Computer Vision Lab

Augmented Multiple Instance Regression for Inferring Object Contours in Bounding Boxes

¹Academia Sinica ²National Taiwan University

Abstract

In this paper, we address the problem of the high annotation cost of acquiring training data for semantic segmentation. Most modern approaches to semantic segmentation are based upon graphical models, such as the conditional random fields, and rely on sufficient training data in form of object contours. To reduce the manual effort on pixel-wise annotating contours, we consider the setting in which the training data set for semantic segmentation is a mixture of a few object contours and an abundant set of bounding boxes of objects. Our idea is to borrow the knowledge derived from the object contours to infer the unknown object contours enclosed by the bounding boxes. The inferred contours can then serve as training data for semantic segmentation. To this end, we generate multiple contour hypotheses for each bounding box with the assumption that at least one hypothesis is close to the ground truth. This paper proposes an approach, called augmented multiple instance regression (AMIR), that formulates the task of hypothesis selection as the problem of multiple instance regression (MIR), and augments information derived from the object contours to guide and regularize the training process of MIR. In this way, a bounding box is treated as a bag with its contour hypotheses as instances, and the positive instances refer to the hypotheses close to the ground truth. The proposed approach has been evaluated on the Pascal VOC segmentation task. The promising results demonstrate that AMIR can precisely infer the object contours in the bounding boxes, and hence provide effective alternatives to manually labeled contours for semantic segmentation

Publications:

"Augmented Multiple Instance Regression for Inferring Object Contours in Bounding Boxes", Kuang-Jui Hsu, Yen-Yu Lin, and Yung-Yu Chuang, in TIP 2014.

Related Works:

"Multiple Structured-Instance Learning for Semantic Segmentation with Uncertain Training Data", Feng-Ju Chang, Yen-Yu Lin, and Kuang-Jui Hsu, in CVPR 2014.
"Knowledge Leverage from Contours to Bounding Boxes: A Concise Approach to Annotation", Jie-Zhi Cheng, Feng-Ju Chang, Kuang-Jui Hsu, and Yen-Yu Lin, in ACCV 2012.

Resources:

Code

Bibtex

@ARTICLE{hsu14,
    AUTHOR    = "Kuang-Jui Hsu and Yen-Yu Lin and Yung-Yu Chuang", 
    TITLE     = "Augmented Multiple Instance Regression for Inferring Object Contours in Bounding Boxes",
    VOLUME = "23", 
    NUMBER = "4", 
    PAGES = "1722-1736", 
    JOURNAL = {IEEE Trans. on Image Processing (TIP 14)},
    YEAR = "2014",
}