Journal of King Saud University - Computer and Information Sciences · 2023 · 24 citations · 64 references
ComputingComputer ScienceComputer VisionMachine VisionSensor FusionFeature DetectionFeature-level FusionImage Feature EngineeringImage FusionObject DetectionObject RecognitionCross-modal FusionCross-modal Object DetectionImage Feature FusionModal FusionMultimodal Feature FusionMultimodal Object DetectionMultisensor Feature FusionSalient Object Detection
In recent years, bimodal salient object detection has developed rapidly. In view of the advanced performance of their robustness to extreme situations such as background similarity and illumination variation, researchers began to focus on RGB-Depth-Thermal salient object detection (RGB-D-T SOD). However, most existing bimodal methods usually need expensive computational costs to complete accurate prediction, and this situation is even more serious for three-modal methods, which undoubtedly limits their applicability. To solve this problem, we are the first to propose a lightweight multi-level feature difference fusion network (MFDF) for real-time RGB-D-T SOD. In view of the depth modality contains less useful information, we design an asymmetric three-stream encoder based on MobileNetV2. Due to the differences in semantics and details between high and low level features, using the same module without discrimination will lead to a large number of redundant parameters. On the contrary, in the coding stage, we introduce a cross-modal enhancement module (CME) and a cross-modal fusion module (CMF) to fuse low-level and high-level features respectively. In order to reduce redundant parameters, we design a low-level feature decoding module (LFD) and a multi-scale high-level feature fusion module (MHFF). A great deal of experiments proves that the proposed MFDF has more advantages than the 17 state-of-the-art methods. On the efficiency side, MFDF has a faster speed (124 FPS when the image size is 320 × 320) and much fewer parameters (8.9 M).
64
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Mark Sandler, Andrew Howard, Menglong Zhu et al. · 2018 · 25.4K citations
Saliency filters: Contrast based filtering for salient region detection
Federico Perazzi, Philipp Krähenbühl, Yael Pritch et al. · 2012 · 2.1K citations
Structure-Measure: A New Way to Evaluate Foreground Maps
Deng-Ping Fan, Ming‐Ming Cheng, Yun Liu et al. · 2017 · 1.8K citations