Review — CENet: Enhancing Diversity of Defocus Blur Detectors via Cross-Ensemble Network (Blur Detection)

Ensemble Network With Enhancing Diversity, Outperforms BTBNet & Park CVPR’17 / DHCF

Outline

1. Problem Formulation

An Example of Standard Network
Proposed Network

2. Single Detector Network (SENet)

Single Detector Network (SENet)

3. Multi-detector Ensemble Network (MENet)

Multi-detector Ensemble Network (MENet)

Although MENet improves the detection accuracy over SENet, it has limit when the input image has small-scale focused area or large-scale homogeneous regions.

The main reason is that MENet does not effectively encourage these detectors diversity.

4. Proposed Cross-Ensemble Network (CENet)

Proposed Cross-Ensemble Network (CENet)

Each detector is not only negatively correlated with the other detectors of the current group, but also with the ones of the other one group.

5. CENet: Network Architecture & Training & Testing

Network Architecture
Training Strategy
The gradients for the first branch
The gradients for the second branch

6. Experimental Results

Effectiveness of parameters γ and λ on both DUT and CUHK datasets.
Effectiveness of parameter K on both DUT and CUHK datasets.
Comparison of DBD Maps: From Top to Bottom, Images, SENet, MENet, CENet and Ground Truth
Visual comparison of DBD maps. First four from DUT dataset. Last four from CUHK dataset.
Quantitative comparison of F-measure and MAE scores
Comparison of precision-recall curves
Comparison of the average precision, recall, and F-measure scores

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store