| Presentation | 2020-12-18 Rethinking the local similarity in content-based image retrieval Longjiao Zhao, Yu Wang, Yoshiharu Ishikawa, Jien Kato, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Recently, Convolutional Neural Networks(CNN) have shown good performance in the image retrieval task. Especially, local convolutional features which are extracted by CNN have presented outstanding result. Therefore, most of the works study on the pooling method which embeds the local features to global features and evaluate the global similarity between two images with global features. However, the global similarity is hard to present the effect of fine-grained information which is very important to the image retrieval task. Here, we propose a method that utilizes the local similarity to evaluate the images’ similarity. To do this, we generate a local similarity tensor(LST) and evaluate its effect from two aspects: spatial scale and local scale. Moreover, we propose a mask to the LST by analyzing the geometric features of images. Experiments demonstrate that LST can achieve higher accuracy than the baseline method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | image retrievallocal similaritydeep learning |
| Paper # | PRMU2020-68 |
| Date of Issue | 2020-12-10 (PRMU) |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2020/12/17(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Transfer learning and few shot learning |
| Chair | Yoichi Sato(Univ. of Tokyo) |
| Vice Chair | Akisato Kimura(NTT) / Masakazu Iwamura(Osaka Pref. Univ.) |
| Secretary | Akisato Kimura(Mobility Technologies) / Masakazu Iwamura(Chubu Univ.) |
| Assistant | Takashi Shibata(NTT) / Masashi Nishiyama(Tottori Univ.) |
| 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) | Rethinking the local similarity in content-based image retrieval |
| Sub Title (in English) | |
| Keyword(1) | image retrievallocal similaritydeep learning |
| 1st Author's Name | Longjiao Zhao |
| 1st Author's Affiliation | Nagoya University(Nagoya Univ.) |
| 2nd Author's Name | Yu Wang |
| 2nd Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ) |
| 3rd Author's Name | Yoshiharu Ishikawa |
| 3rd Author's Affiliation | Nagoya University(Nagoya Univ.) |
| 4th Author's Name | Jien Kato |
| 4th Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ) |
| Date | 2020-12-18 |
| Paper # | PRMU2020-68 |
| Volume (vol) | vol.120 |
| Number (no) | PRMU-300 |
| Page | pp.pp.172-176(PRMU), |
| #Pages | 5 |
| Date of Issue | 2020-12-10 (PRMU) |