Distilling Knowledge from Object Classification to Aesthetics Assessment

Page view(s)
7
Checked on Mar 25, 2024
Distilling Knowledge from Object Classification to Aesthetics Assessment
Title:
Distilling Knowledge from Object Classification to Aesthetics Assessment
Journal Title:
IEEE Transactions on Circuits and Systems for Video Technology
Publication Date:
27 June 2022
Citation:
Hou, J., Ding, H., Lin, W., Liu, W., & Fang, Y. (2022). Distilling Knowledge from Object Classification to Aesthetics Assessment. IEEE Transactions on Circuits and Systems for Video Technology, 1–1. https://doi.org/10.1109/tcsvt.2022.3186307
Abstract:
In this work, we point out that the major dilemma of image aesthetics assessment (IAA) comes from the abstract nature of aesthetic labels. That is, a vast variety of distinct contents can correspond to the same aesthetic label. On the one hand, during inference, the IAA model is required to relate various distinct contents to the same aesthetic label. On the other hand, when training, it would be hard for the IAA model to learn to distinguish different contents merely with the supervision from aesthetic labels, since aesthetic labels are not directly related to any specific content. To deal with this dilemma, we propose to distill knowledge on semantic patterns for a vast variety of image contents from multiple pre-trained object classification (POC) models to an IAA model. Expecting the combination of multiple POC models can provide sufficient knowledge on various image contents, the IAA model can easier learn to relate various distinct contents to a limited number of aesthetic labels. By supervising an end-to-end single-backbone IAA model with the distilled knowledge, the performance of the IAA model is significantly improved by 4.8% in SRCC compared to the version trained only with ground-truth aesthetic labels. On specific categories of images, the SRCC improvement brought by the proposed method can achieve up to 7.2%. Peer comparison also shows that our method outperforms 10 previous IAA methods.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Ministry of Education - Tier-1 Fund MOE2021
Grant Reference no. : RG14/21
Description:
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
1558-2205
1051-8215
Files uploaded:

File Size Format Action
distilling-knowledge-from-object-classification-to-aesthetics-assessment-for-astar-repo.pdf 6.50 MB PDF Request a copy