Weakly Supervised Discriminative Localization and Classification: A Joint Learning Process
Abstract
Visual categorization problems, such as object classification or action recognition, are increasingly often approached using a detection strategy: a classifier function is first applied to candidate subwindows of the image or the video, and then the maximum classifier score is used for class decision. Traditionally, the subwindow classifiers are trained on a large collection of examples manually annotated with masks or bounding boxes. The reliance on time-consuming human labeling effectively limits the application of these methods to problems involving very few categories. Furthermore, the human selection of the masks introduces arbitrary biases (e.g. in terms of window size and location) which may be suboptimal for classification.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 15, 2009
- Accession Number
- ADA507101
Entities
People
- Carsten Rother
- Fernando De La Torre
- Lorenzo Torresani
- Minh H. Nguyen
Organizations
- Carnegie Mellon University