Papers with Code · CC BY-SA 4.0

Dichotomous Image Segmentation

RGB Salient Object Detection › Dichotomous Image Segmentation 113 평가 기록 6 datasets

Currently, existing image segmentation tasks mainly focus on segmenting objects with specific characteristics, e.g., salient, camouflaged, meticulous, or specific categories. Most of them have the same input/output formats, and barely use exclusive mechanisms designed for segmenting targets in their models, which means almost all tasks are dataset-dependent. Thus, it is very promising to formulate a category-agnostic DIS task for accurately segmenting objects with different structure complexities, regardless of their characteristics. Compared with semantic segmentation, the proposed DIS task usually focuses on images with single or a few targets, from which getting richer accurate details of each target is more feasible.

논문

Pyramid Scene Parsing Network

1612.01105 2016-12-04 이 페이지의 평가 2건
max F-Measure: 0.691weighted F-measure: 0.603MAE: 0.102S-Measure: 0.744

Searching for MobileNetV3

1905.02244 2019-05-06 이 페이지의 평가 2건
max F-Measure: 0.714weighted F-measure: 0.642MAE: 0.092S-Measure: 0.758

Concealed Object Detection

2102.10274 2021-02-20 이 페이지의 평가 1건
max F-Measure: 0.665weighted F-measure: 0.584MAE: 0.110S-Measure: 0.727