AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Plant Taxonomy Meets Plant Counting: A Fine-Grained, Taxonomic Dataset for Counting Hundreds of Plant Species

Jinyu Xu, Tianqi Hu, Xiaonan Hu, Letian Zhou, Songliang Cao, Meng Zhang, Hao Lu

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add species name text prompt (ablation)CountGD · TPC-268 testMAE: 19.52 -> 17.53Improved
add full taxonomy text prompt (ablation)CountGD · TPC-268 testMAE: 19.52 -> 16.90Improved
add full taxonomy text prompt (ablation)CountGD · TPC-268 testR2: 0.61 -> 0.71Improved
train on FSC-147 and test on TPC-268 instead of train on TPC-268LOCA · TPC-268 testMAE: 17.51 -> 24.70Hurt
train on TPC-268 and test on FSC-147 instead of train on FSC-147LOCA · FSC-147 testMAE: 10.72 -> 15.16Hurt
train on FSC-147 and test on TPC-268CountTR · TPC-268 testMAE: 25.19 -> 38.62Hurt
train on FSC-147 and test on TPC-268CACViT · TPC-268 testMAE: 22.04 -> 26.73Hurt
use 3 exemplars instead of 1 exemplarLOCA · TPC-268 testMAE: 21.47 -> 17.51Improved
use 3 exemplars instead of 1 exemplarTasselNetV4 · TPC-268 testMAE: 22.20 -> 22.95No clear effect
replace ResNet-50 backbone with BioCLIP2 (ablation)LOCA · TPC-268 testMAE: 17.51 -> 34.75Hurt
use global-attention models (CACViT, TasselNetV4) instead of LOCA on test splitCAC models · TPC-268 testMAE: 17.51 -> 22.04Hurt
use detection-based CountGD instead of regression-based LOCACAC models · TPC-268 testMAE: 17.51 -> 19.52Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy