Ensemble Predicate Decoding for Unbiased Scene Graph Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909295884369920 |
|---|---|
| author | Feng, Jiasong Wang, Lichun Xu, Hongbo Xu, Kai Yin, Baocai |
| author_facet | Feng, Jiasong Wang, Lichun Xu, Hongbo Xu, Kai Yin, Baocai |
| contents | Scene Graph Generation (SGG) aims to generate a comprehensive graphical representation that accurately captures the semantic information of a given scenario. However, the SGG model's performance in predicting more fine-grained predicates is hindered by a significant predicate bias. According to existing works, the long-tail distribution of predicates in training data results in the biased scene graph. However, the semantic overlap between predicate categories makes predicate prediction difficult, and there is a significant difference in the sample size of semantically similar predicates, making the predicate prediction more difficult. Therefore, higher requirements are placed on the discriminative ability of the model. In order to address this problem, this paper proposes Ensemble Predicate Decoding (EPD), which employs multiple decoders to attain unbiased scene graph generation. Two auxiliary decoders trained on lower-frequency predicates are used to improve the discriminative ability of the model. Extensive experiments are conducted on the VG, and the experiment results show that EPD enhances the model's representation capability for predicates. In addition, we find that our approach ensures a relatively superior predictive capability for more frequent predicates compared to previous unbiased SGG methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_14187 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Ensemble Predicate Decoding for Unbiased Scene Graph Generation Feng, Jiasong Wang, Lichun Xu, Hongbo Xu, Kai Yin, Baocai Computer Vision and Pattern Recognition Scene Graph Generation (SGG) aims to generate a comprehensive graphical representation that accurately captures the semantic information of a given scenario. However, the SGG model's performance in predicting more fine-grained predicates is hindered by a significant predicate bias. According to existing works, the long-tail distribution of predicates in training data results in the biased scene graph. However, the semantic overlap between predicate categories makes predicate prediction difficult, and there is a significant difference in the sample size of semantically similar predicates, making the predicate prediction more difficult. Therefore, higher requirements are placed on the discriminative ability of the model. In order to address this problem, this paper proposes Ensemble Predicate Decoding (EPD), which employs multiple decoders to attain unbiased scene graph generation. Two auxiliary decoders trained on lower-frequency predicates are used to improve the discriminative ability of the model. Extensive experiments are conducted on the VG, and the experiment results show that EPD enhances the model's representation capability for predicates. In addition, we find that our approach ensures a relatively superior predictive capability for more frequent predicates compared to previous unbiased SGG methods. |
| title | Ensemble Predicate Decoding for Unbiased Scene Graph Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.14187 |