Optimizing the F-measure for Threshold-free Salient Object Detection
Code accompanying the paper Optimizing the F-measure for Threshold-free Salient Object Detection.
Howto
- Download and build caffe with python interface;
- Download the MSRA-B dataset to
data/
and the initial VGG weights tomodel/
- Generate network and solver prototxt via
python model/fdss.py
; - Start training the DSS+FLoss model with
python train.py --solver tmp/fdss_beta0.80_aug_solver.pt
Loss surface
The proposed FLoss holds considerable gradients even in the saturated area, resulting in polarized predictions that are stable against the threshold.
Loss surface of FLoss (left), Log-FLoss (mid) and Cross-entropy loss (right). FLoss holds larger gradients in the saturated area, leading to high-contrast predictions.
Example detection results
Several detection results. Our method results in high-contrast detections.
Stability against threshold
FLoss (solid lines) achieves high F-measure under a larger range of thresholds, presenting stability against the changing of threshold.
Pretrained models
For pretrained models and evaluation results, please visit http://kaizhao.net/fmeasure.
If you have any problem using this code, please contact Kai Zhao.