| Presentation | 2021-12-16 Unsupervised Logo Detection Using Adversarial Learning from Synthetic to Real Images Rahul Kumar Jain, Takahiro Sato, Taro Watasue, Tomohiro Nakagawa, Yutaro Iwamoto, Xiang Ruan, Yen-Wei Chen, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Most of the existing deep learning based logo detection methods typically use a large amount of annotated training data, assuming that the training and test data belong to the same data distribution. Synthesized training images with automatically generated object-level annotations can be a solution to avoid the labor-intensive and time-consuming object annotation task. However, real-world problems limit this assumption and object detectors face domain-shift problems resulting in performance degradation. Here, we address the domain-shift problem in the field of logo detection from synthetic to real images. In this paper, to align the domain gap from synthetic to real image, we propose to use entropy minimization of mid-level output feature maps. We also synthesize training images using various data augmentation methods to perform experiments. Our experiments show that our proposed method improves performance by around 4% mAP compared to direct transfer from source to target domain (synthetic-to-real images) without any labeling cost and increasing network parameters. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Unsupervised Domain AdaptationAdversarial LearningAnchorless Object DetectorsEntropy Minimization |
| Paper # | PRMU2021-31 |
| Date of Issue | 2021-12-09 (PRMU) |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2021/12/16(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Seiichi Uchida(Kyushu Univ.) |
| Vice Chair | Masakazu Iwamura(Osaka Pref. Univ.) / Mitsuru Anpai(Denso IT Lab.) |
| Secretary | Masakazu Iwamura(NTT) / Mitsuru Anpai(Tottori Univ.) |
| Assistant | Kouta Yamaguchi(CyberAgent) / Yusuke Matsui(Univ. of Tokyo) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding |
|---|---|
| Language | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Unsupervised Logo Detection Using Adversarial Learning from Synthetic to Real Images |
| Sub Title (in English) | |
| Keyword(1) | Unsupervised Domain AdaptationAdversarial LearningAnchorless Object DetectorsEntropy Minimization |
| 1st Author's Name | Rahul Kumar Jain |
| 1st Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
| 2nd Author's Name | Takahiro Sato |
| 2nd Author's Affiliation | tiwaki Co. Ltd.(tiwaki) |
| 3rd Author's Name | Taro Watasue |
| 3rd Author's Affiliation | tiwaki Co. Ltd.(tiwaki) |
| 4th Author's Name | Tomohiro Nakagawa |
| 4th Author's Affiliation | tiwaki Co. Ltd.(tiwaki) |
| 5th Author's Name | Yutaro Iwamoto |
| 5th Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
| 6th Author's Name | Xiang Ruan |
| 6th Author's Affiliation | tiwaki Co. Ltd.(tiwaki) |
| 7th Author's Name | Yen-Wei Chen |
| 7th Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
| Date | 2021-12-16 |
| Paper # | PRMU2021-31 |
| Volume (vol) | vol.121 |
| Number (no) | PRMU-304 |
| Page | pp.pp.43-44(PRMU), |
| #Pages | 2 |
| Date of Issue | 2021-12-09 (PRMU) |