Benchmark RadarAI BENCHMARK PROFILE
NEEDL-Bench
NEEDL-Bench is a microscopy detection benchmark for Swiss Needle Cast and stomata detection, with 3250 annotated images from 1082 Douglas-fir needles, annotated for keypoint and bounding-box detectors, and two evaluation splits.
- Released
- 2026-07-13
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
There is no existing dataset for automatic detection of these structures, despite the importance of Douglas-fir. This benchmark provides a standardized evaluation for keypoint and object detection methods, highlighting challenges like small objects and occlusion.
Motivation
We present NEEDL-Bench, a microscopy detection benchmark for Swiss Needle Cast (SNC), a fungal disease of Douglas-fir trees.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.