Using Citizen Science Data as Pre-Training for Semantic Segmentation of High-Resolution UAV Images for Natural Forests Post-Disturbance Assessment
Using citizen science data to improve UAV image analysis
• By William Guimont-Martin Proprioception Is All You Need: Terrain Classification for Boreal Forests
Exterioception need-not apply
• By William Guimont-Martin Replication Study and Benchmarking of Real-Time Object Detection Models
In depth analysis of real-time object detection models
• By William Guimont-Martin RandAugment
Presentation on RandAugment
• By William Guimont-Martin Segment Anything
Presentation on Segment Anything
• By William Guimont-Martin MaskBEV: Joint Object Detection and Footprint Completion for Bird's-eye View 3D Point Clouds
• By William Guimont-Martin Learn Transformers
The Transformer architecture reimplemented to be easy to understand
• By William Guimont-Martin torch_waymo
Python library for loading the Waymo Open Dataset in PyTorch
• By William Guimont-Martin Apprentissage par réseaux de neurones profonds sur les nuages de points 3D
• By William Guimont-Martin Point-BERT IFT-6001
• By William Guimont-Martin Compute Canada Quickstart
A guide to using Compute Canada clusters for deep learning.
• By William Guimont-Martin Transformers in Computer Vision
A talk on transformer-based neural network architectures for computer vision.
• By William Guimont-Martin TossingBot
Explaining TossingBot
• By William Guimont-Martin On Learning
Some thoughts on human learning and representation learning
• By William Guimont-Martin PROSAC
A variant of RANSAC using quality to speed up the process
• By William Guimont-Martin