This work presents variations of our novel architecture, MiniNet, designed for efficient semantic segmentation. We have explored the design of the CNN for segmentation as well as applications for event-based cameras and 3D data.
Iñigo Alonso, Luis Riazuelo, Luis Montesano, Ana C Murillo
Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank.
I. Alonso, A. Sabater, D. Ferstl, L. Montesano, A.C. Murillo. Proc. of the IEEE/CVF International Conference on Computer Vision (ORAL). 2021. Paper and supplementary (CVF) | Code
Domain Adaptation in LiDAR Semantic Segmentation by Aligning Class Distributions. I. Alonso, L. Montesano, A. C. Murillo. In Proc. of 18th Int. Conference on Informatics in Control, Automation and Robotics - ICINCO, 330-337, 2021. BEST STUDENT PAPER AWARD. paper (arxiv) | paper (scitepress) | Video
3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation. I. Alonso, Luis Riazuelo, L. Montesano, Ana C. Murillo. IEEE Robotics and Automation Letters (RA-L), 2020. paper (arxiv) | paper (IEEExplore) | Code | Video
MiniNet: An Efficient Semantic Segmentation ConvNet for Real-time Robotic Applications. I. Alonso, L. Riazuelo, Ana C. Murillo. IEEE Transactions on Robotics (T-RO), 2020. paper (preprint) | paper (IEEExplore) | Code (original version); Code (TF2 version)
Enhancing V-SLAM Keyframe Selection with an Efficient ConvNet for Semantic Analysis. I. Alonso, L. Riazuelo, Ana C. Murillo. International Conference on on Robotics and Automation (ICRA), 2019. Paper | Poster | code
EV-SegNet: Semantic Segmentation for Event-based Cameras. I. Alonso, Ana C. Murillo. Computer Vision and Pattern Recognition Conference Workshops (CVPRW), 2019. Paper | Poster | code
The authors would like to thank NVIDIA Corporation for the donation of a Titan Xp GPU used in this work.
This research has been partially funded by the Spanish Government project PGC2018-098817-A-I00 and RTC-2017-6421-7 (MCIU/AEI/10.13039/501100011033/FEDER,UE), UZCUD2017-TEC-06 and Aragón regional government (Grupo DGA T45 17R/FSE, DGA_FSE T45_20R).