cs.CVNov 10, 2026

What Factors Matter for Collection-Level Counting with Human-AI Collaboration?

Authors: Seoyun Jeong, Logan Lawrence, Owen L. Martin, Benjamin Koger, Daniel Sheldon, Subhransu Maji

Organizations: University of Massachusetts Amherst · University of Wyoming

Abstract

Many scientific and policy decisions require estimating the total number of target objects across a large image collection. Exhaustive human labeling is often infeasible, while raw model predictions can be biased, especially under domain shift. Recent human--AI estimation methods combine imperfect model predictions with limited human verification to obtain reliable collection-level estimates. However, existing work provides little guidance on how practitioners should choose among models, estimators, and adaptation strategies for a new deployment. We study these choices within a common human-in-the-loop counting framework on CLC-12, a benchmark of 12 tasks spanning biomedical microscopy, ground-level and aerial wildlife surveys, and overhead imagery of urban structures. Our results show that modern multimodal models provide a strong, training-free starting point for many tasks, while fine-tuned detectors become more advantageous at larger labeling budgets and across repeated deployments. Estimation efficiency improves further when model predictions are used to prioritize which units humans label, rather than sampling uniformly. We also find that each model's ranking quality can be estimated with a small pilot set, yielding practical guidance for selecting strategies on new counting tasks. In a field deployment on aerial pronghorn surveys, a task-specific adaptation of these methods meets the survey's ±\pm 5% tolerance after reviewing a median of only 3.2% of collected images.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Scalable Model-Assisted Multi-Target Estimation in Large Image Collections

    Jul 20, 2026Max Hamilton, Jinlin Lai, Daniel Sheldon +1Importance Sampling

  2. Count Anything at Any Granularity

    May 11, 2026Chang Liu, Haoning Wu, Weidi XieObject CountingMultimodal Large Language Models

  3. Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challenges

    Aug 24, 2026Joana Konadu Owusu, Shivanand Venkanna SheshappanavarObject CountingVisual Counting