# Scalable Vision Transformers with Hierarchical Pooling

arXiv: https://arxiv.org/abs/2103.10619 · HTML: https://mlsanity.com/paper/2103.10619/

## Key facts

- Cited by 84 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 53 references that are in the map.
- First posted on arXiv 19 Mar 2021.

## Builds on (most cited first, 30 of 44)

- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [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)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Are Sixteen Heads Really Better than One?](https://mlsanity.com/paper/1905.10650/) (2019)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [End-to-End Video Instance Segmentation with Transformers](https://mlsanity.com/paper/2011.14503/) (2020)

## Built on by (most cited first, 30 of 84)

- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [Adaptive Token Sampling For Efficient Vision Transformers](https://mlsanity.com/paper/2111.15667/) (2021)
- [SPViT: Enabling Faster Vision Transformers via Soft Token Pruning](https://mlsanity.com/paper/2112.13890/) (2021)
- [Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers](https://mlsanity.com/paper/2108.06932/) (2021)
- [Multi-class Token Transformer for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02891/) (2022)
- [Patch Slimming for Efficient Vision Transformers](https://mlsanity.com/paper/2106.02852/) (2021)
- [Selective Structured State-Spaces for Long-Form Video Understanding](https://mlsanity.com/paper/2303.14526/) (2023)
- [Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers](https://mlsanity.com/paper/2304.10716/) (2023)
- [Unified Visual Transformer Compression](https://mlsanity.com/paper/2203.08243/) (2022)
- [A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity](https://mlsanity.com/paper/2302.06015/) (2023)
- [Gaze Estimation using Transformer](https://mlsanity.com/paper/2105.14424/) (2021)
- [X-Pruner: eXplainable Pruning for Vision Transformers](https://mlsanity.com/paper/2303.04935/) (2023)
- [DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers](https://mlsanity.com/paper/2204.12997/) (2022)
- [CF-ViT: A General Coarse-to-Fine Method for Vision Transformer](https://mlsanity.com/paper/2203.03821/) (2022)
- [Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting--Full Version](https://mlsanity.com/paper/2204.13767/) (2022)
- [A Survey on Transformer Compression](https://mlsanity.com/paper/2402.05964/) (2024)
- [Attention Mechanism in Neural Networks: Where it Comes and Where it Goes](https://mlsanity.com/paper/2204.13154/) (2022)
- [Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning](https://mlsanity.com/paper/2203.09064/) (2022)
- [Stitchable Neural Networks](https://mlsanity.com/paper/2302.06586/) (2023)
- [Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks](https://mlsanity.com/paper/2207.01580/) (2022)
- [Skip-Attention: Improving Vision Transformers by Paying Less Attention](https://mlsanity.com/paper/2301.02240/) (2023)
- [Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation](https://mlsanity.com/paper/2307.03407/) (2023)
- [MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2308.03005/) (2023)
- [Generative Spoken Language Model based on continuous word-sized audio tokens](https://mlsanity.com/paper/2310.05224/) (2023)
- [Revealing Occlusions with 4D Neural Fields](https://mlsanity.com/paper/2204.10916/) (2022)
- [PanGu-π: Enhancing Language Model Architectures via Nonlinearity Compensation](https://mlsanity.com/paper/2312.17276/) (2023)
- [Dynamic Focus-aware Positional Queries for Semantic Segmentation](https://mlsanity.com/paper/2204.01244/) (2022)
- [An Efficient Spatio-Temporal Pyramid Transformer for Action Detection](https://mlsanity.com/paper/2207.10448/) (2022)
- [Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2308.04016/) (2023)
- [TransMatting: Enhancing Transparent Objects Matting with Transformers](https://mlsanity.com/paper/2208.03007/) (2022)

## Abstract (arXiv)

The recently proposed Visual image Transformers (ViT) with pure attention have achieved promising performance on image recognition tasks, such as image classification. However, the routine of the current ViT model is to maintain a full-length patch sequence during inference, which is redundant and lacks hierarchical representation. To this end, we propose a Hierarchical Visual Transformer (HVT) which progressively pools visual tokens to shrink the sequence length and hence reduces the computational cost, analogous to the feature maps downsampling in Convolutional Neural Networks (CNNs). It brings a great benefit that we can increase the model capacity by scaling dimensions of depth/width/resolution/patch size without introducing extra computational complexity due to the reduced sequence length. Moreover, we empirically find that the average pooled visual tokens contain more discriminative information than the single class token. To demonstrate the improved scalability of our HVT, we conduct extensive experiments on the image classification task. With comparable FLOPs, our HVT outperforms the competitive baselines on ImageNet and CIFAR-100 datasets. Code is available at https://github.com/MonashAI/HVT