# Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?

arXiv: https://arxiv.org/abs/2309.06891 · HTML: https://mlsanity.com/paper/2309.06891/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 113 references that are in the map.
- First posted on arXiv 13 Sep 2023.

## Builds on (most cited first, 30 of 64)

- [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)
- [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)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)

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

- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language](https://mlsanity.com/paper/2406.05629/) (2024)
- [Vision Transformers Need More Than Registers](https://mlsanity.com/paper/2602.22394/) (2026)
- [Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency](https://mlsanity.com/paper/2506.10178/) (2025)
- [Register and [CLS] tokens yield a decoupling of local and global features in large ViTs](https://mlsanity.com/paper/2505.05892/) (2025)
- [Occlusion-Aware Seamless Segmentation](https://mlsanity.com/paper/2407.02182/) (2024)
- [Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification](https://mlsanity.com/paper/2509.24901/) (2025)
- [Beyond [cls]: Exploring the true potential of Masked Image Modeling representations](https://mlsanity.com/paper/2412.03215/) (2024)
- [LOCORE: Image Re-ranking with Long-Context Sequence Modeling](https://mlsanity.com/paper/2503.21772/) (2025)
- [Attention-Guided Masked Autoencoders For Learning Image Representations](https://mlsanity.com/paper/2402.15172/) (2024)
- [On Train-Test Class Overlap and Detection for Image Retrieval](https://mlsanity.com/paper/2404.01524/) (2024)
- [EDIT: Enhancing Vision Transformers by Mitigating Attention Sink through an Encoder-Decoder Architecture](https://mlsanity.com/paper/2504.06738/) (2025)
- [Two-stage Vision Transformers and Hard Masking offer Robust Object Representations](https://mlsanity.com/paper/2506.08915/) (2025)
- [SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models](https://mlsanity.com/paper/2601.11729/) (2026)
- [Channel-Aware Probing for Multi-Channel Imaging](https://mlsanity.com/paper/2602.12696/) (2026)
- [What-Where Transformer: A Slot-Centric Visual Backbone for Concurrent Representation and Localization](https://mlsanity.com/paper/2605.12021/) (2026)

## Abstract (arXiv)

Convolutional networks and vision transformers have different forms of pairwise interactions, pooling across layers and pooling at the end of the network. Does the latter really need to be different? As a by-product of pooling, vision transformers provide spatial attention for free, but this is most often of low quality unless self-supervised, which is not well studied. Is supervision really the problem? In this work, we develop a generic pooling framework and then we formulate a number of existing methods as instantiations. By discussing the properties of each group of methods, we derive SimPool, a simple attention-based pooling mechanism as a replacement of the default one for both convolutional and transformer encoders. We find that, whether supervised or self-supervised, this improves performance on pre-training and downstream tasks and provides attention maps delineating object boundaries in all cases. One could thus call SimPool universal. To our knowledge, we are the first to obtain attention maps in supervised transformers of at least as good quality as self-supervised, without explicit losses or modifying the architecture. Code at: https://github.com/billpsomas/simpool.