CNN-based Cross-dataset No-reference Image Quality Assessment
Yang, Dan; Peltoketo, Veli-Tapani; Kämäräinen, Joni-Kristian (2019)
Yang, Dan
Peltoketo, Veli-Tapani
Kämäräinen, Joni-Kristian
IEEE
2019
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tuni-202006055937
https://urn.fi/URN:NBN:fi:tuni-202006055937
Kuvaus
Peer reviewed
Tiivistelmä
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.
Kokoelmat
- TUNICRIS-julkaisut [17109]