Discerning Feature Supported Encoder for Image Representation

dc.contributor.authorWang, Shuyang
dc.contributor.authorDing, Zhengming
dc.contributor.authorFu, Yun
dc.contributor.departmentComputer Information and Graphics Technology, School of Engineering and Technologyen_US
dc.date.accessioned2020-12-23T16:08:41Z
dc.date.available2020-12-23T16:08:41Z
dc.date.issued2019
dc.description.abstractInspired by the recent successes of deep architecture, the auto-encoder and its variants have been intensively explored on image clustering and classification tasks by learning effective feature representations. Conventional auto-encoder attempts to uncover the data's intrinsic structure, by constraining the output to be as much identical to the input as possible, which denotes that the hidden representation could faithfully reconstruct the input data. One issue that arises, however, is that such representations might not be optimized for specific tasks, e.g., image classification and clustering, since it compresses not only the discriminative information but also a lot of redundant or even noise within data. In other words, not all hidden units would benefit the specific tasks, while partial units are mainly used to represent the task-irrelevant patterns. In this paper, a general framework named discerning feature supported encoder (DFSE) is proposed, which integrates the auto-encoder and feature selection together into a unified model. Specifically, the feature selection is adapted to learned hidden-layer features to capture the task-relevant ones from the task-irrelevant ones. Meanwhile, the selected hidden units could in turn encode more discriminability only on the selected task-relevant units. To this end, our proposed algorithm can generate more effective image representation by distinguishing the task-relevant features from the task-irrelevant ones. Two scenarios of the experiments on image classification and clustering are conducted to evaluate our algorithm. The experiments on several benchmarks demonstrate that our method can achieve better performance over the state-of-the-art approaches in two scenarios.en_US
dc.eprint.versionAuthor's manuscripten_US
dc.identifier.citationWang, S., Ding, Z., & Fu, Y. (2019). Discerning Feature Supported Encoder for Image Representation. IEEE Transactions on Image Processing, 28(8), 3728–3738. https://par.nsf.gov/biblio/10113619en_US
dc.identifier.urihttps://hdl.handle.net/1805/24717
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.relation.isversionof10.1109/TIP.2019.2900646en_US
dc.relation.journalIEEE Transactions on Image Processingen_US
dc.rightsPublisher Policyen_US
dc.sourceAuthoren_US
dc.subjectimage representationen_US
dc.subjectfeature extractionen_US
dc.subjectlearning systemsen_US
dc.titleDiscerning Feature Supported Encoder for Image Representationen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Wang_2019_discerning.pdf
Size:
3.06 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.99 KB
Format:
Item-specific license agreed upon to submission
Description: