# A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition

arXiv: https://arxiv.org/abs/2110.01240 · HTML: https://mlsanity.com/paper/2110.01240/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 4 Oct 2021.

## Builds on (most cited first, 21 of 21)

- [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)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [TransFG: A Transformer Architecture for Fine-grained Recognition](https://mlsanity.com/paper/2103.07976/) (2021)
- [Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition](https://mlsanity.com/paper/1903.06150/) (2019)
- [Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches](https://mlsanity.com/paper/2003.03836/) (2020)
- [Learning Attentive Pairwise Interaction for Fine-Grained Classification](https://mlsanity.com/paper/2002.10191/) (2020)
- [Interpretable and Accurate Fine-grained Recognition via Region Grouping](https://mlsanity.com/paper/2005.10411/) (2020)
- [The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification](https://mlsanity.com/paper/1411.6447/) (2014)
- [Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up](https://mlsanity.com/paper/1903.02827/) (2019)
- [Maximum-Entropy Fine-Grained Classification](https://mlsanity.com/paper/1809.05934/) (2018)
- [Part-Stacked CNN for Fine-Grained Visual Categorization](https://mlsanity.com/paper/1512.08086/) (2015)
- [Cross-X Learning for Fine-Grained Visual Categorization](https://mlsanity.com/paper/1909.04412/) (2019)
- [Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks](https://mlsanity.com/paper/1809.03355/) (2018)
- [Learning Deep Bilinear Transformation for Fine-grained Image Representation](https://mlsanity.com/paper/1911.03621/) (2019)
- [Bird Species Categorization Using Pose Normalized Deep Convolutional Nets](https://mlsanity.com/paper/1406.2952/) (2014)
- [Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval](https://mlsanity.com/paper/1604.04994/) (2016)
- [RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition](https://mlsanity.com/paper/2107.08192/) (2021)
- [Learning Semantically Enhanced Feature for Fine-Grained Image Classification](https://mlsanity.com/paper/2006.13457/) (2020)
- [Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition](https://mlsanity.com/paper/1605.06878/) (2016)

## Built on by (most cited first, 16 of 16)

- [Fine-grained Visual Classification with High-temperature Refinement and Background Suppression](https://mlsanity.com/paper/2303.06442/) (2023)
- [A Novel Plug-in Module for Fine-Grained Visual Classification](https://mlsanity.com/paper/2202.03822/) (2022)
- [On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition](https://mlsanity.com/paper/2205.13282/) (2022)
- [R2-Trans:Fine-Grained Visual Categorization with Redundancy Reduction](https://mlsanity.com/paper/2204.10095/) (2022)
- [Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition](https://mlsanity.com/paper/2305.07180/) (2023)
- [Global-Local Similarity for Efficient Fine-Grained Image Recognition with Vision Transformers](https://mlsanity.com/paper/2407.12891/) (2024)
- [Salient Mask-Guided Vision Transformer for Fine-Grained Classification](https://mlsanity.com/paper/2305.07102/) (2023)
- [Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images](https://mlsanity.com/paper/2212.00330/) (2022)
- [Conviformers: Convolutionally guided Vision Transformer](https://mlsanity.com/paper/2208.08900/) (2022)
- [ViTree: Single-path Neural Tree for Step-wise Interpretable Fine-grained Visual Categorization](https://mlsanity.com/paper/2401.17050/) (2024)
- [LoDisc: Learning Global-Local Discriminative Features for Self-Supervised Fine-Grained Visual Recognition](https://mlsanity.com/paper/2403.04066/) (2024)
- [Semantic Feature Integration network for Fine-grained Visual Classification](https://mlsanity.com/paper/2302.10275/) (2023)
- [Improving Deep Representation Learning via Auxiliary Learnable Target Coding](https://mlsanity.com/paper/2305.18680/) (2023)
- [Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Work](https://mlsanity.com/paper/2306.01929/) (2023)
- [Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition](https://mlsanity.com/paper/2504.09215/) (2025)
- [ReCalMatch:Reliability-Calibrated Semantic Guidance for Semi-Supervised Fine-Grained Recognition](https://mlsanity.com/paper/2609.29678/) (2026)

## Abstract (arXiv)

Learning subtle representation about object parts plays a vital role in fine-grained visual recognition (FGVR) field. The vision transformer (ViT) achieves promising results on computer vision due to its attention mechanism. Nonetheless, with the fixed size of patches in ViT, the class token in deep layer focuses on the global receptive field and cannot generate multi-granularity features for FGVR. To capture region attention without box annotations and compensate for ViT shortcomings in FGVR, we propose a novel method named Adaptive attention multi-scale Fusion Transformer (AFTrans). The Selective Attention Collection Module (SACM) in our approach leverages attention weights in ViT and filters them adaptively to correspond with the relative importance of input patches. The multiple scales (global and local) pipeline is supervised by our weights sharing encoder and can be easily trained end-to-end. Comprehensive experiments demonstrate that AFTrans can achieve SOTA performance on three published fine-grained benchmarks: CUB-200-2011, Stanford Dogs and iNat2017.