Data-Efficient Image Quality Assessment with Attention-Panel Decoder

16Citations
Citations of this article
7Readers
Mendeley users who have this article in their library.

Abstract

Blind Image Quality Assessment (BIQA) is a fundamental task in computer vision, which however remains unresolved due to the complex distortion conditions and diversified image contents. To confront this challenge, we in this paper propose a novel BIQA pipeline based on the Transformer architecture, which achieves an efficient quality-aware feature representation with much fewer data. More specifically, we consider the traditional fine-tuning in BIQA as an interpretation of the pre-trained model. In this way, we further introduce a Transformer decoder to refine the perceptual information of the CLS token from different perspectives. This enables our model to establish the quality-aware feature manifold efficiently while attaining a strong generalization capability. Meanwhile, inspired by the subjective evaluation behaviors of human, we introduce a novel attention panel mechanism, which improves the model performance and reduces the prediction uncertainty simultaneously. The proposed BIQA method maintains a lightweight design with only one layer of the decoder, yet extensive experiments on eight standard BIQA datasets (both synthetic and authentic) demonstrate its superior performance to the state-of-the-art BIQA methods, i.e., achieving the SRCC values of 0.875 (vs. 0.859 in LIVEC) and 0.980 (vs. 0.969 in LIVE). Checkpoints, logs and code will be available at https://github.com/narthchin/DEIQT.

Cite

CITATION STYLE

APA

Qin, G., Hu, R., Liu, Y., Zheng, X., Liu, H., Li, X., & Zhang, Y. (2023). Data-Efficient Image Quality Assessment with Attention-Panel Decoder. In Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023 (Vol. 37, pp. 2091–2100). AAAI Press. https://doi.org/10.1609/aaai.v37i2.25302

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free