Sensors · 2022 · 11 citations · 28 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionDepth EstimationEarly FusionFeature DetectionObject DetectionScene UnderstandingVisual DetectionAccuracyImage Feature FusionKnowledge DistillationSalient Object DetectionTraining
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.
28
Feature Pyramid Networks for Object Detection
Tsung-Yi Lin, Piotr Dollár, Ross Girshick et al. · 2017 · 28.7K citations
Multi-Scale Interactive Network for Salient Object Detection
Youwei Pang, Xiaoqi Zhao, Lihe Zhang et al. · 2020 · 844 citations
Shifting More Attention to Video Salient Object Detection
Deng-Ping Fan, Wenguan Wang, Ming‐Ming Cheng et al. · 2019 · 529 citations