Blocks that shout: distinctive parts for scene classification
The automatic discovery of distinctive parts for an object or scene class is challenging since it requires simultaneously to learn the part appearance and also to identify the part occurrences in images. In this paper, we propose a simple, efficient, and effective method to do so. We address this pr...
| Main Authors: | , , , |
|---|---|
| 格式: | Conference item |
| 出版: |
IEEE
2013
|
| _version_ | 1826257986274721792 |
|---|---|
| author | Juneja, M Vedaldi, A Jawahar, C Zisserman, A |
| author_facet | Juneja, M Vedaldi, A Jawahar, C Zisserman, A |
| author_sort | Juneja, M |
| collection | OXFORD |
| description | The automatic discovery of distinctive parts for an object or scene class is challenging since it requires simultaneously to learn the part appearance and also to identify the part occurrences in images. In this paper, we propose a simple, efficient, and effective method to do so. We address this problem by learning parts incrementally, starting from a single part occurrence with an Exemplar SVM. In this manner, additional part instances are discovered and aligned reliably before being considered as training examples. We also propose entropy-rank curves as a means of evaluating the distinctiveness of parts shareable between categories and use them to select useful parts out of a set of candidates. We apply the new representation to the task of scene categorisation on the MIT Scene 67 benchmark. We show that our method can learn parts which are significantly more informative and for a fraction of the cost, compared to previous part-learning methods such as Singh et al. [28]. We also show that a well constructed bag of words or Fisher vector model can substantially outperform the previous state-of-the-art classification performance on this data. |
| first_indexed | 2024-03-06T18:26:52Z |
| format | Conference item |
| id | oxford-uuid:084630ba-0e1e-4c84-a088-addf66dc8f9a |
| institution | University of Oxford |
| last_indexed | 2024-03-06T18:26:52Z |
| publishDate | 2013 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:084630ba-0e1e-4c84-a088-addf66dc8f9a2022-03-26T09:12:01ZBlocks that shout: distinctive parts for scene classificationConference itemhttp://purl.org/coar/resource_type/c_5794uuid:084630ba-0e1e-4c84-a088-addf66dc8f9aSymplectic Elements at OxfordIEEE2013Juneja, MVedaldi, AJawahar, CZisserman, AThe automatic discovery of distinctive parts for an object or scene class is challenging since it requires simultaneously to learn the part appearance and also to identify the part occurrences in images. In this paper, we propose a simple, efficient, and effective method to do so. We address this problem by learning parts incrementally, starting from a single part occurrence with an Exemplar SVM. In this manner, additional part instances are discovered and aligned reliably before being considered as training examples. We also propose entropy-rank curves as a means of evaluating the distinctiveness of parts shareable between categories and use them to select useful parts out of a set of candidates. We apply the new representation to the task of scene categorisation on the MIT Scene 67 benchmark. We show that our method can learn parts which are significantly more informative and for a fraction of the cost, compared to previous part-learning methods such as Singh et al. [28]. We also show that a well constructed bag of words or Fisher vector model can substantially outperform the previous state-of-the-art classification performance on this data. |
| spellingShingle | Juneja, M Vedaldi, A Jawahar, C Zisserman, A Blocks that shout: distinctive parts for scene classification |
| title | Blocks that shout: distinctive parts for scene classification |
| title_full | Blocks that shout: distinctive parts for scene classification |
| title_fullStr | Blocks that shout: distinctive parts for scene classification |
| title_full_unstemmed | Blocks that shout: distinctive parts for scene classification |
| title_short | Blocks that shout: distinctive parts for scene classification |
| title_sort | blocks that shout distinctive parts for scene classification |
| work_keys_str_mv | AT junejam blocksthatshoutdistinctivepartsforsceneclassification AT vedaldia blocksthatshoutdistinctivepartsforsceneclassification AT jawaharc blocksthatshoutdistinctivepartsforsceneclassification AT zissermana blocksthatshoutdistinctivepartsforsceneclassification |