Poster
in
Workshop: Symmetry and Geometry in Neural Representations

Roto-translation Equivariant YOLO for Aerial Images

Benjamin Maurel ⋅ Samy Blusseau ⋅ Santiago Velasco-Forero ⋅ Teodora Petrisor

Project Page [ OpenReview]

Abstract

This work introduces Eq-YOLO, an Equivariant One-Stage Object Detector based on YOLO-v8 incorporating group convolutions to handle rotational transformations. We show the interest of using equivariant-transforms to improve the detection performance on rotated data over the regular YOLO-v8 model while dividing the number of parameters to train by a factor greater than three.

Chat is not available.