Dynamic Knowledge Distillation with Noise Elimination for RGB-D Salient Object Detection

Guangyu Ren*, Yinxiao Yu, Hengyan Liu, Tania Stathaki

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)


RGB-D salient object detection (SOD) demonstrates its superiority in detecting in complex environments due to the additional depth information introduced in the data. Inevitably, an independent stream is introduced to extract features from depth images, leading to extra computation and parameters. This methodology sacrifices the model size to improve the detection accuracy which may impede the practical application of SOD problems. To tackle this dilemma, we propose a dynamic knowledge distillation (DKD) method, along with a lightweight structure, which significantly reduces the computational burden while maintaining validity. This method considers the factors of both teacher and student performance within the training stage and dynamically assigns the distillation weight instead of applying a fixed weight on the student model. We also investigate the issue of RGB-D early fusion strategy in distillation and propose a simple noise elimination method to mitigate the impact of distorted training data caused by low quality depth maps. Extensive experiments are conducted on five public datasets to demonstrate that our method can achieve competitive performance with a fast inference speed (136FPS) compared to 12 prior methods.

Original languageEnglish
Article number6188
Issue number16
Publication statusPublished - Aug 2022
Externally publishedYes


  • RGB-D
  • dynamic knowledge distillation
  • salient object detection


Dive into the research topics of 'Dynamic Knowledge Distillation with Noise Elimination for RGB-D Salient Object Detection'. Together they form a unique fingerprint.

Cite this