Emre Akbas
@eakbas2.bsky.social
Visiting scholar at Explainable ML, Helmholtz Munich | CS/CEng professor at Middle East Technical University
https://user.ceng.metu.edu.tr/~emre/
https://user.ceng.metu.edu.tr/~emre/
The companion website is open to all at 384book.net.
Book can be found at www.wiley.com/en-us/Signal...
Book can be found at www.wiley.com/en-us/Signal...
February 24, 2025 at 11:17 AM
The companion website is open to all at 384book.net.
Book can be found at www.wiley.com/en-us/Signal...
Book can be found at www.wiley.com/en-us/Signal...
Wiley did an excellent job creating the e-book version. See the attached video for an excerpt! (The ebook is hosted at vitalsource.com)
February 24, 2025 at 11:17 AM
Wiley did an excellent job creating the e-book version. See the attached video for an excerpt! (The ebook is hosted at vitalsource.com)
Over the years of teaching this course with Prof. Fatos Yarman Vural, we have gradually enriched and transformed her handwritten lecture notes into a textbook. It has been a long and challenging but fun project!
February 24, 2025 at 11:17 AM
Over the years of teaching this course with Prof. Fatos Yarman Vural, we have gradually enriched and transformed her handwritten lecture notes into a textbook. It has been a long and challenging but fun project!
Dear @csprofkgd.bsky.social , I'd love to be included if there is space. Thank you!
November 30, 2024 at 2:39 PM
Dear @csprofkgd.bsky.social , I'd love to be included if there is space. Thank you!
When you want to directly optimize the evaluation measure, e.g. in object detection, you face non-differentiable or zero-gradient components. Then, you manipulate the gradient, see: aLRP loss arxiv.org/abs/2009.13592 and RS loss: arxiv.org/abs/2107.11669.
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection
We propose average Localisation-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detection. aLRP extends t...
arxiv.org
November 30, 2024 at 9:55 AM
When you want to directly optimize the evaluation measure, e.g. in object detection, you face non-differentiable or zero-gradient components. Then, you manipulate the gradient, see: aLRP loss arxiv.org/abs/2009.13592 and RS loss: arxiv.org/abs/2107.11669.