Back to Search
Start Over
DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Discriminative Multi-Scale Deep Features
- Source :
- IEEE Transactions on Pattern Analysis and Machine Intelligence. 44:955-968
- Publication Year :
- 2022
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2022.
-
Abstract
- Albeit great success has been achieved in image defocus blur detection, there are still several unsolved challenges, e.g., interference of background clutter, scale sensitivity and missing boundary details of blur regions. To deal with these issues, we propose a deep neural network which recurrently fuses and refines multi-scale deep features (DeFusionNet) for defocus blur detection. We first fuse the features from different layers of FCN as shallow features and semantic features, respectively. Then, the fused shallow features are propagated to deep layers for refining the details of detected defocus blur regions, and the fused semantic features are propagated to shallow layers to assist in better locating blur regions. The fusion and refinement are carried out recurrently. In order to narrow the gap between low-level and high-level features, we embed a feature adaptation module before feature propagating to exploit the complementary information as well as reduce the contradictory response of different feature layers. Since different feature channels are with different extents of discrimination for detecting blur regions, we design a channel attention module to select discriminative features for feature refinement. Finally, the output of each layer at last recurrent step are fused to obtain the final result. We collect a new dataset consists of various challenging images and their pixel-wise annotations for promoting further study. Extensive experiments on two commonly used datasets and our newly collected one are conducted to demonstrate both the efficacy and efficiency of DeFusionNet.
- Subjects :
- Artificial neural network
Channel Attention
Computer science
business.industry
Applied Mathematics
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Multi-scale Features
Pattern recognition
Feature Fusing
02 engineering and technology
Defocus Blur Detection
Computational Theory and Mathematics
Discriminative model
Artificial Intelligence
Feature (computer vision)
0202 electrical engineering, electronic engineering, information engineering
Clutter
020201 artificial intelligence & image processing
Computer Vision and Pattern Recognition
Sensitivity (control systems)
Artificial intelligence
Scale (map)
business
Software
Subjects
Details
- ISSN :
- 19393539 and 01628828
- Volume :
- 44
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Accession number :
- edsair.doi.dedup.....9ec21088be51523fdf44f8645eebcbb4