Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/190415
Title: Weakly-Supervised Image Annotation and Segmentation with Objects and Attributes
Authors: Zhiyuan Shi;Yongxin Yang;Timothy M. Hospedales;Tao Xiang
Year: 2017
Publisher: IEEE
Abstract: We propose to model complex visual scenes using a non-parametric Bayesian model learned from weakly labelled images abundant on media sharing sites such as Flickr. Given weak image-level annotations of objects and attributes without locations or associations between them, our model aims to learn the appearance of object and attribute classes as well as their association on each object instance. Once learned, given an image, our model can be deployed to tackle a number of vision problems in a joint and coherent manner, including recognising objects in the scene (automatic object annotation), describing objects using their attributes (attribute prediction and association), and localising and delineating the objects (object detection and semantic segmentation). This is achieved by developing a novel Weakly Supervised Markov Random Field Stacked Indian Buffet Process (WS-MRF-SIBP) that models objects and attributes as latent factors and explicitly captures their correlations within and across superpixels. Extensive experiments on benchmark datasets demonstrate that our weakly supervised model significantly outperforms weakly supervised alternatives and is often comparable with existing strongly supervised models on a variety of tasks including semantic segmentation, automatic image annotation and retrieval based on object-attribute associations.
URI: http://localhost/handle/Hannan/190415
volume: 39
issue: 12
More Information: 2525,
2538
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7797474.pdf1.98 MBAdobe PDF
Title: Weakly-Supervised Image Annotation and Segmentation with Objects and Attributes
Authors: Zhiyuan Shi;Yongxin Yang;Timothy M. Hospedales;Tao Xiang
Year: 2017
Publisher: IEEE
Abstract: We propose to model complex visual scenes using a non-parametric Bayesian model learned from weakly labelled images abundant on media sharing sites such as Flickr. Given weak image-level annotations of objects and attributes without locations or associations between them, our model aims to learn the appearance of object and attribute classes as well as their association on each object instance. Once learned, given an image, our model can be deployed to tackle a number of vision problems in a joint and coherent manner, including recognising objects in the scene (automatic object annotation), describing objects using their attributes (attribute prediction and association), and localising and delineating the objects (object detection and semantic segmentation). This is achieved by developing a novel Weakly Supervised Markov Random Field Stacked Indian Buffet Process (WS-MRF-SIBP) that models objects and attributes as latent factors and explicitly captures their correlations within and across superpixels. Extensive experiments on benchmark datasets demonstrate that our weakly supervised model significantly outperforms weakly supervised alternatives and is often comparable with existing strongly supervised models on a variety of tasks including semantic segmentation, automatic image annotation and retrieval based on object-attribute associations.
URI: http://localhost/handle/Hannan/190415
volume: 39
issue: 12
More Information: 2525,
2538
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7797474.pdf1.98 MBAdobe PDF
Title: Weakly-Supervised Image Annotation and Segmentation with Objects and Attributes
Authors: Zhiyuan Shi;Yongxin Yang;Timothy M. Hospedales;Tao Xiang
Year: 2017
Publisher: IEEE
Abstract: We propose to model complex visual scenes using a non-parametric Bayesian model learned from weakly labelled images abundant on media sharing sites such as Flickr. Given weak image-level annotations of objects and attributes without locations or associations between them, our model aims to learn the appearance of object and attribute classes as well as their association on each object instance. Once learned, given an image, our model can be deployed to tackle a number of vision problems in a joint and coherent manner, including recognising objects in the scene (automatic object annotation), describing objects using their attributes (attribute prediction and association), and localising and delineating the objects (object detection and semantic segmentation). This is achieved by developing a novel Weakly Supervised Markov Random Field Stacked Indian Buffet Process (WS-MRF-SIBP) that models objects and attributes as latent factors and explicitly captures their correlations within and across superpixels. Extensive experiments on benchmark datasets demonstrate that our weakly supervised model significantly outperforms weakly supervised alternatives and is often comparable with existing strongly supervised models on a variety of tasks including semantic segmentation, automatic image annotation and retrieval based on object-attribute associations.
URI: http://localhost/handle/Hannan/190415
volume: 39
issue: 12
More Information: 2525,
2538
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7797474.pdf1.98 MBAdobe PDF