2.1.3 Scale Equivariance for Computer Vision
Course subject(s)
Module 2: AI in Practice: Preparing for AI
Ivan Sosnovik, a PhD candidate at the Delta Lab and the University of Amsterdam, presents a use case about Scale Equivariance for Computer Vision.
This video lesson is based on two scientific studies that are referred to below. Note: This additional information is not mandatory for the course and is primarily intended for learners who wish to dive deeper into the material.
- Ivan Sosnovik, Michał Szmaja, Arnold Smeulders. Scale-Equivariant Steerable Networks. 2020. The code referred to in the paper can be found here.
- Ivan Sosnovik, Artem Moskalev, Arnold Smeulders. Scale Equivariance Improves Siamese Tracking. 2020. The code referred to in the paper can be found here.
AI in Practice: Preparing for AI by TU Delft OpenCourseWare is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Based on a work at https://online-learning.tudelft.nl/courses/ai-in-practice-preparing-for-ai/ /