# Refiner: Refining Self-attention for Vision Transformers

arXiv: https://arxiv.org/abs/2106.03714 · HTML: https://mlsanity.com/paper/2106.03714/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 70 references that are in the map.
- First posted on arXiv 7 Jun 2021.

## Builds on (most cited first, 30 of 50)

- [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)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)

## Built on by (most cited first, 30 of 38)

- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [Mobile-Former: Bridging MobileNet and Transformer](https://mlsanity.com/paper/2108.05895/) (2021)
- [Focal Modulation Networks](https://mlsanity.com/paper/2203.11926/) (2022)
- [Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer](https://mlsanity.com/paper/2108.01390/) (2021)
- [SPViT: Enabling Faster Vision Transformers via Soft Token Pruning](https://mlsanity.com/paper/2112.13890/) (2021)
- [VOLO: Vision Outlooker for Visual Recognition](https://mlsanity.com/paper/2106.13112/) (2021)
- [Understanding The Robustness in Vision Transformers](https://mlsanity.com/paper/2204.12451/) (2022)
- [Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice](https://mlsanity.com/paper/2203.05962/) (2022)
- [MetaFormer Baselines for Vision](https://mlsanity.com/paper/2210.13452/) (2022)
- [CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06165/) (2021)
- [Large language models in healthcare and medical domain: A review](https://mlsanity.com/paper/2401.06775/) (2023)
- [A Survey of Visual Transformers](https://mlsanity.com/paper/2111.06091/) (2021)
- [Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition](https://mlsanity.com/paper/2106.12368/) (2021)
- [HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers](https://mlsanity.com/paper/2211.08110/) (2022)
- [Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention](https://mlsanity.com/paper/2112.14000/) (2021)
- [The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy](https://mlsanity.com/paper/2203.06345/) (2022)
- [The Devil is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2204.08227/) (2022)
- [Scaled ReLU Matters for Training Vision Transformers](https://mlsanity.com/paper/2109.03810/) (2021)
- [DynaMixer: A Vision MLP Architecture with Dynamic Mixing](https://mlsanity.com/paper/2201.12083/) (2022)
- [Sequencer: Deep LSTM for Image Classification](https://mlsanity.com/paper/2205.01972/) (2022)
- [FFT-based Dynamic Token Mixer for Vision](https://mlsanity.com/paper/2303.03932/) (2023)
- [Setting the Record Straight on Transformer Oversmoothing](https://mlsanity.com/paper/2401.04301/) (2024)
- [ELSA: Enhanced Local Self-Attention for Vision Transformer](https://mlsanity.com/paper/2112.12786/) (2021)
- [Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention](https://mlsanity.com/paper/2203.03937/) (2022)
- [SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation](https://mlsanity.com/paper/2308.11568/) (2023)
- [Graph Convolutions Enrich the Self-Attention in Transformers!](https://mlsanity.com/paper/2312.04234/) (2023)
- [ConvFormer: Plug-and-Play CNN-Style Transformers for Improving Medical Image Segmentation](https://mlsanity.com/paper/2309.05674/) (2023)
- [Calibrating Undisciplined Over-Smoothing in Transformer for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2305.03112/) (2023)
- [Foundation Models for Autonomous Robots in Unstructured Environments](https://mlsanity.com/paper/2407.14296/) (2024)
- [3D Shuffle-Mixer: An Efficient Context-Aware Vision Learner of Transformer-MLP Paradigm for Dense Prediction in Medical Volume](https://mlsanity.com/paper/2204.06779/) (2022)

## Abstract (arXiv)

Vision Transformers (ViTs) have shown competitive accuracy in image classification tasks compared with CNNs. Yet, they generally require much more data for model pre-training. Most of recent works thus are dedicated to designing more complex architectures or training methods to address the data-efficiency issue of ViTs. However, few of them explore improving the self-attention mechanism, a key factor distinguishing ViTs from CNNs. Different from existing works, we introduce a conceptually simple scheme, called refiner, to directly refine the self-attention maps of ViTs. Specifically, refiner explores attention expansion that projects the multi-head attention maps to a higher-dimensional space to promote their diversity. Further, refiner applies convolutions to augment local patterns of the attention maps, which we show is equivalent to a distributed local attention features are aggregated locally with learnable kernels and then globally aggregated with self-attention. Extensive experiments demonstrate that refiner works surprisingly well. Significantly, it enables ViTs to achieve 86% top-1 classification accuracy on ImageNet with only 81M parameters.