论文标题
KD-SCFNET：通过知识蒸馏更准确，更有效的显着对象检测
KD-SCFNet: Towards More Accurate and Efficient Salient Object Detection via Knowledge Distillation
论文作者
论文摘要
由于复杂且庞大的模型结构，大多数现有的显着对象检测（SOD）模型很难应用。尽管提出了一些轻巧的模型，但准确性几乎不令人满意。在本文中，我们设计了一种新型的语义引导的上下文融合网络（SCFNET），该网络重点介绍了多层次特征的互动融合，以进行准确有效的显着对象检测。此外，我们将知识蒸馏应用于SOD任务，并提供相当大的数据集KD-SOD80K。详细说明，我们通过未标记的图像将丰富的知识从经验丰富的老师转移到未经训练的SCFNET，使SCFNet能够学习强大的概括能力，以更准确地检测出明显的对象。基于知识蒸馏的SCFNET（KDSCFNET）的精度与最先进的重量级方法相当的精度具有少于1M参数和174 fps实时检测速度。广泛的实验证明了所提出的蒸馏方法和SOD框架的鲁棒性和有效性。代码和数据：https：//github.com/zhangjincv/kd-scfnet。
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.
