徐郁淞
  • NEW!
    NEW!  Connect Ideas Across Notes
    Save time and share insights. With Paragraph Citation, you can quote others’ work with source info built in. If someone cites your note, you’ll see a card showing where it’s used—bringing notes closer together.
    Got it
      • Create new note
      • Create a note from template
        • Sharing URL Link copied
        • /edit
        • View mode
          • Edit mode
          • View mode
          • Book mode
          • Slide mode
          Edit mode View mode Book mode Slide mode
        • Customize slides
        • Note Permission
        • Read
          • Only me
          • Signed-in users
          • Everyone
          Only me Signed-in users Everyone
        • Write
          • Only me
          • Signed-in users
          • Everyone
          Only me Signed-in users Everyone
        • Engagement control Commenting, Suggest edit, Emoji Reply
      • Invite by email
        Invitee

        This note has no invitees

      • Publish Note

        Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note No publishing access yet

        Your note will be visible on your profile and discoverable by anyone.
        Your note is now live.
        This note is visible on your profile and discoverable online.
        Everyone on the web can find and read all notes of this public team.

        Your account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

        Your team account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

        Explore these features while you wait
        Complete general settings
        Bookmark and like published notes
        Write a few more notes
        Complete general settings
        Write a few more notes
        See published notes
        Unpublish note
        Please check the box to agree to the Community Guidelines.
        View profile
      • Commenting
        Permission
        Disabled Forbidden Owners Signed-in users Everyone
      • Enable
      • Permission
        • Forbidden
        • Owners
        • Signed-in users
        • Everyone
      • Suggest edit
        Permission
        Disabled Forbidden Owners Signed-in users Everyone
      • Enable
      • Permission
        • Forbidden
        • Owners
        • Signed-in users
      • Emoji Reply
      • Enable
      • Versions and GitHub Sync
      • Note settings
      • Note Insights New
      • Engagement control
      • Make a copy
      • Transfer ownership
      • Delete this note
      • Save as template
      • Insert from template
      • Import from
        • Dropbox
        • Google Drive
        • Gist
        • Clipboard
      • Export to
        • Dropbox
        • Google Drive
        • Gist
      • Download
        • Markdown
        • HTML
        • Raw HTML
    Menu Note settings Note Insights Versions and GitHub Sync Sharing URL Create Help
    Create Create new note Create a note from template
    Menu
    Options
    Engagement control Make a copy Transfer ownership Delete this note
    Import from
    Dropbox Google Drive Gist Clipboard
    Export to
    Dropbox Google Drive Gist
    Download
    Markdown HTML Raw HTML
    Back
    Sharing URL Link copied
    /edit
    View mode
    • Edit mode
    • View mode
    • Book mode
    • Slide mode
    Edit mode View mode Book mode Slide mode
    Customize slides
    Note Permission
    Read
    Only me
    • Only me
    • Signed-in users
    • Everyone
    Only me Signed-in users Everyone
    Write
    Only me
    • Only me
    • Signed-in users
    • Everyone
    Only me Signed-in users Everyone
    Engagement control Commenting, Suggest edit, Emoji Reply
  • Invite by email
    Invitee

    This note has no invitees

  • Publish Note

    Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note No publishing access yet

    Your note will be visible on your profile and discoverable by anyone.
    Your note is now live.
    This note is visible on your profile and discoverable online.
    Everyone on the web can find and read all notes of this public team.

