Transfer Learning for Olfactory Object Detection

Zinnen M, Madhu P, Bell P, Maier A, Christlein V (2022)

Publication Language: English

Publication Type: Conference contribution, Abstract of lecture

Publication year: 2022

Series: Digitial Humanities

Book Volume: 2022

Pages Range: 409-413

Conference Proceedings Title: Digital Humanities 2022 Conference Abstracts

Event location: Tokyo, Japan, Online JP

URI: https://dh2022.dhii.asia/dh2022bookofabsts.pdf

Open Access Link: https://arxiv.org/abs/2301.09906

Abstract

We investigate the effect of style and category similarity in multiple datasets used for object detection pretraining. We find that including an additional stage of object-detection pretraining can increase the detection performance considerably. While our experiments suggest that style similarities between pre-training and target datasets are less important than matching categories, further experiments are needed to verify this hypothesis.

Authors with CRIS profile

Mathias Zinnen Lehrstuhl für Informatik 5 (Mustererkennung) Prathmesh Madhu Lehrstuhl für Informatik 5 (Mustererkennung) Peter Bell Juniorprofessur für Digital Humanities mit Schwerpunkt Kunstgeschichte Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung) Vincent Christlein Lehrstuhl für Informatik 5 (Mustererkennung)

How to cite

APA:

Zinnen, M., Madhu, P., Bell, P., Maier, A., & Christlein, V. (2022, July). Transfer Learning for Olfactory Object Detection. Paper presentation at Digital Humanities 2022, Tokyo, Japan, Online, JP.

MLA:

Zinnen, Mathias, et al. "Transfer Learning for Olfactory Object Detection." Presented at Digital Humanities 2022, Tokyo, Japan, Online Ed. Alliance of Digital Humanities Organizations, 2022.

BibTeX: Download