no code implementations • 24 Nov 2022 • Al-Akhir Nayan, Boonserm Kijsirikul, Yuji Iwahori
Automatic lymph node (LN) segmentation and detection for cancer staging are critical.
no code implementations • 12 Jul 2022 • Al-Akhir Nayan, Boonserm Kijsirikul, Yuji Iwahori
According to the prediction produced by the model, Bangladesh may suffer another COVID-19 attack, where the number of infected cases can be between 929 to 2443 and death cases between 19 to 57.
1 code implementation • ACL 2021 • Kasidis Kanwatchara, Thanapapas Horsuwan, Piyawat Lertvittayakumjorn, Boonserm Kijsirikul, Peerapon Vateekul
Lifelong learning (LL) aims to train a neural network on a stream of tasks while retaining knowledge from previous tasks.
1 code implementation • 22 Oct 2020 • Konpat Preechakul, Sira Sriswasdi, Boonserm Kijsirikul, Ekapol Chuangsuwanich
In medical imaging, Class-Activation Map (CAM) serves as the main explainability tool by pointing to the region of interest.
1 code implementation • arXiv.org 2020 • Pongpisit Thanasutives, Ken-ichi Fukui, Masayuki Numao, Boonserm Kijsirikul
In this paper, we proposed two modified neural network architectures based on SFANet and SegNet respectively for accurate and efficient crowd counting.
2 code implementations • 12 Mar 2020 • Pongpisit Thanasutives, Ken-ichi Fukui, Masayuki Numao, Boonserm Kijsirikul
Inspired by SFANet, the first model, which is named M-SFANet, is attached with atrous spatial pyramid pooling (ASPP) and context-aware module (CAN).
Ranked #1 on Crowd Counting on UCF CC 50
1 code implementation • 24 Dec 2019 • Konpat Preechakul, Boonserm Kijsirikul
When the past gradients agree on direction, CProp keeps the original learning rate.
no code implementations • 3 Dec 2019 • Thanapapas Horsuwan, Kasidis Kanwatchara, Peerapon Vateekul, Boonserm Kijsirikul
The ever-growing volume of data of user-generated content on social media provides a nearly unlimited corpus of unlabeled data even in languages where resources are scarce.
1 code implementation • 22 Oct 2019 • Panayu Keelawat, Nattapong Thammasan, Masayuki Numao, Boonserm Kijsirikul
In this work, a study of CNN and its spatiotemporal feature extraction has been conducted in order to explore capabilities of the model in varied window sizes and electrode orders.
no code implementations • 28 Aug 2017 • Pittipol Kantavat, Boonserm Kijsirikul, Patoomsiri Songsiri, Ken-ichi Fukui, Masayuki Numao
We propose new methods for Support Vector Machines (SVMs) using tree architecture for multi-class classi- fication.
no code implementations • 27 Dec 2013 • Patoomsiri Songsiri, Thimaporn Phetkaew, Ryutaro Ichise, Boonserm Kijsirikul
We propose a method for constructing the Error Correcting Output Code to obtain the suitable combination of positive and negative classes encoded to represent binary classifiers.
no code implementations • 11 Sep 2013 • Patoomsiri Songsiri, Thimaporn Phetkaew, Boonserm Kijsirikul
We propose several novel methods for enhancing the multi-class SVMs by applying the generalization performance of binary classifiers as the core idea.