KDAS: Knowledge Distillation via Attention Supervision Framework for Polyp Segmentation

13 Dec 2023  ·  Quoc-Huy Trinh, Minh-Van Nguyen, Phuoc-Thao Vo Thi ·

Polyp segmentation, a contentious issue in medical imaging, has seen numerous proposed methods aimed at improving the quality of segmented masks. While current state-of-the-art techniques yield impressive results, the size and computational cost of these models create challenges for practical industry applications. To address this challenge, we present KDAS, a Knowledge Distillation framework that incorporates attention supervision, and our proposed Symmetrical Guiding Module. This framework is designed to facilitate a compact student model with fewer parameters, allowing it to learn the strengths of the teacher model and mitigate the inconsistency between teacher features and student features, a common challenge in Knowledge Distillation, via the Symmetrical Guiding Module. Through extensive experiments, our compact models demonstrate their strength by achieving competitive results with state-of-the-art methods, offering a promising approach to creating compact models with high accuracy for polyp segmentation and in the medical imaging field. The implementation is available on https://github.com/huyquoctrinh/KDAS.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Medical Image Segmentation CVC-ClinicDB KDAS mean Dice 0.925 # 21
mIoU 0.872 # 5
Medical Image Segmentation CVC-ColonDB KDAS3 mean Dice 0.759 # 15
mIoU 0.679 # 15
Average MAE 0.032 # 6
Medical Image Segmentation Kvasir-SEG KDAS Average MAE 0.027 # 8
mean Dice 0.913 # 21
mIoU 0.848 # 30

Methods