Papers › OmniCount: Multi-label Object Counting with Semantic-Geometric Priors

OmniCount: Multi-label Object Counting with Semantic-Geometric Priors

8 Mar 2024arXiv:2403.05435archive 2025-07-28

Anindya Mondal, Sauradip Nag, Xiatian Zhu, Anjan Dutta

Object counting is pivotal for understanding the composition of scenes. Previously, this task was dominated by class-specific methods, which have gradually evolved into more adaptable class-agnostic strategies. However, these strategies come with their own set of limitations, such as the need for manual exemplar input and multiple passes for multiple categories, resulting in significant inefficiencies. This paper introduces a more practical approach enabling simultaneous counting of multiple object categories using an open-vocabulary framework. 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, all without additional training. OmniCount distinguishes itself by generating precise object masks and leveraging varied interactive prompts via the Segment Anything Model for efficient counting. To evaluate OmniCount, we created the OmniCount-191 benchmark, a first-of-its-kind dataset with multi-label object counts, including points, bounding boxes, and VQA annotations. Our comprehensive evaluation in OmniCount-191, alongside other leading benchmarks, demonstrates OmniCount's exceptional performance, significantly outpacing existing solutions. The project webpage is available at https://mondalanindya.github.io/OmniCount.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ObjectObject CountingOpen-vocabulary object countingTraining-free Object CountingVisual Question Answering (VQA)

Datasets

Introduced by this paper, per the archive.

Omnicount-191

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Counting FSC147 Omnicount (Open vocabulary, multi-label, without training) MAE(test) 18.63 #18 of 19 Archive leaderboard report
Object Counting FSC147 Omnicount (Open vocabulary, multi-label, without training) RMSE(test) 112 #18 of 19 Archive leaderboard report
Object Counting Omnicount-191 Omnicount mRMSE 0.0023 #1 of 1 Archive leaderboard report
Object Counting Pascal VOC 2007 count-test Omnicount mRMSE 0.0023 #8 of 8 Archive leaderboard report
Object Counting Pascal VOC 2007 count-test Omnicount mRMSE-nz 0.009 #8 of 8 Archive leaderboard report
Training-free Object Counting FSC147 Omnicount MAE 18.63 #1 of 2 Archive leaderboard report
Training-free Object Counting Omnicount-191 Omnicount mRMSE 0.7 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections