# TransFG: A Transformer Architecture for Fine-grained Recognition

arXiv: https://arxiv.org/abs/2103.07976 · HTML: https://mlsanity.com/paper/2103.07976/

## Key facts

- Cited by 132 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 57 references that are in the map.
- First posted on arXiv 14 Mar 2021.

## Builds on (most cited first, 30 of 41)

- [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)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [TransTrack: Multiple Object Tracking with Transformer](https://mlsanity.com/paper/2012.15460/) (2020)
- [MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers](https://mlsanity.com/paper/2012.00759/) (2020)
- [Video Action Transformer Network](https://mlsanity.com/paper/1812.02707/) (2018)
- [Fixing the train-test resolution discrepancy](https://mlsanity.com/paper/1906.06423/) (2019)
- [Learning to Navigate for Fine-grained Classification](https://mlsanity.com/paper/1809.00287/) (2018)
- [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)
- [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)
- [Cross-X Learning for Fine-Grained Visual Categorization](https://mlsanity.com/paper/1909.04412/) (2019)

## Built on by (most cited first, 30 of 132)

- [Revisiting Weakly Supervised Pre-Training of Visual Perception Models](https://mlsanity.com/paper/2201.08371/) (2022)
- [PartImageNet: A Large, High-Quality Dataset of Parts](https://mlsanity.com/paper/2112.00933/) (2021)
- [TransMix: Attend to Mix for Vision Transformers](https://mlsanity.com/paper/2111.09833/) (2021)
- [Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification](https://mlsanity.com/paper/2205.02151/) (2022)
- [Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification](https://mlsanity.com/paper/2307.15254/) (2023)
- [Which Tokens to Use? Investigating Token Reduction in Vision Transformers](https://mlsanity.com/paper/2308.04657/) (2023)
- [Learning Bottleneck Concepts in Image Classification](https://mlsanity.com/paper/2304.10131/) (2023)
- [Efficient Large Multi-modal Models via Visual Context Compression](https://mlsanity.com/paper/2406.20092/) (2024)
- [TF-CLIP: Learning Text-free CLIP for Video-based Person Re-Identification](https://mlsanity.com/paper/2312.09627/) (2023)
- [Image Difference Captioning with Pre-training and Contrastive Learning](https://mlsanity.com/paper/2202.04298/) (2022)
- [Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification](https://mlsanity.com/paper/2403.10254/) (2024)
- [RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition](https://mlsanity.com/paper/2107.08192/) (2021)
- [Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets](https://mlsanity.com/paper/2210.05958/) (2022)
- [MetaFormer: A Unified Meta Framework for Fine-Grained Recognition](https://mlsanity.com/paper/2203.02751/) (2022)
- [Zero-shot Generative Model Adaptation via Image-specific Prompt Learning](https://mlsanity.com/paper/2304.03119/) (2023)
- [Visualizing and Understanding Patch Interactions in Vision Transformer](https://mlsanity.com/paper/2203.05922/) (2022)
- [Fine-grained Visual Classification with High-temperature Refinement and Background Suppression](https://mlsanity.com/paper/2303.06442/) (2023)
- [Recent Advances in Vision Transformer: A Survey and Outlook of Recent Work](https://mlsanity.com/paper/2203.01536/) (2022)
- [SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization](https://mlsanity.com/paper/2209.02109/) (2022)
- [Generative Prompt Model for Weakly Supervised Object Localization](https://mlsanity.com/paper/2307.09756/) (2023)
- [Fine-grained Recognition with Learnable Semantic Data Augmentation](https://mlsanity.com/paper/2309.00399/) (2023)
- [A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition](https://mlsanity.com/paper/2110.01240/) (2021)
- [Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information](https://mlsanity.com/paper/2203.03253/) (2022)
- [Cross-Modal Causal Intervention for Medical Report Generation](https://mlsanity.com/paper/2303.09117/) (2023)
- [Delving into Multimodal Prompting for Fine-grained Visual Classification](https://mlsanity.com/paper/2309.08912/) (2023)
- [Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization](https://mlsanity.com/paper/2209.09209/) (2022)
- [Low-Resource Vision Challenges for Foundation Models](https://mlsanity.com/paper/2401.04716/) (2024)
- [Agglomerative Token Clustering](https://mlsanity.com/paper/2409.11923/) (2024)
- [Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset](https://mlsanity.com/paper/2207.10664/) (2022)
- [Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis](https://mlsanity.com/paper/2501.09333/) (2025)

## Abstract (arXiv)

Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is a very challenging task due to the inherently subtle inter-class differences. Most existing works mainly tackle this problem by reusing the backbone network to extract features of detected discriminative regions. However, this strategy inevitably complicates the pipeline and pushes the proposed regions to contain most parts of the objects thus fails to locate the really important parts. Recently, vision transformer (ViT) shows its strong performance in the traditional classification task. The self-attention mechanism of the transformer links every patch token to the classification token. In this work, we first evaluate the effectiveness of the ViT framework in the fine-grained recognition setting. Then motivated by the strength of the attention link can be intuitively considered as an indicator of the importance of tokens, we further propose a novel Part Selection Module that can be applied to most of the transformer architectures where we integrate all raw attention weights of the transformer into an attention map for guiding the network to effectively and accurately select discriminative image patches and compute their relations. A contrastive loss is applied to enlarge the distance between feature representations of confusing classes. We name the augmented transformer-based model TransFG and demonstrate the value of it by conducting experiments on five popular fine-grained benchmarks where we achieve state-of-the-art performance. Qualitative results are presented for better understanding of our model.