Amir Rahimi
PhD student, ANU
amir.rahimi [AT] anu.edu.au
About
I am a PhD student in the College of Engineering and Computer Science at the Australian National University, advised by Prof. Richard Hartley. I received my bachelor's and master's degrees from the University of Tehran. My research interests lie in the fields of Computer Vision and Machine Learning. Specifically, I work on problems with limited data/supervision, deep neural network confidence calibration, and inference in probabilistic graphical models. I am also interested in meta-learning and deep invertible networks.
Recent Publications
‡ indicates equal contribution.
Few-shot Weakly-Supervised Object Detection via Directional Statistics
Amirreza Shaban‡, Amir Rahimi‡, Thalaiyasingam Ajanthan, Byron Boots, Richard Hartley
Arxiv preprint, 2021
Calibration of neural networks using splines
Kartik Gupta, Amir Rahimi, Thalaiyasingam Ajanthan, Thomas Mensink, Cristian Sminchisescu, Richard Hartley
International Conference on Learning Representation, (ICLR 2021), Virtual Conference (formerly Vienna, Austria).
Post-hoc Calibration of Neural Networks
Amir Rahimi, Kartik Gupta, Thalaiyasingam Ajanthan, Thomas Mensink, Cristian Sminchisescu, Richard Hartley
Arxiv preprint, 2020
Pairwise similarity knowledge transfer for weakly supervised object localization
Amir Rahimi‡, Amirreza Shaban‡, Thalaiyasingam Ajanthan, Richard Hartley, Byron Boots
European Conference on Computer Vision, (ECCV 2020), Virtual Conference (formerly Glasgow, Scotland).
Intra order-preserving functions for calibration of multi-class neural networks
Amir Rahimi‡, Amirreza Shaban‡, Ching-An Cheng‡, Richard Hartley, Byron Boots
34th Conference on Neural Information Processing Systems (NeurIPS 2020), Virtual Conference (formerly Vancouver, Canada).
Learning to find common objects across few image collections
Amirreza Shaban‡, Amir Rahimi‡, Shray Bansal, Stephen Gould, Byron Boots, Richard Hartley
Proceedings of the IEEE/CVF International Conference on Computer Vision, (ICCV 2019), Seoul, Korea.