TY - GEN
T1 - CNN-based Cross-dataset No-reference Image Quality Assessment
AU - Yang, Dan
AU - Peltoketo, Veli-Tapani
AU - Kämäräinen, Joni-Kristian
PY - 2019
Y1 - 2019
N2 - Recent works on no-reference image quality assessment (NR-IQA) have reported good performance for various datasets. However, they suffer from significant performance drops in cross-dataset evaluations which indicates poor generalization power. We propose a Siamese architecture and training procedures for cross-dataset deep NR-IQA that achieves clearly better performance. Moreover, we show that the architecture can be further boosted by i) pre-training with a large aesthetics dataset and ii) adding low-level quality cues, sharpness, tone and colourfulness, as additional features.
AB - Recent works on no-reference image quality assessment (NR-IQA) have reported good performance for various datasets. However, they suffer from significant performance drops in cross-dataset evaluations which indicates poor generalization power. We propose a Siamese architecture and training procedures for cross-dataset deep NR-IQA that achieves clearly better performance. Moreover, we show that the architecture can be further boosted by i) pre-training with a large aesthetics dataset and ii) adding low-level quality cues, sharpness, tone and colourfulness, as additional features.
UR - http://openaccess.thecvf.com/content_ICCVW_2019/papers/LCI/Yang_CNN-Based_Cross-Dataset_No-Reference_Image_Quality_Assessment_ICCVW_2019_paper.pdf
U2 - 10.1109/ICCVW.2019.00485
DO - 10.1109/ICCVW.2019.00485
M3 - Conference contribution
SN - 978-1-7281-5024-6
T3 - IEEE International Conference on Computer Vision workshops
SP - 3913
EP - 3921
BT - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
PB - IEEE
T2 - IEEE International Conference on Computer Vision Workshops
Y2 - 1 January 1900
ER -