Simone Angarano
Hi! Iām Simone Angarano, and I am a 3rd-year Ph.D. student in Machine Learning at Politecnico di Torino . I am a member of the AI section of the Interdepartmental Center for Service Robotics PIC4SeR, where my focus is on creating efficient deep learning models for robot perception and control. In my research, particular attention is given to key aspects of real-world applications like generalization and robustness. Moreover, the constraints imposed by the application field in terms of latency and power consumption are considered. I spent the last year at the University of Texas at Austin, working on efficient foundation vision models. In the previous years, I had the opportunity to work on different research projects spanning tasks like image classification, human action recognition, super-resolution, instance segmentation, path planning, navigation, and localization. Solving these tasks, I got passionate about domain and sim-to-real generalization, model compression, and knowledge distillation. I also collaborated on various projects with companies, leveraging state-of-the-art deep learning solutions to solve real-world tasks in smart agriculture, space exploration, and domestic assistance.
News
Oct 03, 2024 | Our paper Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition just reached 200 citations! š° |
---|---|
Oct 01, 2024 | Iāve been awarded the EECE PhD Quality Award from Politecnico di Torino! š |
Jul 09, 2024 | Our paper Back-to-Bones: Rediscovering the Role of Backbones in Domain Generalization has been published in the Pattern Recognition Journal! ā ļø |
Jun 19, 2024 | I presented our paper Domain Generalization for Crop Segmentation with Standardized Ensemble Knowledge Distillation has been accepted at CVPR 2024 workshop on Vision for Agriculture! šµ |
Jul 19, 2023 | I got my VISA, so itās official: I will be visiting VITA research group @ UT Austin from September ā23 to June ā24! š¤ Thanks to Prof. Atlas Wang for this wonderful opportunity šš¼ |
May 16, 2023 | Check out our upcoming workshop on Deep Learning for Sustainable Precision Agriculture, in collaboration with Politecnico di Milano and University of Galway! š |
May 12, 2023 | Our paper Generative Adversarial Super-Resolution at the Edge with Knowledge Distillation has been published in Engineering Applications of Artificial Intelligence (Elsevier)! šø |
Apr 20, 2023 | I will chair a workshop on Deep Learning for Precision Agriculture at the European Conference of Machine Learning ECML PKDD 2023! š± |
Apr 18, 2023 | New submitted preprint! Autonomous Navigation in Rows of Trees and High Crops with Deep Semantic Segmentation š² |
Apr 03, 2023 | New submitted preprint! Domain Generalization for Crop Segmentation with Knowledge Distillation š³ |
Mar 21, 2023 | New submitted preprint! Online Learning of Wheel Odometry Correction for Mobile Robots with Attention-based Neural Network š |
Feb 01, 2023 | Iām currently looking for Ph.D. visiting opportunities abroad. If you have some advice, please get in touch with me! š |
Jan 09, 2023 | Our paper Deep Instance Segmentation and Visual Servoing to Play Jenga with a Cost-Effective Robotic System has been published in MDPI Sensors! š¹ļø |
Sep 30, 2022 | I presented my poster Efficient Deep Learning models for robot perception, control, and decision-making at the annual PhD PosterDay to professors Barbara Caputo, Alessandro Rizzo and Daniele Pagliari! |
Sep 20, 2022 | I presented the paper āWaypoint Generation in Row-based Crops with Deep Learning and Contrastive Clusteringā with my colleagues Francesco Salvetti and Mauro Martini at ECML PKDD 2022 in Grenoble! š„³ |
Sep 10, 2022 | New submitted preprint! Deep Instance Segmentation and Visual Servoing to Play Jenga with a Cost-Effective Robotic System š¤ |
Sep 10, 2022 | New submitted preprint! Generative Adversarial Super-Resolution at the Edge with Knowledge Distillation š„ø |
Jul 15, 2022 | New submitted preprint! Back-to-Bones: Rediscovering the Role of Backbones in Domain Generalization š¤Æ |
Selected Publications
- CASE
- ECMR