S-measure: 0.734weighted F-measure: 0.476MAE: 0.010mDice: 0.497
Papers with Code · CC BY-SA 4.0
Camouflaged Object Segmentation
Camouflaged object segmentation (COS) or Camouflaged object detection (COD), which was originally promoted by T.-N. Le et al. (2017), aims to identify objects that conceal their texture into the surrounding environment. The high intrinsic similarities between the target object and the background make COS/COD far more challenging than the traditional object segmentation task. Also, refer to the online benchmarks on CAMO dataset, COD dataset, and online demo.
<span style="color:grey; opacity: 0.6">( Image source: Anabranch Network for Camouflaged Object Segmentation )</span>
논문
S-measure: 0.932weighted F-measure: 0.914MAE: 0.015
S-measure: 0.888weighted F-measure: 0.816MAE: 0.030
S-measure: 0.922weighted F-measure: 0.908MAE: 0.017
MAE: 0.092Weighted F-Measure: 0.352S-Measure: 0.685
S-measure: 0.765weighted F-measure: 0.607MAE: 0.007mDice: 0.62
MAE: 0.092Weighted F-Measure: 0.352S-Measure: 0.685
S-Measure: 0.895
MAE: 0.059Weighted F-Measure: 0.508S-Measure: 0.747
S-Measure: 0.922
S-Measure: 0.893
MAE: 0.056Weighted F-Measure: 0.509S-Measure: 0.737
MAE: 0.029Weighted F-Measure: 0.742S-Measure: 0.843
MAE: 0.029Weighted F-Measure: 0.746S-Measure: 0.843
S-Measure: 0.885
S-Measure: 0.916
S-measure: 0.631weighted F-measure: 0.311MAE: 0.027mDice: 0.360
S-Measure: 0.904
S-Measure: 0.888
S-Measure: 0.897
S-measure: 0.776weighted F-measure: 0.628MAE: 0.008mDice: 0.648