References

Rethinking the Inception Architecture for Computer Vision

Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, & Zbigniew Wojna (2016)

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2818-2826.

DOI: https://doi.org/10.1109/cvpr.2016.308

Abstract. Introduces label smoothing as a regularisation technique that softens the one-hot targets used in classification, preventing models from becoming overconfident. The paper also presents the Inception-v3 architecture.

Tags: regularisation label-smoothing inception

This site is currently in Beta. Contact: Chris Paton

Textbook of Usability · Textbook of Digital Health

Auckland Maths and Science Tutoring

AI tools used: Claude (research, coding, text), ChatGPT (diagrams, images), Grammarly (editing).