MixCount provides a scalable synthetic dataset for mixed-object counting that improves state-of-the-art models on real benchmarks, cutting MAE by 20.14% on FSC-147 and 18.3% on PairTally.
Countr: Transformer-based generalised visual counting
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3representative citing papers
RT-Counter introduces VPT and Weaformer modules to achieve competitive accuracy and real-time inference in text-guided open-vocabulary object counting.
ABACUS adapts a 3B unified foundation model using density-aware zooming, boundary-aware GRPO, and cycle-consistent self-critique to achieve SOTA on seven counting and generation benchmarks without task-specific training.
citing papers explorer
-
The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting
MixCount provides a scalable synthetic dataset for mixed-object counting that improves state-of-the-art models on real benchmarks, cutting MAE by 20.14% on FSC-147 and 18.3% on PairTally.
-
RT-Counter: Real-Time Text-Guided Open-Vocabulary Object Counting
RT-Counter introduces VPT and Weaformer modules to achieve competitive accuracy and real-time inference in text-guided open-vocabulary object counting.
-
ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation
ABACUS adapts a 3B unified foundation model using density-aware zooming, boundary-aware GRPO, and cycle-consistent self-critique to achieve SOTA on seven counting and generation benchmarks without task-specific training.