Cross-Breed Few-Shot Learning for Pig Detection via Improved YOLOv7 and CycleGAN-Based Sample Generation
Yizheng Zhuang, Lingyao Xu, Jinyun Jiang, Zhenyang Zhang, Yiting Wang, Pengfei Yu, Yihan Fu, Haoqi Xu, Wei Zhao, Xiaoliang Hou, Jianlan Wang, Yongqi He, Yan Fu, Zhe Zhang, Qishan Wang, Yuchun Pan, Zhen Wang · 2026
Read Cross-Breed Few-Shot Learning for Pig Detection via Improved YOLOv7 and CycleGAN-Based Sample Generation by Yizheng Zhuang, Lingyao Xu, Jinyun Jiang, Zhenyang Zhang, Yiting Wang, Pengfei Yu, Yihan Fu, Haoqi Xu, Wei Zhao, Xiaoliang Hou, Jianlan Wang, Yongqi He, Yan Fu, Zhe Zhang, Qishan Wang, Yuchun Pan, Zhen Wang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13113105.txt.
Description
Yizheng Zhuang and co-authors spot pigs across breeds with few examples in a 2026 study. Pig detection falters when breeds change and labeled photos are scarce. Hand-labeling farm images is slow and costly, so few-shot methods must carry more weight.
An improved YOLOv7 detector gains tuned anchors and attention for crowded pens. A CycleGAN paints extra synthetic pigs in the target breed's style. Perceptual loss keeps those fake pigs looking farm-real. Better localization and feature sharpness lift detection in dense scenes. Farms could onboard new breeds without weeks of photo labeling.
Catalog record
| CREATOR | Yizheng Zhuang, Lingyao Xu, Jinyun Jiang, Zhenyang Zhang, Yiting Wang, Pengfei Yu, Yihan Fu, Haoqi Xu, Wei Zhao, Xiaoliang Hou, Jianlan Wang, Yongqi He, Yan Fu, Zhe Zhang, Qishan Wang, Yuchun Pan, Zhen Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |