Joint Inference in Weakly-Annotated Image Datasets via Dense Correspondence
We present a principled framework for inferring pixel labels in weakly-annotated image datasets. Most previous, example-based approaches to computer vision rely on a large corpus of densely labeled images. However, for large, modern image datasets, such labels are expensive to obtain and are often u...
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
Springer US,
2017-02-15T16:20:20Z.
|
Subjects: | |
Online Access: | Get fulltext |