# CODA: Counting Objects via Scale-aware Adversarial Density Adaption

arXiv: https://arxiv.org/abs/1903.10442 · HTML: https://mlsanity.com/paper/1903.10442/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2019.

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

- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting](https://mlsanity.com/paper/2108.08023/) (2021)
- [DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting](https://mlsanity.com/paper/2308.05311/) (2023)
- [Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network](https://mlsanity.com/paper/2107.12858/) (2021)
- [Bi-level Alignment for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2205.05844/) (2022)
- [Cross-Region Building Counting in Satellite Imagery using Counting Consistency](https://mlsanity.com/paper/2110.13558/) (2021)
- [AdaTreeFormer: Few Shot Domain Adaptation for Tree Counting from a Single High-Resolution Image](https://mlsanity.com/paper/2402.02956/) (2024)
- [Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting](https://mlsanity.com/paper/2402.03758/) (2024)
- [GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting](https://mlsanity.com/paper/2409.12249/) (2024)
- [Towards Conditional Feature Alignment for Cross-Domain Counting](https://mlsanity.com/paper/2506.17137/) (2025)

## Abstract (arXiv)

Recent advances in crowd counting have achieved promising results with increasingly complex convolutional neural network designs. However, due to the unpredictable domain shift, generalizing trained model to unseen scenarios is often suboptimal. Inspired by the observation that density maps of different scenarios share similar local structures, we propose a novel adversarial learning approach in this paper, i.e., CODA (Counting Objects via scale-aware adversarial Density Adaption). To deal with different object scales and density distributions, we perform adversarial training with pyramid patches of multi-scales from both source- and target-domain. Along with a ranking constraint across levels of the pyramid input, consistent object counts can be produced for different scales. Extensive experiments demonstrate that our network produces much better results on unseen datasets compared with existing counting adaption models. Notably, the performance of our CODA is comparable with the state-of-the-art fully-supervised models that are trained on the target dataset. Further analysis indicates that our density adaption framework can effortlessly extend to scenarios with different objects. The code is available at https://github.com/Willy0919/CODA.