# Mutually-Aware Feature Learning for Few-Shot Object Counting

arXiv: https://arxiv.org/abs/2408.09734 · HTML: https://mlsanity.com/paper/2408.09734/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 19 Aug 2024.

## Builds on (most cited first, 22 of 22)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017)
- [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)
- [Class-Agnostic Counting](https://mlsanity.com/paper/1811.00472/) (2018)
- [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)
- [A Low-Shot Object Counting Network With Iterative Prototype Adaptation](https://mlsanity.com/paper/2211.08217/) (2022)
- [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)
- [Few-shot Object Counting and Detection](https://mlsanity.com/paper/2207.10988/) (2022)
- [Perspective-Guided Convolution Networks for Crowd Counting](https://mlsanity.com/paper/1909.06966/) (2019)
- [TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2112.01515/) (2021)
- [Training-free Object Counting with Prompts](https://mlsanity.com/paper/2307.00038/) (2023)
- [STNet: Scale Tree Network with Multi-level Auxiliator for Crowd Counting](https://mlsanity.com/paper/2012.10189/) (2020)
- [Interlayer and Intralayer Scale Aggregation for Scale-invariant Crowd Counting](https://mlsanity.com/paper/2005.11943/) (2020)

## Built on by (most cited first, 2 of 2)

- [OCCAM: Class-Agnostic, Training-Free, Prior-Free and Multi-Class Object Counting](https://mlsanity.com/paper/2601.13871/) (2026)
- [Getting to the Point: Pointing Improves LVLMs at Counting](https://mlsanity.com/paper/2603.21746/) (2026)

## Abstract (arXiv)

Few-shot object counting has garnered significant attention for its practicality as it aims to count target objects in a query image based on given exemplars without additional training. However, the prevailing extract-and-match approach has a shortcoming: query and exemplar features lack interaction during feature extraction since they are extracted independently and later correlated based on similarity. This can lead to insufficient target awareness and confusion in identifying the actual target when multiple class objects coexist. To address this, we propose a novel framework, Mutually-Aware FEAture learning (MAFEA), which encodes query and exemplar features with mutual awareness from the outset. By encouraging interaction throughout the pipeline, we obtain target-aware features robust to a multi-category scenario. Furthermore, we introduce background token to effectively associate the query's target region with exemplars and decouple its background region. Our extensive experiments demonstrate that our model achieves state-of-the-art performance on FSCD-LVIS and FSC-147 benchmarks with remarkably reduced target confusion.