| Paper Abstract and Keywords |
| Presentation |
2024-02-19 13:30
A Note on Domain Adaptation by Setting Features of Interest in Visual Language Models
Hiroki Okamura, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
| Abstract |
(in Japanese) |
(See Japanese page) |
| (in English) |
In this paper, we present a domain adaptation method for image classification using a visual-language model (VLM). Recently, VLMs that are trained with large numbers of image-text pairs have attracted attention. VLMs might already have observed a wide variety of domains, and they achieve high accuracy in zero-shot image classification of multiple domains. Especially, the domain adaptation performance of VLMs is enhanced by prompt engineering and prompt learning. However, prompt engineering is time-consuming, and prompt learning requires high-quality datasets that characterize the target domain, which limit its practical application. We thus propose a domain adaptation method that requires only features of interest in the target domain, as specified by a user. The proposed method can classify images based on simple words that represent the features of interest and improve the accuracy of image classification. |
| Keyword |
(in Japanese) |
(See Japanese page) |
| (in English) |
/ / / / / / / |
| Reference Info. |
ITE Tech. Rep., vol. 48, no. 6, ME2024-24, pp. 39-43, Feb. 2024. |
| Paper # |
ME2024-24 |
| Date of Issue |
2024-02-12 (MMS, ME, AIT) |
| ISSN |
Online edition: ISSN 2424-1970 |
| Download PDF |
|
| Conference Information |
| Committee |
IEICE-ITS IEICE-IE ME AIT MMS |
| Conference Date |
2024-02-19 - 2024-02-20 |
| Place (in Japanese) |
(See Japanese page) |
| Place (in English) |
Hokkaido Univ. |
| Topics (in Japanese) |
(See Japanese page) |
| Topics (in English) |
Image Processing, etc. |
| Paper Information |
| Registration To |
ME |
| Conference Code |
2024-02-ITS-IE-ME-AIT-MMS |
| Language |
Japanese |
| Title (in Japanese) |
(See Japanese page) |
| Sub Title (in Japanese) |
(See Japanese page) |
| Title (in English) |
A Note on Domain Adaptation by Setting Features of Interest in Visual Language Models |
| Sub Title (in English) |
|
| Keyword(1) |
|
| Keyword(2) |
|
| Keyword(3) |
|
| Keyword(4) |
|
| Keyword(5) |
|
| Keyword(6) |
|
| Keyword(7) |
|
| Keyword(8) |
|
| 1st Author's Name |
Hiroki Okamura |
| 1st Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
| 2nd Author's Name |
Keisuke Maeda |
| 2nd Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
| 3rd Author's Name |
Ren Togo |
| 3rd Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
| 4th Author's Name |
Takahiro Ogawa |
| 4th Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
| 5th Author's Name |
Miki Haseyama |
| 5th Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
| 6th Author's Name |
|
| 6th Author's Affiliation |
() |
| 7th Author's Name |
|
| 7th Author's Affiliation |
() |
| 8th Author's Name |
|
| 8th Author's Affiliation |
() |
| 9th Author's Name |
|
| 9th Author's Affiliation |
() |
| 10th Author's Name |
|
| 10th Author's Affiliation |
() |
| 11th Author's Name |
|
| 11th Author's Affiliation |
() |
| 12th Author's Name |
|
| 12th Author's Affiliation |
() |
| 13th Author's Name |
|
| 13th Author's Affiliation |
() |
| 14th Author's Name |
|
| 14th Author's Affiliation |
() |
| 15th Author's Name |
|
| 15th Author's Affiliation |
() |
| 16th Author's Name |
|
| 16th Author's Affiliation |
() |
| 17th Author's Name |
|
| 17th Author's Affiliation |
() |
| 18th Author's Name |
|
| 18th Author's Affiliation |
() |
| 19th Author's Name |
|
| 19th Author's Affiliation |
() |
| 20th Author's Name |
|
| 20th Author's Affiliation |
() |
| Speaker |
Author-1 |
| Date Time |
2024-02-19 13:30:00 |
| Presentation Time |
15 minutes |
| Registration for |
ME |
| Paper # |
MMS2024-8, ME2024-24, AIT2024-8 |
| Volume (vol) |
vol.48 |
| Number (no) |
no.6 |
| Page |
pp.39-43 |
| #Pages |
5 |
| Date of Issue |
2024-02-12 (MMS, ME, AIT) |
|