Exploring whether attention is necessary for vision transformers

Related tags

Deep Learningdo-you-even-need-attention
Overview

Do You Even Need Attention?
A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet

Paper/Report

TL;DR

We replace the attention layer in a vision transformer with a feed-forward layer and find that it still works quite well on ImageNet.

Abstract

The strong performance of vision transformers on image classification and other vision tasks is often attributed to the design of their multi-head attention layers. However, the extent to which attention is responsible for this strong performance remains unclear. In this short report, we ask: is the attention layer even necessary? Specifically, we replace the attention layer in a vision transformer with a feed-forward layer applied over the patch dimension. The resulting architecture is simply a series of feed-forward layers applied over the patch and feature dimensions in an alternating fashion. In experiments on ImageNet, this architecture performs surprisingly well: a ViT/DeiT-base-sized model obtains 74.9% top-1 accuracy, compared to 77.9% and 79.9% for ViT and DeiT respectively. These results indicate that aspects of vision transformers other than attention, such as the patch embedding, may be more responsible for their strong performance than previously thought. We hope these results prompt the community to spend more time trying to understand why our current models are as effective as they are.

Note

This is concurrent research with MLP-Mixer from Google Research. The ideas are exacty the same, with the one difference being that they use (a lot) more compute.

Pretrained models and logs

Here is a Weights and Biases report with the expected training trajectory: W&B

name [email protected] #params url
FF-tiny 61.4 7.7M model
FF-base 74.9 62M model
FF-large 71.4 206M -

Note: I haven't uploaded the FF-Large model because (1) it's over GitHub's file storage limit, and (2) I don't see why anyone would want it, given that it performs worse than the base model. That being said, if you want it, reach out to me and I'll send it to you.

How to train

The model definition in vision_transformer_linear.py is designed to be run with the repo from DeiT, which is itself based on the wonderful timm package.

Steps:

  • Clone the DeiT repo and move the file into it
git clone https://github.com/facebookresearch/deit
mv vision_transformer_linear.py deit
cd deit
  • Add a line to import vision_transformer_linear in main.py. For example, add the following after the import statements (around line 27):
+ import vision_transformer_linear
  • Train:
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m torch.distributed.launch \
--nproc_per_node=8 \
--master_port 10490 \
--use_env main.py \
--model linear_tiny \
--batch-size 128 \
--drop 0.1 \
--output_dir outputs/linear-tiny \
--data-path your/path/to/imagenet

Citation

If you build upon this idea, feel free to drop a citation (and also cite MLP-Mixer).

@article{melaskyriazi2021doyoueven,
  title={Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet},
  author={Luke Melas-Kyriazi},
  journal=arxiv,
  year=2021
}
You might also like...
The first dataset of composite images with rationality score indicating whether the object placement in a composite image is reasonable.
The first dataset of composite images with rationality score indicating whether the object placement in a composite image is reasonable.

Object-Placement-Assessment-Dataset-OPA Object-Placement-Assessment (OPA) is to verify whether a composite image is plausible in terms of the object p

BCMI 53 Nov 15, 2022
Face Mask Detection is a project to determine whether someone is wearing mask or not, using deep neural network.
Face Mask Detection is a project to determine whether someone is wearing mask or not, using deep neural network.

face-mask-detection Face Mask Detection is a project to determine whether someone is wearing mask or not, using deep neural network. It contains 3 scr

amirsalar 13 Jan 18, 2022
This program was designed to detect whether someone is wearing a facemask through a live video stream.

This program was designed to detect whether someone is wearing a facemask through a live video stream. A custom lightweight CNN trained with TensorFlow on a public dataset provided by Kaggle is used to detect whether each face detected by the cv2 face detection dnn is wearing a mask

null 0 Apr 2, 2022
A system used to detect whether a person is wearing a medical mask or not.

Mask_Detection_System A system used to detect whether a person is wearing a medical mask or not. To open the program, please follow these steps: Make

Mohamed Emad 0 Nov 17, 2022
Diabet Feature Engineering - Predict whether people have diabetes when their characteristics are specified

Diabet Feature Engineering - Predict whether people have diabetes when their characteristics are specified

Şebnem 6 Jan 18, 2022
Diabetes-Feature-Engineering - A machine learning model that can predict whether people have diabetes when their characteristics are specified

Diabetes-Feature-Engineering Aim Developing a machine learning model that can pr

Özlem Taşkın 0 Feb 23, 2022
Multivariate Time Series Forecasting with efficient Transformers. Code for the paper
Multivariate Time Series Forecasting with efficient Transformers. Code for the paper "Long-Range Transformers for Dynamic Spatiotemporal Forecasting."

Spacetimeformer Multivariate Forecasting This repository contains the code for the paper, "Long-Range Transformers for Dynamic Spatiotemporal Forecast

QData 440 Jan 2, 2023
Implementation of SE3-Transformers for Equivariant Self-Attention, in Pytorch.

SE3 Transformer - Pytorch Implementation of SE3-Transformers for Equivariant Self-Attention, in Pytorch. May be needed for replicating Alphafold2 resu

Phil Wang 207 Dec 23, 2022
Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.
Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

PyTorch Implementation of Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers 1 Using Colab Please notic

Hila Chefer 489 Jan 7, 2023
Comments
  • On details about the experiments

    On details about the experiments

    In the experiment section of the report, you mention:

    Such a comparison is not exactly fair because the feed-forward model uses stronger training augmentations.

    I wonder what the augmentations are, for details about the augmentation seems missing from the paper.

    opened by boredtylin 2
  • Positional Encoding Ablation

    Positional Encoding Ablation

    Hi Luke, thank you for sharing this amazing work.

