KD-SCFNet: Towards More Accurate and Efficient Salient Object Detection via Knowledge Distillation
This addresses the need for efficient and accurate salient object detection models for real-time applications, though it is incremental as it builds on existing knowledge distillation techniques.
The paper tackles the problem of complex and large models in salient object detection by proposing a novel semantics-guided contextual fusion network (SCFNet) and applying knowledge distillation, achieving comparable accuracy to state-of-the-art methods with less than 1M parameters and 174 FPS speed.
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.