| Presentation | 2022-08-04 Consideration of the structure of CNN models with high image classification performanc Mizuki Dai, Kenya Jinno, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, Transformer-based models such as ViT have shown remarkable performance in image recognition using Deep Learning. However, transformers have problems in terms of model size, memory footprint, and amount of training data required. In contrast, CNN models are lightweight, and their use is important in practical applications. In this study, we investigate the structure of CNN models with high performance from this perspective. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | CNN / CIFAR-10 / image classification / performance prediction |
| Paper # | CCS2022-27 |
| Date of Issue | 2022-07-28 (CCS) |
| Conference Information | |
| Committee | IN / CCS |
|---|---|
| Conference Date | 2022/8/4(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Hokkaido University(Centennial Hall) |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Network Science, Future Network, Cloud/SDN/Virtualization, Contents Delivery/Contents Exchange, and others |
| Chair | Kunio Hato(Internet Multifeed) / Megumi Akai(Hokkaido Univ.) |
| Vice Chair | Tsutomu Murase(Nagoya Univ.) / Hidehiro Nakano(Tokyo City Univ.) / Masaki Aida(TMU) |
| Secretary | Tsutomu Murase(KDDI Research) / Hidehiro Nakano(Nagaoka Univ. of Tech.) / Masaki Aida(NTT) |
| Assistant | / Hiroyuki Yasuda(Univ. of Tokyo) / Hiroyasu Ando(Tsukuba Univ.) / Tomoyuki Sasaki(Shonan Inst. of Tech.) / Miki Kobayashi(Rissho Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Information Networks / Technical Committee on Complex Communication Sciences |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Consideration of the structure of CNN models with high image classification performanc |
| Sub Title (in English) | |
| Keyword(1) | CNN |
| Keyword(2) | CIFAR-10 |
| Keyword(3) | image classification |
| Keyword(4) | performance prediction |
| 1st Author's Name | Mizuki Dai |
| 1st Author's Affiliation | Tokyo City University(Tokyo City University) |
| 2nd Author's Name | Kenya Jinno |
| 2nd Author's Affiliation | Tokyo City University(Tokyo City University) |
| Date | 2022-08-04 |
| Paper # | CCS2022-27 |
| Volume (vol) | vol.122 |
| Number (no) | CCS-145 |
| Page | pp.pp.6-9(CCS), |
| #Pages | 4 |
| Date of Issue | 2022-07-28 (CCS) |