KDAS: Knowledge Distillation via Attention Supervision Framework for Polyp Segmentation

TL;DR

KDAS introduces a knowledge distillation framework with attention supervision and a Symmetrical Guiding Module to create compact, high-performing models for polyp segmentation in medical imaging, balancing accuracy and efficiency.

Contribution

The paper proposes a novel KDAS framework with attention supervision and a Symmetrical Guiding Module for effective knowledge distillation in polyp segmentation.

Findings

Achieves competitive results with state-of-the-art methods.

Produces compact models with fewer parameters.

Demonstrates high accuracy in medical image segmentation.

Abstract

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.