Antonin Vidon

About me

Hi! I am a second year grad student at Columbia University currently enrolled in the MS in Data Science. In the past, I earned a master’s degree in Applied Mathematics at École Polytechnique in France, where I am originally from.

My current work experience in Machine Learning consists of one internship in RL research and another one as an ML Engineer in an automation Start-up. During the former, I developed a deep generative model capable of imitating “expert-like” navigation behavior on different types of surfaces. As for the ML Engineer position, I worked on improving the reading order of segments extracted from pages with complex layouts so as to provide better context to downstream tasks. Earlier in my graduate program, I also had the opportunity to serve as a teaching assistant in electromagnetism and thermodynamics at Shanghai Jiao Tong University for two consecutive semesters.

Portfolio

Report    GitHub

Image-to-image translation with cGAN

Performed image colorization and reconstruction with pix2pix[1]-like cGAN architecture

[1] Philip Isola and Jun-Yan Zhu, Tinghui Zhou and Alexei A. Efros, Image-to-Image Translation with Conditional Adversarial Networks, arvix: https://arxiv.org/abs/1611.07004, doi: 10.48550/ARXIV.1611.07004.




Report    GitHub

Surgical phase recognition

Developing phase recognition models based on MobileNetV2 [1] to classify frames from Hernia surgery videos (14 labels)

[1] Sandler, Mark, et al. “MobileNetV2: Inverted Residuals and Linear Bottlenecks.” ArXiv:1801.04381 [Cs], Mar. 2019. arXiv.org, http://arxiv.org/abs/1801.04381.




GitHub

Breast Histopathology : custom ResNet

Predicting whether a breast tissue patch (scanned at x40) is cancerous

[1] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. Deep Residual Learning for Image Recognition. arXiv:1512.03385
[2] Deng, J. et al., 2009. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. pp. 248–255

Report    GitHub

Squeeze and Excitation Networks

Performing adaptative channel-wise feature recalibration to enhance state-of-the-art CNN architectures

[1] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. Deep Residual Learning for Image Recognition. arXiv:1512.03385
[2] S. Hitawala, Evaluating ResNeXt Model Architecture for Image Classification, CoRR. abs/1805.08700 (2018)
[3] Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, Zbigniew Wojna, “Rethinking the Inception Architecture for Computer Vision”, arXiv [cs.CV] 2015
[4] Hu, J., Shen, L., Albanie, S., Sun, G. and Wu, E., 2022. Squeeze-and-Excitation Networks
[5] Krizhevsky, Alex, Vinod Nair, and Geoffrey Hinton. ”The CIFAR-10 dataset.” online: http://www.cs.toronto.edu/kriz/cifar. html (2014)
[6] Krizhevsky, Alex, Vinod Nair, and Geoffrey Hinton. ”The CIFAR-100 dataset.” online: http://www.cs.toronto.edu/kriz/cifar. html (2014)
[7] Jiayu Wu, Qixiang Zhang, and Guoxi Xu. Tiny imageNet challenge. Technical Report, 2017

Report    GitHub

Energy consumption and human development

Puting to the test some intuitive insights between energy consumption and human development core components


GitHub

Goyav

Creating an R package to easily animate data



Report    GitHub

Breast Histopathology : exploratory analysis and classification with scikit-learn

Predicting whether a breast tissue patch (scanned at x40) is cancerous


Integration of physical models into voxel-based video games

Teaching gamers how classical mechanics, thermodynamics and chemistry interact together and how to improve their gameplay accordingly



GitHub

COVID19 Retweet Prediction

Predicting how many times a tweet will be retweeted

[1] Devlin, J., Chang, M., Lee, K. and Toutanova, K., 2022. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding