ML Anthology

Roto-Translation Equivariant YOLO for Aerial Images

Benjamin Maurel, Samy Blusseau, Santiago Velasco-Forero, Teodora Petrisor
NeurIPSW 2023
/neuripsw/2023/maurel2023neuripsw-rototranslation/

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.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Maurel et al. "Roto-Translation Equivariant YOLO for Aerial Images." NeurIPS 2023 Workshops: NeurReps, 2023.

Markdown

[Maurel et al. "Roto-Translation Equivariant YOLO for Aerial Images." NeurIPS 2023 Workshops: NeurReps, 2023.](https://mlanthology.org/neuripsw/2023/maurel2023neuripsw-rototranslation/)

BibTeX

@inproceedings{maurel2023neuripsw-rototranslation,
  title     = {{Roto-Translation Equivariant YOLO for Aerial Images}},
  author    = {Maurel, Benjamin and Blusseau, Samy and Velasco-Forero, Santiago and Petrisor, Teodora},
  booktitle = {NeurIPS 2023 Workshops: NeurReps},
  year      = {2023},
  url       = {https://mlanthology.org/neuripsw/2023/maurel2023neuripsw-rototranslation/}
}