Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2310.10070 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917079668490240 |
|---|---|
| author | Liang, Jiaming Xue, Yuwan Liu, Haowei Dai, Zhenqi Liao, Yu Wang, Rui Jiang, Weihao Liu, Yaping Chen, Zhikun Liu, Guoxiao Liu, Bo Bi, Xiuli |
| author_facet | Liang, Jiaming Xue, Yuwan Liu, Haowei Dai, Zhenqi Liao, Yu Wang, Rui Jiang, Weihao Liu, Yaping Chen, Zhikun Liu, Guoxiao Liu, Bo Bi, Xiuli |
| contents | In existing splicing forgery datasets, the insufficient semantic variety of spliced regions causes trained detection models to overfit semantic features rather than learn genuine splicing traces. Meanwhile, the lack of a reasonable benchmark dataset has led to inconsistent experimental settings across existing detection methods. To address these issues, we propose GreatSplicing, a manually created, large-scale, high-quality splicing dataset. GreatSplicing comprises 5,000 spliced images and covers spliced regions across 335 distinct semantic categories, enabling detection models to learn splicing traces more effectively. Empirical results show that detection models trained on GreatSplicing achieve low misidentification rates and stronger cross-dataset generalization compared to existing datasets. GreatSplicing is now publicly available for research purposes at the following link. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_10070 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | GreatSplicing: A Semantically Rich Splicing Dataset Liang, Jiaming Xue, Yuwan Liu, Haowei Dai, Zhenqi Liao, Yu Wang, Rui Jiang, Weihao Liu, Yaping Chen, Zhikun Liu, Guoxiao Liu, Bo Bi, Xiuli Computer Vision and Pattern Recognition Artificial Intelligence In existing splicing forgery datasets, the insufficient semantic variety of spliced regions causes trained detection models to overfit semantic features rather than learn genuine splicing traces. Meanwhile, the lack of a reasonable benchmark dataset has led to inconsistent experimental settings across existing detection methods. To address these issues, we propose GreatSplicing, a manually created, large-scale, high-quality splicing dataset. GreatSplicing comprises 5,000 spliced images and covers spliced regions across 335 distinct semantic categories, enabling detection models to learn splicing traces more effectively. Empirical results show that detection models trained on GreatSplicing achieve low misidentification rates and stronger cross-dataset generalization compared to existing datasets. GreatSplicing is now publicly available for research purposes at the following link. |
| title | GreatSplicing: A Semantically Rich Splicing Dataset |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2310.10070 |