79 citations · 174 across the 39 of their papers we have counts for
6 papers · 1 filter
Early-exit Convolutional Neural Networks
Edanur Demir, Emre Akbas
This paper is aimed at developing a method that reduces the computational cost of convolutional neural networks (CNN) during inference. Conventionally, the input data pass through…
A multi-level multi-label text classification dataset of 19th century Ottoman and Russian literary and critical texts
Gokcen Gokceoglu, Devrim Cavusoglu, Emre Akbas +1
This paper introduces a multi-level, multi-label text classification dataset comprising over 3000 documents. The dataset features literary and critical texts from 19th-century Otto…
Bucketed Ranking-based Losses for Efficient Training of Object Detectors
Feyza Yavuz, Baris Can Cam, Adnan Harun Dogan +3
Ranking-based loss functions, such as Average Precision Loss and Rank&Sort Loss, outperform widely used score-based losses in object detection. These loss functions better align wi…
MoCap-to-Visual Domain Adaptation for Efficient Human Mesh Estimation from 2D Keypoints
Bedirhan Uguz, Ozhan Suat, Batuhan Karagoz +1
This paper presents Key2Mesh, a model that takes a set of 2D human pose keypoints as input and estimates the corresponding body mesh. Since this process does not involve any visual…
RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses
Bedrettin Cetinkaya, Sinan Kalkan, Emre Akbas
Detecting edges in images suffers from the problems of (P1) heavy imbalance between positive and negative classes as well as (P2) label uncertainty owing to disagreement between di…
A Comparison of Deep Learning Models for Proton Background Rejection with the AMS Electromagnetic Calorimeter
Raheem Karim Hashmani, Emre Akbaş, Melahat Bilge Demirköz
The Alpha Magnetic Spectrometer (AMS) is a high-precision particle detector onboard the International Space Station containing six different subdetectors. The Transition Radiation…