TY - GEN
T1 - Domain Adaptative Retinal Image Quality Assessment with Knowledge Distillation Using Competitive Teacher-Student Network
AU - Lin, Yuanming
AU - Li, Heng
AU - Liu, Haofeng
AU - Shu, Hai
AU - Li, Zinan
AU - Hu, Yan
AU - Liu, Jiang
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Retinal image quality assessment (RIQA) is essential for retinal examinations, as it impacts the certainty of both manual and intelligent diagnosis. Unfortunately, domain shifts, such as the variance of colors and illumination, are prone to confuse RIQA. Though efficient domain adaptation solutions have been proposed, properly transferring RIQA models to new domains remains a troublesome task. This paper presents a domain adaptative RIQA algorithm with knowledge distillation using a competitive teacher-student network (CTSN) to address the above issue. The main structure consists of a teacher network, a student network, and a competition module. The teacher network provides pseudo-labels by adapting source and target domain features, and the student network learns features from target-specific pseudo-labels. The competition module boosts the fine-grained adaptation of RIQA. Comparison experiments and ablation studies demonstrate that our method performs outstandingly in RIQA with domain shifts.
AB - Retinal image quality assessment (RIQA) is essential for retinal examinations, as it impacts the certainty of both manual and intelligent diagnosis. Unfortunately, domain shifts, such as the variance of colors and illumination, are prone to confuse RIQA. Though efficient domain adaptation solutions have been proposed, properly transferring RIQA models to new domains remains a troublesome task. This paper presents a domain adaptative RIQA algorithm with knowledge distillation using a competitive teacher-student network (CTSN) to address the above issue. The main structure consists of a teacher network, a student network, and a competition module. The teacher network provides pseudo-labels by adapting source and target domain features, and the student network learns features from target-specific pseudo-labels. The competition module boosts the fine-grained adaptation of RIQA. Comparison experiments and ablation studies demonstrate that our method performs outstandingly in RIQA with domain shifts.
KW - Retinal image quality assessment
KW - domain adaptation
KW - knowledge distillation
UR - http://www.scopus.com/inward/record.url?scp=85172117502&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85172117502&partnerID=8YFLogxK
U2 - 10.1109/ISBI53787.2023.10230455
DO - 10.1109/ISBI53787.2023.10230455
M3 - Conference contribution
AN - SCOPUS:85172117502
T3 - Proceedings - International Symposium on Biomedical Imaging
BT - 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023
PB - IEEE Computer Society
T2 - 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023
Y2 - 18 April 2023 through 21 April 2023
ER -