Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Distinct Class Saliency Maps for Multiple Object Images
Wataru Shimoda, Keiji Yanai
Feb 18, 2016 (modified: Feb 18, 2016)ICLR 2016 workshop submissionreaders: everyone
Abstract:This paper proposes a method to obtain more distinct class saliency maps than
Simonyan et al. (2014). We made three improvements over their method: (1) using
CNN derivatives with respect to feature maps of the intermediate convolutional
layers with up-sampling instead of an input image; (2) subtracting saliency
maps of the other classes from saliency maps of the target class to differentiate
target objects from other objects; (3) aggregating multi-scale class saliency maps
to compensate lower resolution of the feature maps.
Enter your feedback below and we'll get back to you as soon as possible.