Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/134876
Citations | ||
Scopus | Web of ScienceĀ® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Deep descriptor Transforming for image co-localization |
Author: | Wei, X.S. Zhang, C.L. Li, Y. Xie, C.W. Wu, J. Shen, C. Zhou, Z.H. |
Citation: | IJCAI : proceedings of the conference / sponsored by the International Joint Conferences on Artificial Intelligence, 2017 / Sierra, C. (ed./s), vol.0, pp.3048-3054 |
Publisher: | AAAI Press |
Publisher Place: | USA |
Issue Date: | 2017 |
ISBN: | 9780999241103 |
ISSN: | 1045-0823 |
Conference Name: | International Joint Conference on Artificial Intelligence (IJCAI 2017) (19 Aug 2017 - 25 Aug 2017 : Melbourne, Australia) |
Editor: | Sierra, C. |
Statement of Responsibility: | Xiu-Shen Wei, Chen-Lin Zhang, Yao Li, Chen-Wei Xie, Jianxin Wu, Chunhua Shen, Zhi-Hua Zhou |
Abstract: | Reusable model design becomes desirable with the rapid expansion of machine learning applications. In this paper, we focus on the reusability of pre-trained deep convolutional models. Specifically, different from treating pre-trained models as feature extractors, we reveal more treasures beneath convolutional layers, i.e., the convolutional activations could act as a detector for the common object in the image colocalization problem. We propose a simple but effective method, named Deep Descriptor Transforming (DDT), for evaluating the correlations of descriptors and then obtaining the category-consistent regions, which can accurately locate the common object in a set of images. Empirical studies validate the effectiveness of the proposed DDT method. On benchmark image co-localization datasets, DDT consistently outperforms existing state-of-the-art methods by a large margin. Moreover, DDT also demonstrates good generalization ability for unseen categories and robustness for dealing with noisy data. |
Keywords: | Machine Learning: Unsupervised Learning; Machine Learning: Deep Learning; Robotics and Vision: Vision and Perception |
Rights: | copyright status unknown |
DOI: | 10.24963/ijcai.2017/425 |
Grant ID: | http://purl.org/au-research/grants/arc/FT120100969 |
Published version: | https://www.aaai.org/Press/press.php |
Appears in Collections: | Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.