    Your account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

    Your team account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

    Explore these features while you wait
    Complete general settings
    Bookmark and like published notes
    Write a few more notes
    Complete general settings
    Write a few more notes
    See published notes
    Unpublish note
    Please check the box to agree to the Community Guidelines.
    View profile
    Engagement control
    Commenting
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    • Everyone
    Suggest edit
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    Emoji Reply
    Enable
    Import from Dropbox Google Drive Gist Clipboard
       Owned this note    Owned this note      
    Published Linked with GitHub
    • Any changes
      Be notified of any changes
    • Mention me
      Be notified of mention me
    • Unsubscribe
    # AN IMAGE IS WORTH 16x16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE **Anonymous authors** Under review as a conference paper at ICLR 2021 ## ABSTRACT * 在 NLP 領域上,Transformer architecture 是一個很重要的架構,但不常使用在 vision * attention 常和 cnn 結合 * 這篇文章要直接應用 transformation , 且證明可以表現得很好 * 可以用更少的資源,且訓練得跟 SOTA 一樣好 ## INTRODUCTION * 由於 self-attention 在 NLP 上的成功,有人他用來取代 CNN(Ramachandran et al., 2019; Wang et al., 2020a),但只有理論上的有效率,而由於他是用特別的 attention patterns ,因此在大型資料集上的 image recognition 還是 classic ResNet-like architecture 比較好 * 因為 NLP 處理的資料是序列化的,而 cv 處理的資料是三維的,長寬和channels,所以將影響分割成 patchs ,並將 patches 變成依序列線性嵌入,當成 transformer 的輸入。 ## METHOD 使用很接近 original Transformer(Vaswani et al., 2017) ,這樣有意的設計是為了有 scalable NLP Transformer architectures 的優勢,還有有效率的實作,希望可以超越最好的 CNN ### 3.1 VISION TRANSFORMER ![](https://i.imgur.com/RMtjepC.png) **a. 將圖片序列化** 首先將圖像分割成 patchs ,然後將每個 patch 重塑成一個向量,得到 flattened patch。 如果圖片是 `H x W x C` 用 `P x P` 大小的 patch 去分割圖片得到 N 個 patch ,那每個 patch 的 shape 是 `P x P x C` ,轉成向量會是 $P^2C$ 維的向量,將 N 個 patch reshape 的向量 concat 在一起得到, $N x (P^2C)$ 的 2D vector , 和 NLP輸入 transformer 的詞向量相同。 **b. Position embedding** 因為 transformer 本身沒有位置訊息,我們要用 position embedding 將位置訊息加到模型。 如上圖,編號 0-9 的紫色框表示各個位置的 positon embedding ,而紫框旁邊的粉色框是經過 linear projection 之後的 flattened patch 向量。 使用將 position embedding 和 patch embedding 相加的方式結合 position 訊息。 **c. Learnable embedding** 上圖帶星號的粉色框不是通過某個 patch 產生的,他是一個 learnable embedding(既做 $X_{class}$),其作用類似於 BERT中的 [class] token。 在 BERT 中。[class] token 經過 encoder 後對應的結果作為整個句子的表示; 類似地,這裡 $X_{class}$ 經過 encoder 後的對應的結果也最為整個圖的表示。 為什麼 BERT 或者這篇文章的 ViT 要多加一個 token 呢?因為如果人為指定一個 embedding ,經過 encoder 得到的結果作為整體的表示,則不可避免會使得整體表示偏向於這個指定 embedding 的訊息,而這個新增的 token 沒有語意訊息,與圖像的任何 patch 無關,所以可以公平的反應全圖的資訊。 **d. Transformer encoder --- 4.5 INSPECTING VISION TRANSFORMER ![](https://i.imgur.com/NbUVSB7.png) 在中等規模的數據集上(例如ImageNet),transformer 模型的表現不如ResNets; 而當數據及的規模擴大, transformer 模型的效果接近或是超過目前的一些 SOTA。 ## 補充 ![](https://i.imgur.com/Kqpigd1.png) ![](https://i.imgur.com/4CNGHhn.png) ![](https://i.imgur.com/KgjtW5H.png) ![](https://i.imgur.com/q8bss0z.png) **Transformer** ![](https://i.imgur.com/Nx3KLcj.png) ## Reference https://arxiv.org/abs/2010.11929 https://zhuanlan.zhihu.com/p/266311690 ###### tags: `uscc論文`

    Import from clipboard

    Paste your markdown or webpage here...

    Advanced permission required

    Your current role can only read. Ask the system administrator to acquire write and comment permission.

    This team is disabled

    Sorry, this team is disabled. You can't edit this note.

    This note is locked

    Sorry, only owner can edit this note.

    Reach the limit

    Sorry, you've reached the max length this note can be.
    Please reduce the content or divide it to more notes, thank you!

