Decoupling What to Count and Where to See for Referring Expression Counting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zou, Yuda, Zhang, Zijian, Xu, Yongchao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908617182019584
author Zou, Yuda
Zhang, Zijian
Xu, Yongchao
author_facet Zou, Yuda
Zhang, Zijian
Xu, Yongchao
contents Referring Expression Counting (REC) extends class-level object counting to the fine-grained subclass-level, aiming to enumerate objects matching a textual expression that specifies both the class and distinguishing attribute. A fundamental challenge, however, has been overlooked: annotation points are typically placed on class-representative locations (e.g., heads), forcing models to focus on class-level features while neglecting attribute information from other visual regions (e.g., legs for "walking"). To address this, we propose W2-Net, a novel framework that explicitly decouples the problem into "what to count" and "where to see" via a dual-query mechanism. Specifically, alongside the standard what-to-count (w2c) queries that localize the object, we introduce dedicated where-to-see (w2s) queries. The w2s queries are guided to seek and extract features from attribute-specific visual regions, enabling precise subclass discrimination. Furthermore, we introduce Subclass Separable Matching (SSM), a novel matching strategy that incorporates a repulsive force to enhance inter-subclass separability during label assignment. W2-Net significantly outperforms the state-of-the-art on the REC-8K dataset, reducing counting error by 22.5% (validation) and 18.0% (test), and improving localization F1 by 7% and 8%, respectively. Code will be available.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24374
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Decoupling What to Count and Where to See for Referring Expression Counting
Zou, Yuda
Zhang, Zijian
Xu, Yongchao
Computer Vision and Pattern Recognition
Referring Expression Counting (REC) extends class-level object counting to the fine-grained subclass-level, aiming to enumerate objects matching a textual expression that specifies both the class and distinguishing attribute. A fundamental challenge, however, has been overlooked: annotation points are typically placed on class-representative locations (e.g., heads), forcing models to focus on class-level features while neglecting attribute information from other visual regions (e.g., legs for "walking"). To address this, we propose W2-Net, a novel framework that explicitly decouples the problem into "what to count" and "where to see" via a dual-query mechanism. Specifically, alongside the standard what-to-count (w2c) queries that localize the object, we introduce dedicated where-to-see (w2s) queries. The w2s queries are guided to seek and extract features from attribute-specific visual regions, enabling precise subclass discrimination. Furthermore, we introduce Subclass Separable Matching (SSM), a novel matching strategy that incorporates a repulsive force to enhance inter-subclass separability during label assignment. W2-Net significantly outperforms the state-of-the-art on the REC-8K dataset, reducing counting error by 22.5% (validation) and 18.0% (test), and improving localization F1 by 7% and 8%, respectively. Code will be available.
title Decoupling What to Count and Where to See for Referring Expression Counting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.24374