.png){kind=icon}
.png){kind=icon}
Return
Automatic visual pattern mining from categorical image dataset
.png){kind=icon}
PRE
AI
DOI：10.1007/s13735-018-0163-1.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We study in this paper the problem of visual pattern mining, which is to identify visually distinctive and semantically meaningful regions in images for solving various visual recognition tasks. Toward this goal, we propose a novel deep neural network architecture called PatternNet for discovering visual patterns that are both discriminative and representative. The proposed PatternNet leverages the filters in the last convolution layer of a convolutional neural network to find locally consistent visual patches, and by combining these filters we can effectively discover unique visual patterns. In addition, PatternNet can discover visual patterns efficiently without performing expensive image patch sampling, and this advantage provides an order of magnitude speedup compared to most other approaches. We evaluate the proposed PatternNet subjectively by showing randomly selected visual patterns which are discovered by our method and quantitatively by performing image classification with the identified visual patterns and comparing our performance with the current state-of-the-art. We also directly evaluate the quality of the discovered visual patterns by leveraging the identified patterns as proposed objects in an image and compare with other relevant methods.
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.9
Papers:
270
Citations:
866