# CountingDINO: A Training-free Pipeline for Class-Agnostic Counting using Unsupervised Backbones

arXiv: https://arxiv.org/abs/2504.16570 · HTML: https://mlsanity.com/paper/2504.16570/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 23 Apr 2025.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [Learning To Count Everything](https://mlsanity.com/paper/2104.08391/) (2021)
- [Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning](https://mlsanity.com/paper/2212.04994/) (2022)
- [Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting](https://mlsanity.com/paper/2203.08354/) (2022)
- [CounTR: Transformer-based Generalised Visual Counting](https://mlsanity.com/paper/2208.13721/) (2022)
- [An End-to-End Transformer Model for Crowd Localization](https://mlsanity.com/paper/2202.13065/) (2022)
- [A Low-Shot Object Counting Network With Iterative Prototype Adaptation](https://mlsanity.com/paper/2211.08217/) (2022)
- [DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting](https://mlsanity.com/paper/2404.16622/) (2024)
- [Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2411.19331/) (2024)
- [Point, Segment and Count: A Generalized Framework for Object Counting](https://mlsanity.com/paper/2311.12386/) (2023)
- [Counting Everyday Objects in Everyday Scenes](https://mlsanity.com/paper/1604.03505/) (2016)
- [Training-free Object Counting with Prompts](https://mlsanity.com/paper/2307.00038/) (2023)
- [FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras](https://mlsanity.com/paper/1707.09476/) (2017)
- [Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting](https://mlsanity.com/paper/2305.04440/) (2023)
- [OmniCount: Multi-label Object Counting with Semantic-Geometric Priors](https://mlsanity.com/paper/2403.05435/) (2024)
- [Mind the Prompt: A Novel Benchmark for Prompt-based Class-Agnostic Counting](https://mlsanity.com/paper/2409.15953/) (2024)
- [A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches](https://mlsanity.com/paper/2501.19184/) (2025)
- [Learning to Count without Annotations](https://mlsanity.com/paper/2307.08727/) (2023)

## Built on by (most cited first, 6 of 6)

- [OCCAM: Class-Agnostic, Training-Free, Prior-Free and Multi-Class Object Counting](https://mlsanity.com/paper/2601.13871/) (2026)
- [AdaCount: Training-Free Similarity-Guided Spatial and Feature Adaptation for Zero-Shot Object Counting](https://mlsanity.com/paper/2607.02139/) (2026)
- [Spatially-Aware Class-Agnostic Object Counting](https://mlsanity.com/paper/2607.16826/) (2026)
- [CountZES: Counting via Zero-Shot Exemplar Selection](https://mlsanity.com/paper/2512.16415/) (2025)
- [Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challenges](https://mlsanity.com/paper/2608.23845/) (2026)
- [EviRover: Reinforcing Agentic Perception Beyond a Glance](https://mlsanity.com/paper/2609.40230/) (2026)

## Abstract (arXiv)

Class-agnostic counting (CAC) aims to estimate the number of objects in images without being restricted to predefined categories. However, while current exemplar-based CAC methods offer flexibility at inference time, they still rely heavily on labeled data for training, which limits scalability and generalization to many downstream use cases. In this paper, we introduce CountingDINO, the first training-free exemplar-based CAC framework that exploits a fully unsupervised feature extractor. Specifically, our approach employs self-supervised vision-only backbones to extract object-aware features, and it eliminates the need for annotated data throughout the entire proposed pipeline. At inference time, we extract latent object prototypes via ROI-Align from DINO features and use them as convolutional kernels to generate similarity maps. These are then transformed into density maps through a simple yet effective normalization scheme. We evaluate our approach on the FSC-147 benchmark, where we consistently outperform a baseline based on an SOTA unsupervised object detector under the same label- and training-free setting. Additionally, we achieve competitive results -- and in some cases surpass -- training-free methods that rely on supervised backbones, non-training-free unsupervised methods, as well as several fully supervised SOTA approaches. This demonstrates that label- and training-free CAC can be both scalable and effective. Code: https://lorebianchi98.github.io/CountingDINO/.