Boosting Quantitive and Spatial Awareness for Zero-Shot Object Counting

TL;DR

This paper introduces QICA, a framework enhancing zero-shot object counting by integrating quantity perception and spatial aggregation, improving fine-grained reasoning and generalization across unseen categories and domains.

Contribution

QICA combines quantity perception with spatial aggregation, using a novel prompting strategy and cost aggregation decoder to improve zero-shot counting accuracy and robustness.

Findings

Achieves competitive results on FSC-147 dataset.

Demonstrates superior zero-shot generalization on CARPK and ShanghaiTech-A.

Effectively maintains numerical consistency across the pipeline.

Abstract

Zero-shot object counting (ZSOC) aims to enumerate objects of arbitrary categories specified by text descriptions without requiring visual exemplars. However, existing methods often treat counting as a coarse retrieval task, suffering from a lack of fine-grained quantity awareness. Furthermore, they frequently exhibit spatial insensitivity and degraded generalization due to feature space distortion during model adaptation.To address these challenges, we present \textbf{QICA}, a novel framework that synergizes \underline{q}uantity percept\underline{i}on with robust spatial \underline{c}ast \underline{a}ggregation. Specifically, we introduce a Synergistic Prompting Strategy (\textbf{SPS}) that adapts vision and language encoders through numerically conditioned prompts, bridging the gap between semantic recognition and quantitative reasoning. To mitigate feature distortion, we propose a Cost Aggregation Decoder (\textbf{CAD}) that operates directly on vision-text similarity maps. By refining these maps through spatial aggregation, CAD prevents overfitting while preserving zero-shot transferability. Additionally, a multi-level quantity alignment loss ($\mathcal{L}_{MQA}$) is employed to enforce numerical consistency across the entire pipeline. Extensive experiments on FSC-147 demonstrate competitive performance, while zero-shot evaluation on CARPK and ShanghaiTech-A validates superior generalization to unseen domains.