BASNet, or Boundary-Aware Segmentation Network, is an image segmentation architecture that consists of a predict-refine architecture and a hybrid loss. The proposed BASNet comprises a predict-refine architecture and a hybrid loss, for highly accurate image segmentation. The predict-refine architecture consists of a densely supervised encoder-decoder network and a residual refinement module, which are respectively used to predict and refine a segmentation probability map. The hybrid loss is a combination of the binary cross entropy, structural similarity and intersection-over-union losses, which guide the network to learn three-level (i.e., pixel-, patch- and map- level) hierarchy representations.
Source: Boundary-Aware Segmentation Network for Mobile and Web ApplicationsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 1 | 12.50% |
Salient Object Detection | 1 | 12.50% |
Action Localization | 1 | 12.50% |
Temporal Action Localization | 1 | 12.50% |
Weakly-supervised Temporal Action Localization | 1 | 12.50% |
Camouflaged Object Segmentation | 1 | 12.50% |
Image Segmentation | 1 | 12.50% |
Semantic Segmentation | 1 | 12.50% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |