SLP-Net: A Dual-Level Contrastive Learning Framework with Stripe Attention for Elongated Pepper Detection in Complex Field Environments
Jiangquan Zeng, Jiangzhang Zhu, Guoxiong Zhou, Peng Wang · 2026
Read SLP-Net: A Dual-Level Contrastive Learning Framework with Stripe Attention for Elongated Pepper Detection in Complex Field Environments by Jiangquan Zeng, Jiangzhang Zhu, Guoxiong Zhou, Peng 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-13211103.txt.
Description
Jiangquan Zeng, Jiangzhang Zhu, Guoxiong Zhou, and Peng Wang build a vision system to spot long peppers in fields, in a paper dated twenty twenty-six. Peppers vary in look and hide behind leaves, so detectors miss them. Their network, SLP-Net, guards shape cues that clutter tends to wash out.
A stripe-shaped focus and two-level contrast learning steady the detector. On two test sets it beat rival detectors, with the clearest gains on tight overlap scores and small fruit. Disease, warping, and harsh backgrounds filled the harder set. The system held up as targets grew more varied.
Catalog record
| CREATOR | Jiangquan Zeng, Jiangzhang Zhu, Guoxiong Zhou, Peng Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |