# Few-shot Object Counting with Similarity-Aware Feature Enhancement

arXiv: https://arxiv.org/abs/2201.08959 · HTML: https://mlsanity.com/paper/2201.08959/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 55 references that are in the map.
- First posted on arXiv 22 Jan 2022.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Few-shot Object Detection via Feature Reweighting](https://mlsanity.com/paper/1812.01866/) (2018)
- [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://mlsanity.com/paper/1903.02351/) (2019)
- [Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector](https://mlsanity.com/paper/1908.01998/) (2019)
- [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017)
- [Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework](https://mlsanity.com/paper/2107.12746/) (2021)
- [Learning To Count Everything](https://mlsanity.com/paper/2104.08391/) (2021)
- [End-to-end people detection in crowded scenes](https://mlsanity.com/paper/1506.04878/) (2015)
- [Multi-Scale Positive Sample Refinement for Few-Shot Object Detection](https://mlsanity.com/paper/2007.09384/) (2020)
- [Few-Shot Classification with Feature Map Reconstruction Networks](https://mlsanity.com/paper/2012.01506/) (2020)
- [Switching Convolutional Neural Network for Crowd Counting](https://mlsanity.com/paper/1708.00199/) (2017)
- [A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning](https://mlsanity.com/paper/1609.04453/) (2016)
- [Class-Agnostic Counting](https://mlsanity.com/paper/1811.00472/) (2018)
- [Mining Latent Classes for Few-shot Segmentation](https://mlsanity.com/paper/2103.15402/) (2021)
- [Precise Detection in Densely Packed Scenes](https://mlsanity.com/paper/1904.00853/) (2019)
- [Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs](https://mlsanity.com/paper/1708.00953/) (2017)
- [Where are the Blobs: Counting by Localization with Point Supervision](https://mlsanity.com/paper/1807.09856/) (2018)
- [Perspective-Guided Convolution Networks for Crowd Counting](https://mlsanity.com/paper/1909.06966/) (2019)
- [Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting](https://mlsanity.com/paper/2012.04529/) (2020)
- [DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation](https://mlsanity.com/paper/1712.06679/) (2017)

## Built on by (most cited first, 30 of 62)

- [CLIP-Count: Towards Text-Guided Zero-Shot Object Counting](https://mlsanity.com/paper/2305.07304/) (2023)
- [CounTR: Transformer-based Generalised Visual Counting](https://mlsanity.com/paper/2208.13721/) (2022)
- [A Low-Shot Object Counting Network With Iterative Prototype Adaptation](https://mlsanity.com/paper/2211.08217/) (2022)
- [CountGD: Multi-Modal Open-World Counting](https://mlsanity.com/paper/2407.04619/) (2024)
- [Zero-shot Object Counting](https://mlsanity.com/paper/2303.02001/) (2023)
- [DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting](https://mlsanity.com/paper/2404.16622/) (2024)
- [Open-world Text-specified Object Counting](https://mlsanity.com/paper/2306.01851/) (2023)
- [Training-free Object Counting with Prompts](https://mlsanity.com/paper/2307.00038/) (2023)
- [Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting](https://mlsanity.com/paper/2305.04440/) (2023)
- [Counting Guidance for High Fidelity Text-to-Image Synthesis](https://mlsanity.com/paper/2306.17567/) (2023)
- [Zero-shot Object Counting with Good Exemplars](https://mlsanity.com/paper/2407.04948/) (2024)
- [A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation](https://mlsanity.com/paper/2409.18686/) (2024)
- [T-Rex: Counting by Visual Prompting](https://mlsanity.com/paper/2311.13596/) (2023)
- [LVLM-COUNT: Enhancing the Counting Ability of Large Vision-Language Models](https://mlsanity.com/paper/2412.00686/) (2024)
- [T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting](https://mlsanity.com/paper/2502.20625/) (2025)
- [Can SAM Count Anything? An Empirical Study on SAM Counting](https://mlsanity.com/paper/2304.10817/) (2023)
- [OmniCount: Multi-label Object Counting with Semantic-Geometric Priors](https://mlsanity.com/paper/2403.05435/) (2024)
- [CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Reward](https://mlsanity.com/paper/2504.03724/) (2025)
- [SAAN: Similarity-aware attention flow network for change detection with VHR remote sensing images](https://mlsanity.com/paper/2308.14570/) (2023)
- [Mind the Prompt: A Novel Benchmark for Prompt-based Class-Agnostic Counting](https://mlsanity.com/paper/2409.15953/) (2024)
- [Open-World Object Counting in Videos](https://mlsanity.com/paper/2506.15368/) (2025)
- [OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videos](https://mlsanity.com/paper/2407.17085/) (2024)
- [Zero-Shot Object Counting with Language-Vision Models](https://mlsanity.com/paper/2309.13097/) (2023)
- [Interactive Class-Agnostic Object Counting](https://mlsanity.com/paper/2309.05277/) (2023)
- [A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches](https://mlsanity.com/paper/2501.19184/) (2025)
- [Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluation](https://mlsanity.com/paper/2509.13939/) (2025)
- [Semantic Generative Augmentations for Few-Shot Counting](https://mlsanity.com/paper/2311.16122/) (2023)
- [Single Domain Generalization for Few-Shot Counting via Universal Representation Matching](https://mlsanity.com/paper/2505.16778/) (2025)
- [[De|Re]constructing VLMs' Reasoning in Counting](https://mlsanity.com/paper/2510.19555/) (2025)
- [Learning to Count without Annotations](https://mlsanity.com/paper/2307.08727/) (2023)

## Abstract (arXiv)

This work studies the problem of few-shot object counting, which counts the number of exemplar objects (i.e., described by one or several support images) occurring in the query image. The major challenge lies in that the target objects can be densely packed in the query image, making it hard to recognize every single one. To tackle the obstacle, we propose a novel learning block, equipped with a similarity comparison module and a feature enhancement module. Concretely, given a support image and a query image, we first derive a score map by comparing their projected features at every spatial position. The score maps regarding all support images are collected together and normalized across both the exemplar dimension and the spatial dimensions, producing a reliable similarity map. We then enhance the query feature with the support features by employing the developed point-wise similarities as the weighting coefficients. Such a design encourages the model to inspect the query image by focusing more on the regions akin to the support images, leading to much clearer boundaries between different objects. Extensive experiments on various benchmarks and training setups suggest that we surpass the state-of-the-art methods by a sufficiently large margin. For instance, on a recent large-scale FSC-147 dataset, we surpass the state-of-the-art method by improving the mean absolute error from 22.08 to 14.32 (35%uparrow). Code has been released in https://github.com/zhiyuanyou/SAFECount.