    In your arxiv document, I cannot find any mention of positional encoding, but I see that you use them in your code. Did you conduct any ablation study on the PE? i.e., how much does it affect the performance, with and without?

    Thank you in advance.

    opened by jjparkcv 0
  • Interaction between patches through a transpose may have a stronger role to play ?

    Interaction between patches through a transpose may have a stronger role to play ?

    Hi, I was going through your exp report. You have made a point that since you are able to get a good performance without using attention layer so good performance of ViT may be more to do with it's embedding layer than attention .

    But I believe, It's also may be to do with how you have established an interaction between patches through a transpose very similar to what was done in MLP-Mixer .

    Would love to know your thoughts on this ?

    opened by rakshith291 0
Owner
Luke Melas-Kyriazi
I'm student at Harvard University studying mathematics and computer science, always open to collaborate on interesting projects!
Luke Melas-Kyriazi
GitHub Repository
Matlab Python Heuristic Battery Opt - SMOP conversion and manual conversion

SMOP is Small Matlab and Octave to Python compiler. SMOP translates matlab to py

Tom Xu 1 Jan 12, 2022
SeqTR: A Simple yet Universal Network for Visual Grounding

SeqTR This is the official implementation of SeqTR: A Simple yet Universal Network for Visual Grounding, which simplifies and unifies the modelling fo

seanZhuh 76 Dec 24, 2022
Code for "Causal autoregressive flows" - AISTATS, 2021

Code for "Causal Autoregressive Flow" This repository contains code to run and reproduce experiments presented in Causal Autoregressive Flows, present

Ricardo Pio Monti 35 Dec 16, 2022
VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning

    VarCLR: Variable Representation Pre-training via Contrastive Learning New: Paper accepted by ICSE 2022. Preprint at arXiv! This repository contain

squaresLab 32 Oct 24, 2022
[AAAI2022] Source code for our paper《Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning》

SSVC The source code for paper [Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning] samples of the

7 Oct 26, 2022
PyTorch implementation of DreamerV2 model-based RL algorithm

PyDreamer Reimplementation of DreamerV2 model-based RL algorithm in PyTorch. The official DreamerV2 implementation can be found here. Features ... Run

118 Dec 15, 2022
Official PyTorch code for WACV 2022 paper "CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows"

CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows WACV 2022 preprint:https://arxiv.org/abs/2107.1

Denis 156 Dec 28, 2022
Repository for MDPGT

MD-PGT Repository for implementing and reproducing the results for the paper MDPGT: Momentum-based Decentralized Policy Gradient Tracking. Available E

Xian Yeow Lee 2 Dec 30, 2021
Tools to create pixel-wise object masks, bounding box labels (2D and 3D) and 3D object model (PLY triangle mesh) for object sequences filmed with an RGB-D camera.

Tools to create pixel-wise object masks, bounding box labels (2D and 3D) and 3D object model (PLY triangle mesh) for object sequences filmed with an RGB-D camera. This project prepares training and t

305 Dec 16, 2022
Demo code for ICCV 2021 paper "Sensor-Guided Optical Flow"

Sensor-Guided Optical Flow Demo code for "Sensor-Guided Optical Flow", ICCV 2021 This code is provided to replicate results with flow hints obtained f

10 Mar 16, 2022
Python Implementation of algorithms in Graph Mining, e.g., Recommendation, Collaborative Filtering, Community Detection, Spectral Clustering, Modularity Maximization, co-authorship networks.

Graph Mining Author: Jiayi Chen Time: April 2021 Implemented Algorithms: Network: Scrabing Data, Network Construbtion and Network Measurement (e.g., P

Jiayi Chen 3 Mar 03, 2022
PyImpetus is a Markov Blanket based feature subset selection algorithm that considers features both separately and together as a group in order to provide not just the best set of features but also the best combination of features

PyImpetus PyImpetus is a Markov Blanket based feature selection algorithm that selects a subset of features by considering their performance both indi

Atif Hassan 103 Dec 14, 2022
Specification language for generating Generalized Linear Models (with or without mixed effects) from conceptual models

tisane Tisane: Authoring Statistical Models via Formal Reasoning from Conceptual and Data Relationships TL;DR: Analysts can use Tisane to author gener

Eunice Jun 11 Nov 15, 2022
A tool for making map images from OpenTTD save games

OpenTTD Surveyor A tool for making map images from OpenTTD save games. This is not part of the main OpenTTD codebase, nor is it ever intended to be pa

Aidan Randle-Conde 9 Feb 15, 2022
CMP 414/765 course repository for Spring 2022 semester

CMP414/765: Artificial Intelligence Spring2021 This is the GitHub repository for course CMP 414/765: Artificial Intelligence taught at The City Univer

ch00226855 4 May 16, 2022
Collective Multi-type Entity Alignment Between Knowledge Graphs (WWW'20)

CG-MuAlign A reference implementation for "Collective Multi-type Entity Alignment Between Knowledge Graphs", published in WWW 2020. If you find our pa

Bran Zhu 28 Dec 11, 2022
Deep Q-learning for playing chrome dino game

[PYTORCH] Deep Q-learning for playing Chrome Dino

Viet Nguyen 68 Dec 05, 2022
U-2-Net: U Square Net - Modified for paired image training of style transfer

U2-Net: U Square Net Modified for paired image training of style transfer This is an unofficial repo making use of the code which was made available b

Doron Adler 43 Oct 03, 2022
[CVPR 2021] 'Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator'

[CVPR2021] Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator Overview This is the entire codebase for the paper

35 Dec 01, 2022
PantheonRL is a package for training and testing multi-agent reinforcement learning environments.

PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tuning, ad-hoc coordination, and more.

Stanford Intelligent and Interactive Autonomous Systems Group 57 Dec 28, 2022