no code implementations • 29 Jan 2022 • Varun Vasudevan, Maxime Bassenne, Md Tauhidul Islam, Lei Xing
On the contrary, this study investigates image classification using graphs generated from an image-specific number of multiscale superpixels.
no code implementations • 1 Jan 2021 • Maxime Bassenne, Varun Vasudevan, Lei Xing
In this study, we investigate learning from a new principled representation in which individual images are represented by an image-specific number of multiscale superpixels.
no code implementations • 29 Dec 2019 • Maxime Bassenne, Adrián Lozano-Durán
The combination of reinforcement learning with objectives (i), (ii) and (iii) differentiate our work from previous modeling attempts based on machine learning.
no code implementations • 31 Oct 2019 • Hyunseok Seo, Charles Huang, Maxime Bassenne, Ruoxiu Xiao, Lei Xing
To cope with these problems, we added a residual path with deconvolution and activation operations to the skip connection of the U-Net to avoid duplication of low resolution information of features.