AIConfPaper
← Search

Jayakorn Vongkulbhisal

6 accepted papers

2021

Data-Efficient Framework for Real-World Multiple Sound Source 2d Localization

Guillaume Le Moing, Phongtharin Vinayavekhin, Don Joven Agravante, Tadanobu Inoue, Jayakorn Vongkulbhisal, Asim Munawar +1
ICASSP 2021accepted

Deep neural networks have recently led to promising results for the task of multiple sound source localization. Yet, they require a lot of training data to cover a variety of acoustic conditions and micro-phone array layouts. One can leverage acoustic simulators to inexpensively generate labeled tra…

Cited by 0Source ↗Scholar ↗
2021

On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective

Nontawat Charoenphakdee, Jayakorn Vongkulbhisal, Nuttapong Chairatanakul, Masashi Sugiyama
CVPR 2021poster

The focal loss has demonstrated its effectiveness in many real-world applications such as object detection and image classification, but its theoretical understanding has been limited so far. In this paper, we first prove that the focal loss is classification-calibrated, i.e., its minimizer surely y…

Cited by 34PDF ↗Scholar ↗
2019

Unifying Heterogeneous Classifiers With Distillation

Jayakorn Vongkulbhisal, Phongtharin Vinayavekhin, Marco Visentini-Scarzanella
CVPR 2019poster

In this paper, we study the problem of unifying knowledge from a set of classifiers with different architectures and target classes into a single classifier, given only a generic set of unlabelled data. We call this problem Unifying Heterogeneous Classifiers (UHC). This problem is motivated by scena…

Cited by 75PDF ↗Scholar ↗
2018

Inverse Composition Discriminative Optimization for Point Cloud Registration

Jayakorn Vongkulbhisal, Beñat Irastorza Ugalde, Fernando De la Torre, João P. Costeira
CVPR 2018poster

Rigid Point Cloud Registration (PCReg) refers to the problem of finding the rigid transformation between two sets of point clouds. This problem is particularly important due to the advances in new 3D sensing hardware, and it is challenging because neither the correspondence nor the transformation pa…

Cited by 24Source ↗PDF ↗Scholar ↗
2017

Discriminative Optimization: Theory and Applications to Point Cloud Registration

Jayakorn Vongkulbhisal, Fernando De la Torre, Joao P. Costeira
CVPR 2017poster

Many computer vision problems are formulated as the optimization of a cost function. This approach faces two main challenges: (1) designing a cost function with a local optimum at an acceptable solution, and (2) developing an efficient numerical method to search for one (or multiple) of these local…

Cited by 42PDF ↗Scholar ↗
2016

Motion From Structure (MfS): Searching for 3D Objects in Cluttered Point Trajectories

Jayakorn Vongkulbhisal, Ricardo Cabral, Fernando De la Torre, Joao P. Costeira
CVPR 2016spotlight

Object detection has been a long standing problem in computer vision, and state-of-the-art approaches rely on the use of sophisticated features and/or classifiers. However, these learning-based approaches heavily depend on the quality and quantity of labeled data, and do not generalize well to extre…

Cited by 4PDF ↗Scholar ↗