Deep filter banks for texture recognition, description, and segmentation
Visual textures have played a key role in image understanding because they convey important semantics of images, and because texture representations that pool local image descriptors in an orderless manner have had a tremendous impact in diverse applications. In this paper we make several contributi...
| Κύριοι συγγραφείς: | , , , |
|---|---|
| Μορφή: | Conference item |
| Έκδοση: |
Springer
2016
|
| _version_ | 1826283860786151424 |
|---|---|
| author | Cimpoi, M Maji, S Kokkinos, I Vedaldi, A |
| author_facet | Cimpoi, M Maji, S Kokkinos, I Vedaldi, A |
| author_sort | Cimpoi, M |
| collection | OXFORD |
| description | Visual textures have played a key role in image understanding because they convey important semantics of images, and because texture representations that pool local image descriptors in an orderless manner have had a tremendous impact in diverse applications. In this paper we make several contributions to texture understanding. First, instead of focusing on texture instance and material category recognition, we propose a human-interpretable vocabulary of texture attributes to describe common texture patterns, complemented by a new describable texture dataset for benchmarking. Second, we look at the problem of recognizing materials and texture attributes in realistic imaging conditions, including when textures appear in clutter, developing corresponding benchmarks on top of the recently proposed OpenSurfaces dataset. Third, we revisit classic texture represenations, including bag-of-visual-words and the Fisher vectors, in the context of deep learning and show that these have excellent efficiency and generalization properties if the convolutional layers of a deep model are used as filter banks. We obtain in this manner state-of-the-art performance in numerous datasets well beyond textures, an efficient method to apply deep features to image regions, as well as benefit in transferring features from one domain to another. |
| first_indexed | 2024-03-07T01:05:12Z |
| format | Conference item |
| id | oxford-uuid:8b19a08b-47ca-4e25-8671-8868f091b219 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T01:05:12Z |
| publishDate | 2016 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:8b19a08b-47ca-4e25-8671-8868f091b2192022-03-26T22:35:52ZDeep filter banks for texture recognition, description, and segmentationConference itemhttp://purl.org/coar/resource_type/c_5794uuid:8b19a08b-47ca-4e25-8671-8868f091b219Symplectic Elements at OxfordSpringer2016Cimpoi, MMaji, SKokkinos, IVedaldi, AVisual textures have played a key role in image understanding because they convey important semantics of images, and because texture representations that pool local image descriptors in an orderless manner have had a tremendous impact in diverse applications. In this paper we make several contributions to texture understanding. First, instead of focusing on texture instance and material category recognition, we propose a human-interpretable vocabulary of texture attributes to describe common texture patterns, complemented by a new describable texture dataset for benchmarking. Second, we look at the problem of recognizing materials and texture attributes in realistic imaging conditions, including when textures appear in clutter, developing corresponding benchmarks on top of the recently proposed OpenSurfaces dataset. Third, we revisit classic texture represenations, including bag-of-visual-words and the Fisher vectors, in the context of deep learning and show that these have excellent efficiency and generalization properties if the convolutional layers of a deep model are used as filter banks. We obtain in this manner state-of-the-art performance in numerous datasets well beyond textures, an efficient method to apply deep features to image regions, as well as benefit in transferring features from one domain to another. |
| spellingShingle | Cimpoi, M Maji, S Kokkinos, I Vedaldi, A Deep filter banks for texture recognition, description, and segmentation |
| title | Deep filter banks for texture recognition, description, and segmentation |
| title_full | Deep filter banks for texture recognition, description, and segmentation |
| title_fullStr | Deep filter banks for texture recognition, description, and segmentation |
| title_full_unstemmed | Deep filter banks for texture recognition, description, and segmentation |
| title_short | Deep filter banks for texture recognition, description, and segmentation |
| title_sort | deep filter banks for texture recognition description and segmentation |
| work_keys_str_mv | AT cimpoim deepfilterbanksfortexturerecognitiondescriptionandsegmentation AT majis deepfilterbanksfortexturerecognitiondescriptionandsegmentation AT kokkinosi deepfilterbanksfortexturerecognitiondescriptionandsegmentation AT vedaldia deepfilterbanksfortexturerecognitiondescriptionandsegmentation |