| Paper Abstract and Keywords |
| Presentation |
2024-02-20 13:15
A Note on Improvement of Multimodal Large Language Model Considering Object Attributes and Relationships
Shunya Ohaga, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
| Abstract |
(in Japanese) |
(See Japanese page) |
| (in English) |
In this paper, we propose an enhanced Multimodal Large Language Model (MLLM) specifically designed to mitigate hallucinations related to the attributes of objects and their interrelations. The proposed method employs object detection models to obtain images centered on objects relevant to the given instructions, thereby improving the MLLM's ability to recognize object attributes and interrelations. By converting image information into text information and combining it with the instructions, the disparity in influence between images and text is reduced. Furthermore, specialized processing for instructions querying the number of objects is introduced to enhance response accuracy. Overall, this approach significantly improves the MLLM's recognition of object attributes and relationships. Experimental results show the effectiveness of the proposed method. |
| Keyword |
(in Japanese) |
(See Japanese page) |
| (in English) |
Multimodal Large Language Model / Hallucination / Attribute / Relation / Object Detection / / / |
| Reference Info. |
ITE Tech. Rep., vol. 48, no. 6, ME2024-43, pp. 132-136, Feb. 2024. |
| Paper # |
ME2024-43 |
| 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 Improvement of Multimodal Large Language Model Considering Object Attributes and Relationships |
| Sub Title (in English) |
|
| Keyword(1) |
Multimodal Large Language Model |
| Keyword(2) |
Hallucination |
| Keyword(3) |
Attribute |
| Keyword(4) |
Relation |
| Keyword(5) |
Object Detection |
| Keyword(6) |
|
| Keyword(7) |
|
| Keyword(8) |
|
| 1st Author's Name |
Shunya Ohaga |
| 1st Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
| 2nd Author's Name |
Ren Togo |
| 2nd Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
| 3rd Author's Name |
Takahiro Ogawa |
| 3rd Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
| 4th Author's Name |
Miki Haseyama |
| 4th Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
| 5th Author's Name |
|
| 5th Author's Affiliation |
() |
| 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 |
2024-02-20 13:15:00 |
| Presentation Time |
15 minutes |
| Registration for |
ME |
| Paper # |
MMS2024-27, ME2024-43, AIT2024-27 |
| Volume (vol) |
vol.48 |
| Number (no) |
no.6 |
| Page |
pp.132-136 |
| #Pages |
5 |
| Date of Issue |
2024-02-12 (MMS, ME, AIT) |