Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2405.12648 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909207789305856 |
|---|---|
| author | Kim, Hyeongjin Kim, Sangwon Ahn, Dasom Lee, Jong Taek Ko, Byoung Chul |
| author_facet | Kim, Hyeongjin Kim, Sangwon Ahn, Dasom Lee, Jong Taek Ko, Byoung Chul |
| contents | Scene graph generation (SGG) is an important task in image understanding because it represents the relationships between objects in an image as a graph structure, making it possible to understand the semantic relationships between objects intuitively. Previous SGG studies used a message-passing neural networks (MPNN) to update features, which can effectively reflect information about surrounding objects. However, these studies have failed to reflect the co-occurrence of objects during SGG generation. In addition, they only addressed the long-tail problem of the training dataset from the perspectives of sampling and learning methods. To address these two problems, we propose CooK, which reflects the Co-occurrence Knowledge between objects, and the learnable term frequency-inverse document frequency (TF-l-IDF) to solve the long-tail problem. We applied the proposed model to the SGG benchmark dataset, and the results showed a performance improvement of up to 3.8% compared with existing state-of-the-art models in SGGen subtask. The proposed method exhibits generalization ability from the results obtained, showing uniform performance improvement for all MPNN models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_12648 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency Kim, Hyeongjin Kim, Sangwon Ahn, Dasom Lee, Jong Taek Ko, Byoung Chul Computer Vision and Pattern Recognition Artificial Intelligence Scene graph generation (SGG) is an important task in image understanding because it represents the relationships between objects in an image as a graph structure, making it possible to understand the semantic relationships between objects intuitively. Previous SGG studies used a message-passing neural networks (MPNN) to update features, which can effectively reflect information about surrounding objects. However, these studies have failed to reflect the co-occurrence of objects during SGG generation. In addition, they only addressed the long-tail problem of the training dataset from the perspectives of sampling and learning methods. To address these two problems, we propose CooK, which reflects the Co-occurrence Knowledge between objects, and the learnable term frequency-inverse document frequency (TF-l-IDF) to solve the long-tail problem. We applied the proposed model to the SGG benchmark dataset, and the results showed a performance improvement of up to 3.8% compared with existing state-of-the-art models in SGGen subtask. The proposed method exhibits generalization ability from the results obtained, showing uniform performance improvement for all MPNN models. |
| title | Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2405.12648 |