5 papers
CogSense: A Cognitively Inspired Framework for Perception Adaptation
Hyukseong Kwon, Amir Rahimi, Kevin G. Lee +2
This paper proposes the CogSense system, which is inspired by sense-making cognition and perception in the mammalian brain to perform perception error detection and perception para…
Few-shot Weakly-Supervised Object Detection via Directional Statistics
Amirreza Shaban, Amir Rahimi, Thalaiyasingam Ajanthan +2
Detecting novel objects from few examples has become an emerging topic in computer vision recently. However, these methods need fully annotated training images to learn new object…
Pairwise Similarity Knowledge Transfer for Weakly Supervised Object Localization
Amir Rahimi, Amirreza Shaban, Thalaiyasingam Ajanthan +2
Weakly Supervised Object Localization (WSOL) methods only require image level labels as opposed to expensive bounding box annotations required by fully supervised algorithms. We st…
Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks
Amir Rahimi, Amirreza Shaban, Ching-An Cheng +2
Predicting calibrated confidence scores for multi-class deep networks is important for avoiding rare but costly mistakes. A common approach is to learn a post-hoc calibration funct…
Learning to Find Common Objects Across Few Image Collections
Amirreza Shaban, Amir Rahimi, Shray Bansal +3
Given a collection of bags where each bag is a set of images, our goal is to select one image from each bag such that the selected images are from the same object class. We model t…