Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gosal, Oswin, Rios, Edwin Arkel, Surya, Augusto Christian, Mikael, Fernando, Lai, Bo-Cheng, Hu, Min-Chun
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.15689
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909046439673856
author Gosal, Oswin
Rios, Edwin Arkel
Surya, Augusto Christian
Mikael, Fernando
Lai, Bo-Cheng
Hu, Min-Chun
author_facet Gosal, Oswin
Rios, Edwin Arkel
Surya, Augusto Christian
Mikael, Fernando
Lai, Bo-Cheng
Hu, Min-Chun
contents Fine-grained image recognition classifies subcategories such as bird species or car models. While state-of-the-art (SOTA) models are accurate, they are often too resource-intensive for deployment on constrained devices. Knowledge distillation addresses this by transferring knowledge from a large teacher model to a smaller student model. A key challenge is selecting the right teacher, as it heavily impacts student performance. This paper introduces a teacher selection metric, \textbf{Ratio 1-2}, based on teacher prediction ratios. Extensive analysis of over one thousand experiments across 3 students, 8 teachers, and 8 datasets under 4 training strategies demonstrates that our metric improves teacher selection by 18\% over previous methods, enabling small student models to achieve up to 17\% accuracy gains. Experiment codebase is available at: \href{https://github.com/arkel23/FGIR-KD-Teacher}{https://github.com/arkel23/FGIR-KD-Teacher}.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15689
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle How to Choose Your Teacher for Fine Grained Image Recognition
Gosal, Oswin
Rios, Edwin Arkel
Surya, Augusto Christian
Mikael, Fernando
Lai, Bo-Cheng
Hu, Min-Chun
Computer Vision and Pattern Recognition
I.2; I.4
Fine-grained image recognition classifies subcategories such as bird species or car models. While state-of-the-art (SOTA) models are accurate, they are often too resource-intensive for deployment on constrained devices. Knowledge distillation addresses this by transferring knowledge from a large teacher model to a smaller student model. A key challenge is selecting the right teacher, as it heavily impacts student performance. This paper introduces a teacher selection metric, \textbf{Ratio 1-2}, based on teacher prediction ratios. Extensive analysis of over one thousand experiments across 3 students, 8 teachers, and 8 datasets under 4 training strategies demonstrates that our metric improves teacher selection by 18\% over previous methods, enabling small student models to achieve up to 17\% accuracy gains. Experiment codebase is available at: \href{https://github.com/arkel23/FGIR-KD-Teacher}{https://github.com/arkel23/FGIR-KD-Teacher}.
title How to Choose Your Teacher for Fine Grained Image Recognition
topic Computer Vision and Pattern Recognition
I.2; I.4
url https://arxiv.org/abs/2605.15689