# Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting

arXiv: https://arxiv.org/abs/2012.08149 · HTML: https://mlsanity.com/paper/2012.08149/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2020.

## Built on by (most cited first, 10 of 10)

- [Few-shot Object Counting with Similarity-Aware Feature Enhancement](https://mlsanity.com/paper/2201.08959/) (2022)
- [TransCrowd: weakly-supervised crowd counting with transformers](https://mlsanity.com/paper/2104.09116/) (2021)
- [CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model](https://mlsanity.com/paper/2304.04231/) (2023)
- [Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision](https://mlsanity.com/paper/2205.10203/) (2022)
- [Multi-Scale Adaptive Network for Single Image Denoising](https://mlsanity.com/paper/2203.04313/) (2022)
- [NWPU-MOC: A Benchmark for Fine-grained Multi-category Object Counting in Aerial Images](https://mlsanity.com/paper/2401.10530/) (2024)
- [Mamba-MOC: A Multicategory Remote Object Counting via State Space Model](https://mlsanity.com/paper/2501.06697/) (2025)
- [Super-Resolution Information Enhancement For Crowd Counting](https://mlsanity.com/paper/2303.06925/) (2023)
- [Count, Decode and Fetch: A New Approach to Handwritten Chinese Character Error Correction](https://mlsanity.com/paper/2307.16253/) (2023)
- [Getting the Numbers Rightunicodex2014Modelling Multi-Class Object Counting in Dense and Varied Scenes](https://mlsanity.com/paper/2510.02213/) (2025)

## Abstract (arXiv)

Object counting aims to estimate the number of objects in images. The leading counting approaches focus on the single category counting task and achieve impressive performance. Note that there are multiple categories of objects in real scenes. Multi-class object counting expands the scope of application of object counting task. The multi-target detection task can achieve multi-class object counting in some scenarios. However, it requires the dataset annotated with bounding boxes. Compared with the point annotations in mainstream object counting issues, the coordinate box-level annotations are more difficult to obtain. In this paper, we propose a simple yet efficient counting network based on point-level annotations. Specifically, we first change the traditional output channel from one to the number of categories to achieve multiclass counting. Since all categories of objects use the same feature extractor in our proposed framework, their features will interfere mutually in the shared feature space. We further design a multi-mask structure to suppress harmful interaction among objects. Extensive experiments on the challenging benchmarks illustrate that the proposed method achieves state-of-the-art counting performance.