AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

YOLO-Count: Differentiable Object Counting for Text-to-Image Generation

Guanning Zeng, Xiang Zhang, Zirui Wang, Haiyang Xu, Zeyuan Chen, Bingnan Li, Zhuowen Tu

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 8 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 LVIS strong-supervision pretraining (ablation)YOLO-Count · FSC147 testMAE: 18.42 -> 14.80Improved
add FSC147 weak-supervision finetuning (ablation)YOLO-Count · FSC147 testMAE: 43.91 -> 14.80Improved
use cardinality map regression instead of density map (ablation)YOLO-Count · FSC147 testMAE: 16.71 -> 14.80Improved
use cardinality map regression instead of density map (ablation)YOLO-Count · FSC147 valRMSE: 76.42 -> 58.36Improved
add classification branch for representation alignment (ablation)YOLO-Count · FSC147 testMAE: 17.01 -> 14.80Improved
add separate VLPAN feature output for each head (ablation)YOLO-Count · FSC147 testMAE: 16.54 -> 14.80Improved
use cardinality map instead of density map training (ablation)regression counting models · FSC147 object-size downscalingcount biasImproved
filter cardinality output with classification probability threshold 0.5 instead of 0.0 (ablation)YOLO-Count · FSC147MAEHurt
filter cardinality output with classification probability threshold 0.5 instead of 0.0YOLO-Count · LVISMAEImproved
use YOLO-Count guidance instead of CountGD surrogate loss or CLIP-CountSDXL-Turbo token optimization · LargeGen and LargeGen-Newcount accuracyImproved
use YOLO-Count instead of CountGDcounting model · LVIS valMAE: 4.84 -> 1.65Improved

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