ABACUS is a unified vision-language model that handles object counting, crowd counting, referring-expression counting, and count-faithful image generation without any benchmark-specific training required. Our model is built on existing 3B-parameter unified foundation model and is adapted for object localization tasks using three key innovations: density-aware adaptive zooming with objectness maps for spatial grounding; a boundary-aware count policy via GRPO to eliminate crop-boundary errors; and a cycle-consistent GRPO strategy where the understanding branch self-critiques generated outputs, closing the understanding-generation gap without any external annotations.
The paper reviews the evolution of object‑counting techniques from class‑specific density regression to open‑vocabulary, foundation‑model‑backed counters that can handle visual and textual prompts. It highlights that current evaluation relies on a few saturated benchmarks, leading to models exploiting statistical regularities rather than true generalization. The authors propose a five‑axis taxonomy and audit the literature across domains such as microscopy, remote sensing, crowd counting, and agriculture, identifying six structural contradictions and outlining a roadmap for robust, multimodal evaluation protocols.
By Joana Konadu Owusu, Shivanand Venkanna Sheshappanavar
The paper introduces Group-Individual Object Counting (GIC), a new task that requires models to count both individual objects and higher‑level semantic groups within the same image. To support this, the authors present BunchCount, a benchmark of 1,330 images with 89,254 individual and 11,065 group annotations that include explicit containment relations. Experiments show that existing counting models excel at individual counting but struggle with group counting, leading the authors to propose a relational counting framework that leverages group‑individual containment to improve group‑level accuracy while preserving individual performance.
By Rui Wang, Junyi Huang, Jiahui Li, Qiao Yu, Yixue Hao, Long Hu, Baoru Huang
Object-counting methods have rapidly shifted from class-specific density regression to open-vocabulary, foundation-model-backed counters. These methods now enumerate instances from various visual and...
NumBench is a large benchmark of 640,000 text‑to‑image prompts that tests how well models count objects, covering 1,600 categories and counts from 1 to 100. It uses a factorial design to vary composition, spatial guidance, and appearance while balancing counts, and introduces a process model that predicts a near‑quadratic collision deficit at low occupancy. The authors also propose the Confidence‑Weighted Numeric Precision Score for scalable evaluation and find that all tested systems perform poorly above 50 objects, with count range, layout, and composition having the largest effects.
By Sandeep Wadhwa, Mayank Vatsa, Richa Singh, Parrva Chirag Shah, Prakhar Galriya
arXiv:2607. 06420v1 Announce Type: cross Abstract: Visual counting is a fundamental pillar of multimodal intelligence, requiring a seamless integration of fine-grained grounding and spatial reasoning.
By Jinhong Deng, Limeng Qiao, Guanglu Wan
arXiv:2608.20621v1 Announce Type: new
Abstract: Text-guided zero-shot object counters excel at spatial localization but categorize poorly on novel or fine-grained classes: natural language is too coa...
By Adriano D'Alessandro, Ali Mahdavi-Amiri, Ghassan Hamarneh
arXiv:2607. 09544v1 Announce Type: cross Abstract: Despite strong performance on many multimodal tasks, vision-language models (VLMs) still struggle with basic object counting.
By Ahmed Oumar El-Shangiti, Abzal Nurgazy, Hilal AlQuabeh, Nikolai Rozanov, Kentaro Inui
The paper introduces OpenRef, a benchmark for Referring Expression Comprehension (REC) designed for open‑world scenarios. OpenRef expands beyond simple settings by including diverse visual domains, variable target counts (multi‑target and none‑target), and a rich vocabulary with proper nouns, polysemous words, and ordinal terms. It also proposes new evaluation metrics—F1 for grounding accuracy and N3R for negative expression rejection—and presents a training‑free Multi‑task Consistency Checker (MCC) that improves model performance with a single click.
By Zongjian Wu, Lei Zhang
arXiv:2609.17613v1 Announce Type: new
Abstract: Zero-shot object counting aims to estimate the number of objects specified by a text query without category-specific training. Recent approaches primar...
By Xuan Cuong Ngo
arXiv:2607. 07322v1 Announce Type: cross Abstract: Automated crowd counting in Hajj video is difficult not because current models lack capacity, but because the footage violates the assumptions those models were built on: cameras observe the crowd from steep, near-vertical angles, individuals occlude one another extensively, and a single frame can contain well over a thousand people.
By Reem AlYabis, Fares AlTuwaim, AlJawharh AlOtaibi, Mohamed Eltahir
Cross-image comparative reasoning remains challenging for vision-language models (VLMs), especially when correct prediction requires fine-grained attribute grounding and globally consistent reasoning. We present CoRe, a unified framework for this problem.