A
Adela Barriuso
Researcher at Massachusetts Institute of Technology
Publications - 7
Citations - 3817
Adela Barriuso is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Image segmentation & Parsing. The author has an hindex of 5, co-authored 6 publications receiving 2084 citations.
Papers
More filters
Proceedings ArticleDOI
Scene Parsing through ADE20K Dataset
TL;DR: The ADE20K dataset, spanning diverse annotations of scenes, objects, parts of objects, and in some cases even parts of parts, is introduced and it is shown that the trained scene parsing networks can lead to applications such as image content removal and scene synthesis.
Journal ArticleDOI
Semantic Understanding of Scenes Through the ADE20K Dataset
TL;DR: The ADE20K dataset as discussed by the authors contains 25k images of complex everyday scenes containing a variety of objects in their natural spatial context, on average there are 19.5 instances and 10.5 object classes per image.
Posted Content
Semantic Understanding of Scenes through the ADE20K Dataset
TL;DR: This work presents a densely annotated dataset ADE20K, which spans diverse annotations of scenes, objects, parts of objects, and in some cases even parts of parts, and shows that the networks trained on this dataset are able to segment a wide variety of scenes and objects.
Proceedings ArticleDOI
DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
Yuxuan Zhang,Huan Ling,Jun Gao,Kangxue Yin,Jean-Francois Lafleche,Adela Barriuso,Antonio Torralba,Sanja Fidler +7 more
TL;DR: DatasetGAN as discussed by the authors uses GANs to generate high-quality semantically segmented images, which can then be used for training any computer vision architecture just as real datasets are.
Posted Content
Notes on image annotation
Adela Barriuso,Antonio Torralba +1 more
TL;DR: An expert image annotator relates her experience on segmenting and labeling tens of thousands of images and the notes she took try to highlight the difficulties encountered, the solutions adopted, and the decisions made in order to get a consistent set of annotations.