-attention Network for Weakly-supervised Semantic Segmentation

Weakly supervised semantic segmentation (WSSS) using only image-level la...
research
06/04/2018

Cube Padding for Weakly-Supervised Saliency Prediction in 360° Videos

Automatic saliency prediction in 360 videos is critical for viewpoint gu...
research
03/21/2018

Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions

Diagnostic imaging often requires the simultaneous identification of a m...

Please sign up or login with your details

Forgot password? Click here to reset