Positive-Incentive Pseudo Label Optimization for Salient Object Detection
Open Access
- 8 October 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 153841-153850
Abstract
We present a salient object detection method in this paper. It uses a lightweight network based on multi-scale information aggregation (MIA) module and bidirectional cross-stage feature fusion (BCF2) module to speed up the reasoning process. Besides, it designs a stepwise coupling optimization strategy based on positive-incentive pseudo label to alleviate the miss detection rate for small objects and the false detection rate for big objects. It isworth noting that the positive-incentive pseudo label generation mechanism can increase the ratio of salient pixels in small objects to alleviate the severe category imbalance problem, while the stepwise coupling optimization strategy can avoid the misguidance of pseudo label to big objects. In addition, the experimental results demonstrate that our method is fairly efficient, its frame rate in reasoning phase reaches 275.6 FPS on NVIDIA RTX3080 GPU when the input resolution is set to 336 × 336.Keywords
Funding Information
- National Natural Science Foundation of China (62201454)
This publication has 58 references indexed in Scilit:
- Cross-Modal Fusion and Progressive Decoding Network for RGB-D Salient Object DetectionInternational Journal of Computer Vision, 2024
- Autonomous gait switching method and experiments of a hexapod walking robot for Mars environment with multiple terrainsIntelligent Service Robotics, 2024
- KD-SCFNet: Towards more accurate and lightweight salient object detection via knowledge distillationNeurocomputing, 2023
- MEANet: An effective and lightweight solution for salient object detection in optical remote sensing imagesExpert Systems with Applications, 2023
- Transformer-based visual object tracking via fine–coarse concatenated attention and cross concatenated MLPPattern Recognition, 2023
- Where you edit is what you get: Text-guided image editing with region-based attentionPattern Recognition, 2023
- EGA-Net: Edge feature enhancement and global information attention network for RGB-D salient object detectionInformation Sciences, 2023
- UDNet: Uncertainty-aware deep network for salient object detectionPattern Recognition, 2022
- TF-SOD: a novel transformer framework for salient object detectionNeural Computing and Applications, 2022
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015