Count Anything at Any Granularity

• URL: http://arxiv.org/abs/2605.10887v1
• Date: Mon, 11 May 2026 17:32:37 GMT
• Title: Count Anything at Any Granularity
• Abstract summary: KubriCount is the largest and most comprehensively annotated counting dataset to date.<n>We train a multi-grained counting model that jointly leverages text and visual exemplars as complementary target specifications.<n>HieraCount substantially improves multi-grained counting accuracy and generalizes robustly to challenging real-world scenarios.
• Score: 55.70950689938894
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Open-world object counting remains brittle: despite rapid advances in vision-language models (VLMs), reliably counting the objects a user intends is far from solved. We argue that a central reason is that counting granularity is left implicit; users may refer to a specific identity, an attribute, an instance type, a category, or an abstract concept, yet most methods treat "what to count" as a single, category-level matching problem. In this work, we redefine open-world counting as multi-grained counting, where visual exemplars specify target appearance and fine-grained text, with optional negative prompts, specifies the intended semantic granularity across five explicit levels. Making granularity explicit, however, exposes a critical data bottleneck: existing counting datasets lack the multi-category scenes, controlled distractors, and instance-level annotations needed to verify fine-grained prompt semantics. To address this, we propose the first fully automatic data-scaling pipeline that integrates controllable 3D synthesis with consistent image editing and VLM-based filtering, and use it to construct KubriCount, the largest and most comprehensively annotated counting dataset to date, supporting both training and multi-grained evaluation. Systematic benchmarking reveals that both multimodal large language models and specialist counting models exhibit severe prompt-following failures under fine-grained distinctions. Motivated by these findings, we train HieraCount, a multi-grained counting model that jointly leverages text and visual exemplars as complementary target specifications. HieraCount substantially improves multi-grained counting accuracy and generalizes robustly to challenging real-world scenarios. The project page is available here: https://verg-avesta.github.io/KubriCount/.

Related papers

• HoloCount: A Holistic Visual Counting Benchmark for MLLMs [17.08907754405721]
  HoloCount is a diagnostically rich benchmark structured around a three-level hierarchical taxonomy.<n>We evaluate over 20 state-of-the-art Multimodal Large Language Models (MLLMs)<n>Our findings offer a roadmap for developing more grounded and reliable multimodal systems.
  arXiv  Detail & Related papers  (2026-07-07T15:48:57Z)
• Count Anything [41.17667085289094]
  We study text-guided object counting across domains, where a model takes an image and a natural-language query as input and returns an instance-grounded set of target points.<n>Based on CLOC, we propose Count Anything, a generalist model for text-guided object counting.
  arXiv  Detail & Related papers  (2026-05-29T05:08:31Z)
• Bootstrapping MLLM for Weakly-Supervised Class-Agnostic Object Counting [59.37613121962146]
  We propose WS-COC, the first MLLM-driven weakly-supervised framework for class-agnostic object counting.<n> WS-COC matches or even surpasses many state-of-art fully-supervised methods while significantly reducing annotation costs.
  arXiv  Detail & Related papers  (2026-02-13T09:58:35Z)
• CountGD++: Generalized Prompting for Open-World Counting [54.61576076312857]
  We introduce novel capabilities that expand how the target object can be specified.<n> Specifically, we extend the prompt to enable what not to count to be described with text and/or visual examples.<n>We also introduce the concept of pseudo-exemplars' that automate the annotation of visual examples at inference.
  arXiv  Detail & Related papers  (2025-12-29T10:23:22Z)
• Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluation [21.90583276089241]
  PairTally is a benchmark dataset designed to evaluate fine-grained visual counting.<n>Each of the 681 high-resolution images in PairTally contains two object categories.<n>We show that despite recent advances, current models struggle to reliably count what users intend.
  arXiv  Detail & Related papers  (2025-09-17T13:06:58Z)
• CountGD: Multi-Modal Open-World Counting [54.88804890463491]
  This paper aims to improve the generality and accuracy of open-vocabulary object counting in images.<n>We introduce the first open-world counting model, CountGD, where the prompt can be specified by a text description or visual exemplars or both.
  arXiv  Detail & Related papers  (2024-07-05T16:20:48Z)
• OmniCount: Multi-label Object Counting with Semantic-Geometric Priors [52.28092505350977]
  This paper introduces a more practical approach enabling simultaneous counting of multiple object categories using an open-vocabulary framework.<n>Our solution, OmniCount, stands out by using semantic and geometric insights (priors) from pre-trained models to count multiple categories of objects as specified by users.<n>Our comprehensive evaluation in OmniCount-191, alongside other leading benchmarks, demonstrates OmniCount's exceptional performance, significantly outpacing existing solutions.
  arXiv  Detail & Related papers  (2024-03-08T16:38:11Z)
• M$^3$Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition [80.21796574234287]
  M$3$Net is a matching-based framework for few-shot fine-grained (FS-FG) action recognition. It incorporates textitmulti-view encoding, textitmulti-view matching, and textitmulti-view fusion to facilitate embedding encoding, similarity matching, and decision making. Explainable visualizations and experimental results demonstrate the superiority of M$3$Net in capturing fine-grained action details.
  arXiv  Detail & Related papers  (2023-08-06T09:15:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.