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

8 Mar 2024  ·  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 new, 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 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 point 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 and heralding a new era in object counting technology.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Training-free Object Counting FSC147 Omnicount MAE 18.63 # 1
Object Counting FSC147 Omnicount (Open vocabulary, multi-label, without training) MAE(test) 18.63 # 13
RMSE(test) 112 # 13
Object Counting Omnicount-191 Omnicount mRMSE 0.0023 # 1
Training-free Object Counting Omnicount-191 Omnicount mRMSE 0.7 # 1
Object Counting Pascal VOC 2007 count-test Omnicount mRMSE 0.0023 # 1
mRMSE-nz 0.009 # 1

Methods


No methods listed for this paper. Add relevant methods here