# M2Former: Multi-Scale Patch Selection for Fine-Grained Visual Recognition

arXiv: https://arxiv.org/abs/2308.02161 · HTML: https://mlsanity.com/paper/2308.02161/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 66 of its 95 references that are in the map.
- First posted on arXiv 4 Aug 2023.

## Builds on (most cited first, 30 of 66)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)

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

- [Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition](https://mlsanity.com/paper/2504.09215/) (2025)
- [CPR: Chained Perceptual Refinement for Coarse-to-Fine Medical Image Classification](https://mlsanity.com/paper/2607.02591/) (2026)

## Abstract (arXiv)

Recently, vision Transformers (ViTs) have been actively applied to fine-grained visual recognition (FGVR). ViT can effectively model the interdependencies between patch-divided object regions through an inherent self-attention mechanism. In addition, patch selection is used with ViT to remove redundant patch information and highlight the most discriminative object patches. However, existing ViT-based FGVR models are limited to single-scale processing, and their fixed receptive fields hinder representational richness and exacerbate vulnerability to scale variability. Therefore, we propose multi-scale patch selection (MSPS) to improve the multi-scale capabilities of existing ViT-based models. Specifically, MSPS selects salient patches of different scales at different stages of a multi-scale vision Transformer (MS-ViT). In addition, we introduce class token transfer (CTT) and multi-scale cross-attention (MSCA) to model cross-scale interactions between selected multi-scale patches and fully reflect them in model decisions. Compared to previous single-scale patch selection (SSPS), our proposed MSPS encourages richer object representations based on feature hierarchy and consistently improves performance from small-sized to large-sized objects. As a result, we propose M2Former, which outperforms CNN-/ViT-based models on several widely used FGVR benchmarks.