Scene recognition and weakly supervised object localization with deformable part-based models
Weakly supervised discovery of common visual structure in highly variable, cluttered images is a key problem in recognition. We address this problem using deformable part-based models (DPM's) with latent SVM training [6]. These models have been introduced for fully supervised training of object...
Saved in:
Published in | 2011 International Conference on Computer Vision pp. 1307 - 1314 |
---|---|
Main Authors | , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.11.2011
|
Online Access | Get full text |
Cover
Loading…
Summary: | Weakly supervised discovery of common visual structure in highly variable, cluttered images is a key problem in recognition. We address this problem using deformable part-based models (DPM's) with latent SVM training [6]. These models have been introduced for fully supervised training of object detectors, but we demonstrate that they are also capable of more open-ended learning of latent structure for such tasks as scene recognition and weakly supervised object localization. For scene recognition, DPM's can capture recurring visual elements and salient objects; in combination with standard global image features, they obtain state-of-the-art results on the MIT 67-category indoor scene dataset. For weakly supervised object localization, optimization over latent DPM parameters can discover the spatial extent of objects in cluttered training images without ground-truth bounding boxes. The resulting method outperforms a recent state-of-the-art weakly supervised object localization approach on the PASCAL-07 dataset. |
---|---|
ISBN: | 9781457711015 145771101X |
ISSN: | 1550-5499 2380-7504 |
DOI: | 10.1109/ICCV.2011.6126383 |