LCWG-DETR: a wavelet-enhanced detection transformer for citrus disease detection improving visual perception in harvesting
Dalin Zhang, Baijing Wu, Ke Gao, Guanghui Yan · 2026
Read LCWG-DETR: a wavelet-enhanced detection transformer for citrus disease detection improving visual perception in harvesting by Dalin Zhang, Baijing Wu, Ke Gao, Guanghui Yan (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-13597759.txt.
Description
Dalin Zhang, Baijing Wu, Ke Gao, and Guanghui Yan present a 2026 method for spotting citrus diseases in orchard photos. Harvest robots need sharp vision to find sick fruit and leaves. Small spots, hidden leaves, and look-alike diseases make that hard, and standard networks lose the fine details of tiny lesions as they process an image.
Their system adds three fixes. A feature extractor tuned to texture and frequency keeps small-spot detail alive. A fusion module blends image scales with shifting weights so detail survives resizing. A wavelet-based attention part steers focus to lesion edges, and a new loss treats boxes as soft blobs to steady training. On two data sets the method beat the base model on accuracy while using slightly fewer parameters.
Catalog record
| CREATOR | Dalin Zhang, Baijing Wu, Ke Gao, Guanghui Yan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 89 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |