TY - GEN
T1 - Semantic Similarity-based Visual Reasoning without Language Information
AU - Choi, Changsu
AU - Lim, Hyeonseok
AU - Jang, Hayoung
AU - Park, Juhan
AU - Kim, Eunkyung
AU - Lim, Kyungtae
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - In this research, we propose new training data for the visual reasoning task based on semantic similarity and proposed a deep learning model that utilizes the data. The first contribution of this study is the construction of training data. Based on a total of 40 object attributes, we created a visual inference problem using only image data. As a result, a total of 6,000 datasets were built to create training and test data. We also propose a visual inference model as the second contribution of this work. The inference model shown in this study was evaluated for two tasks using ResNet50 and Vision Transformer, respectively. Based on the experimental evaluation results, we investigated the suitable pre-trained model for both single-choice binary reasoning and multiple-selection reasoning, respectively.
AB - In this research, we propose new training data for the visual reasoning task based on semantic similarity and proposed a deep learning model that utilizes the data. The first contribution of this study is the construction of training data. Based on a total of 40 object attributes, we created a visual inference problem using only image data. As a result, a total of 6,000 datasets were built to create training and test data. We also propose a visual inference model as the second contribution of this work. The inference model shown in this study was evaluated for two tasks using ResNet50 and Vision Transformer, respectively. Based on the experimental evaluation results, we investigated the suitable pre-trained model for both single-choice binary reasoning and multiple-selection reasoning, respectively.
KW - Deep Learning
KW - Image similarity
KW - Inference
KW - Visual Reasoning
UR - https://www.scopus.com/pages/publications/85151977214
U2 - 10.1109/ICAIIC57133.2023.10067104
DO - 10.1109/ICAIIC57133.2023.10067104
M3 - Conference contribution
AN - SCOPUS:85151977214
T3 - 5th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2023
SP - 107
EP - 111
BT - 5th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2023
Y2 - 20 February 2023 through 23 February 2023
ER -