computer-vision-11
Dichotomous Image Segmentation
3260 papers • 126 benchmarks • 313 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.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in dichotomous-image-segmentation-11
Trend
Dataset
Best Model
Actions
DIS-VD
DIS-VD
DIS-TE1
DIS-TE1
Libraries
iUse these libraries to find dichotomous-image-segmentation-11 models and implementations
7 papers 8,226
Datasets
Subtasks
No subtasks available.
Most implemented papers
U-Net: Convolutional Networks for Biomedical Image Segmentation
O. Ronneberger, T. Brox, P. Fischer•Sun May 17 2015
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
90626
