Towards Reliable Advertising Image Generation Using Human Feedback
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_ | 1866929445916377088 |
|---|---|
| author | Du, Zhenbang Feng, Wei Wang, Haohan Li, Yaoyu Wang, Jingsen Li, Jian Zhang, Zheng Lv, Jingjing Zhu, Xin Jin, Junsheng Shen, Junjie Lin, Zhangang Shao, Jingping |
| author_facet | Du, Zhenbang Feng, Wei Wang, Haohan Li, Yaoyu Wang, Jingsen Li, Jian Zhang, Zheng Lv, Jingjing Zhu, Xin Jin, Junsheng Shen, Junjie Lin, Zhangang Shao, Jingping |
| contents | In the e-commerce realm, compelling advertising images are pivotal for attracting customer attention. While generative models automate image generation, they often produce substandard images that may mislead customers and require significant labor costs to inspect. This paper delves into increasing the rate of available generated images. We first introduce a multi-modal Reliable Feedback Network (RFNet) to automatically inspect the generated images. Combining the RFNet into a recurrent process, Recurrent Generation, results in a higher number of available advertising images. To further enhance production efficiency, we fine-tune diffusion models with an innovative Consistent Condition regularization utilizing the feedback from RFNet (RFFT). This results in a remarkable increase in the available rate of generated images, reducing the number of attempts in Recurrent Generation, and providing a highly efficient production process without sacrificing visual appeal. We also construct a Reliable Feedback 1 Million (RF1M) dataset which comprises over one million generated advertising images annotated by human, which helps to train RFNet to accurately assess the availability of generated images and faithfully reflect the human feedback. Generally speaking, our approach offers a reliable solution for advertising image generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_00418 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Reliable Advertising Image Generation Using Human Feedback Du, Zhenbang Feng, Wei Wang, Haohan Li, Yaoyu Wang, Jingsen Li, Jian Zhang, Zheng Lv, Jingjing Zhu, Xin Jin, Junsheng Shen, Junjie Lin, Zhangang Shao, Jingping Computer Vision and Pattern Recognition In the e-commerce realm, compelling advertising images are pivotal for attracting customer attention. While generative models automate image generation, they often produce substandard images that may mislead customers and require significant labor costs to inspect. This paper delves into increasing the rate of available generated images. We first introduce a multi-modal Reliable Feedback Network (RFNet) to automatically inspect the generated images. Combining the RFNet into a recurrent process, Recurrent Generation, results in a higher number of available advertising images. To further enhance production efficiency, we fine-tune diffusion models with an innovative Consistent Condition regularization utilizing the feedback from RFNet (RFFT). This results in a remarkable increase in the available rate of generated images, reducing the number of attempts in Recurrent Generation, and providing a highly efficient production process without sacrificing visual appeal. We also construct a Reliable Feedback 1 Million (RF1M) dataset which comprises over one million generated advertising images annotated by human, which helps to train RFNet to accurately assess the availability of generated images and faithfully reflect the human feedback. Generally speaking, our approach offers a reliable solution for advertising image generation. |
| title | Towards Reliable Advertising Image Generation Using Human Feedback |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.00418 |