KD-SCFNet: Towards More Accurate and Efficient Salient Object Detection via Knowledge Distillation

TL;DR

This paper introduces KD-SCFNet, a lightweight yet accurate salient object detection model that leverages knowledge distillation from a teacher network and a new dataset, achieving real-time performance with high accuracy.

Contribution

The paper proposes a novel semantics-guided fusion network combined with knowledge distillation for efficient salient object detection, along with a new large-scale dataset KD-SOD80K.

Findings

Achieves state-of-the-art accuracy with less than 1M parameters

Runs at 174 FPS in real-time

Demonstrates robustness and effectiveness through extensive experiments

Abstract

Most existing salient object detection (SOD) models are difficult to apply due to the complex and huge model structures. Although some lightweight models are proposed, the accuracy is barely satisfactory. In this paper, we design a novel semantics-guided contextual fusion network (SCFNet) that focuses on the interactive fusion of multi-level features for accurate and efficient salient object detection. Furthermore, we apply knowledge distillation to SOD task and provide a sizeable dataset KD-SOD80K. In detail, we transfer the rich knowledge from a seasoned teacher to the untrained SCFNet through unlabeled images, enabling SCFNet to learn a strong generalization ability to detect salient objects more accurately. The knowledge distillation based SCFNet (KDSCFNet) achieves comparable accuracy to the state-of-the-art heavyweight methods with less than 1M parameters and 174 FPS real-time detection speed. Extensive experiments demonstrate the robustness and effectiveness of the proposed distillation method and SOD framework. Code and data: https://github.com/zhangjinCV/KD-SCFNet.