Sökning: onr:"swepub:oai:DiVA.org:kth-246576" >
DEL :
DEL : Deep embedding learning for efficient image segmentation
-
- Liu, Yun (författare)
- Nankai Univ, Tianjin, Peoples R China.
-
- Jiang, Peng-Tao (författare)
- Nankai Univ, Tianjin, Peoples R China.
-
- Petrosyan, Vahan (författare)
- KTH,Reglerteknik
-
visa fler...
-
- Li, Shi-Jie (författare)
- Nankai Univ, Tianjin, Peoples R China.
-
- Bian, Jiawang (författare)
- Univ Adelaide, Adelaide, SA, Australia.
-
- Zhang, Le (författare)
- Adv Digital Sci Ctr, Singapore, Singapore.
-
- Cheng, Ming-Ming (författare)
- Nankai Univ, Tianjin, Peoples R China.
-
visa färre...
-
Nankai Univ, Tianjin, Peoples R China Reglerteknik (creator_code:org_t)
- California : International Joint Conferences on Artificial Intelligence, 2018
- 2018
- Engelska.
-
Ingår i: Proceedings Of The Twenty-Seventh International Joint Conference On Artificial Intelligence. - California : International Joint Conferences on Artificial Intelligence. ; , s. 864-870
- Relaterad länk:
-
https://doi.org/10.2...
-
visa fler...
-
https://www.ijcai.or...
-
https://urn.kb.se/re...
-
https://doi.org/10.2...
-
visa färre...
Abstract
Ämnesord
Stäng
- Image segmentation has been explored for many years and still remains a crucial vision problem. Some efficient or accurate segmentation algorithms have been widely used in many vision applications. However, it is difficult to design a both efficient and accurate image segmenter. In this paper, we propose a novel method called DEL (deep embedding learning) which can efficiently transform superpixels into image segmentation. Starting with the SLIC superpixels, we train a fully convolutional network to learn the feature embedding space for each superpixel. The learned feature embedding corresponds to a similarity measure that measures the similarity between two adjacent superpixels. With the deep similarities, we can directly merge the superpixels into large segments. The evaluation results on BSDS500 and PASCAL Context demonstrate that our approach achieves a good tradeoff between efficiency and effectiveness. Specifically, our DEL algorithm can achieve comparable segments when compared with MCG but is much faster than it, i.e. 11.4fps vs. 0.07fps.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Reglerteknik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Control Engineering (hsv//eng)
Nyckelord
- Artificial intelligence
- Deep learning
- Pixels
- Superpixels
- Convolutional networks
- Evaluation results
- Feature embedding
- Segmentation algorithms
- Segmenter
- Similarity measure
- Vision applications
- Vision problems
- Image segmentation
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)