Skip to content
Code accompanying the paper Optimizing the F-measure for Threshold-free Salient Object Detection.
TeX Python Shell
Branch: master
Clone or download
Latest commit 21bfcc2 Aug 13, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
latex LaTeX source Aug 13, 2019
lib code release Jul 31, 2019
models code release Jul 31, 2019
pytorch pytorch Aug 8, 2019
README.md code release Jul 31, 2019
train.py code release Jul 31, 2019

README.md

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

  1. Download and build caffe with python interface;
  2. Download the MSRA-B dataset to data/ and the initial VGG weights to model/
  3. Generate network and solver prototxt via python model/fdss.py;
  4. 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.

You can’t perform that action at this time.