    Import from Gist

    Import from Snippet

    or

    Export to Snippet

    Are you sure?

    Do you really want to delete this note?
    All users will lose their connection.

    Create a note from template

    Create a note from template

    Oops...
    This template has been removed or transferred.
    Upgrade
    All
    • All
    • Team
    No template.

    Create a template

    Upgrade

    Delete template

    Do you really want to delete this template?
    Turn this template into a regular note and keep its content, versions, and comments.

    This page need refresh

    You have an incompatible client version.
    Refresh to update.
    New version available!
    See releases notes here
    Refresh to enjoy new features.
    Your user state has changed.
    Refresh to load new user state.

    Sign in

    Forgot password
    or
    Sign in via Google Sign in via Facebook Sign in via X(Twitter) Sign in via GitHub Sign in via Dropbox Sign in with Wallet
    Wallet ( )
    Connect another wallet

    New to HackMD? Sign up

    By signing in, you agree to our terms of service.

    Help

    • English
    • 中文
    • Français
    • Deutsch
    • 日本語
    • Español
    • Català
    • Ελληνικά
    • Português
    • italiano
    • Türkçe
    • Русский
    • Nederlands
    • hrvatski jezik
    • język polski
    • Українська
    • हिन्दी
    • svenska
    • Esperanto
    • dansk

    Documents

    Help & Tutorial

    How to use Book mode

    Slide Example

    API Docs

    Edit in VSCode

    Install browser extension

    Contacts

    Feedback

    Discord

    Send us email

    Resources

    Releases

    Pricing

    Blog

    Policy

    Terms

    Privacy

    Cheatsheet

    Syntax Example Reference
    # Header Header 基本排版
    - Unordered List
    • Unordered List
    1. Ordered List
    1. Ordered List
    - [ ] Todo List
    • Todo List
    > Blockquote
    Blockquote
    **Bold font** Bold font
    *Italics font* Italics font
    ~~Strikethrough~~ Strikethrough
    19^th^ 19th
    H~2~O H2O
    ++Inserted text++ Inserted text
    ==Marked text== Marked text
    [link text](https:// "title") Link
    ![image alt](https:// "title") Image
    `Code` Code 在筆記中貼入程式碼
    ```javascript
    var i = 0;
    ```
    var i = 0;
    :smile: :smile: Emoji list
    {%youtube youtube_id %} Externals
    $L^aT_eX$ LaTeX
    :::info
    This is a alert area.
    :::

    This is a alert area.

    Versions and GitHub Sync
    Get Full History Access

    • Edit version name
    • Delete

    revision author avatar     named on  

    More Less

    Note content is identical to the latest version.
    Compare
      Choose a version
      No search result
      Version not found
    Sign in to link this note to GitHub
    Learn more
    This note is not linked with GitHub
     

    Feedback

    Submission failed, please try again

    Thanks for your support.

    On a scale of 0-10, how likely is it that you would recommend HackMD to your friends, family or business associates?

    Please give us some advice and help us improve HackMD.

     

    Thanks for your feedback

    Remove version name

    Do you want to remove this version name and description?

    Transfer ownership

    Transfer to
      Warning: is a public team. If you transfer note to this team, everyone on the web can find and read this note.

        Link with GitHub

        Please authorize HackMD on GitHub
        • Please sign in to GitHub and install the HackMD app on your GitHub repo.
        • HackMD links with GitHub through a GitHub App. You can choose which repo to install our App.
        Learn more  Sign in to GitHub

        Push the note to GitHub Push to GitHub Pull a file from GitHub

          Authorize again
         

        Choose which file to push to

        Select repo
        Refresh Authorize more repos
        Select branch
        Select file
        Select branch
        Choose version(s) to push
        • Save a new version and push
        • Choose from existing versions
        Include title and tags
        Available push count

        Pull from GitHub

         
        File from GitHub
        File from HackMD

        GitHub Link Settings

        File linked

        Linked by
        File path
        Last synced branch
        Available push count

        Danger Zone

        Unlink
        You will no longer receive notification when GitHub file changes after unlink.

        Syncing

        Push failed

        Push successfully