Yi-Ting Li
    • 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

      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.
      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

    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.
    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
    # Oral Feedback ## 老師 1. Q: FewVLM 訓練與 Predict 方式 - [x] 預訓練: MLM / PrefixLM, 推論: PrefixLM 2. Q: Pix2Seq 有包含的 Object - [x] 365 labaels ([Object365 Dataset](https://www.objects365.org/overview.html)) 3. Q: Patch 數量實驗 - [x] 須做實驗 4. Q: 論文最後結果最後放 - [ ] 先用數據鋪陳再放最後比較表 5. Q: Hint使用數量 - [x] 以完成 6. Q: 在inference 的實驗 - [ ] 詢問老師 7. Q: Image2text attention 取中點 -> 取平均 - [ ] 8. Q: PolyFormer用途 ## 朱老師 1. Q: 可解釋性的意義 A: 我們是否能夠理解模型 2. Q: 第一個用prompt是FewVLM 3. Q: 為什麼Loss function使用Cross-Entropy ![](https://hackmd.io/_uploads/HyR6bMxPn.png) A: 4. Q: Prompt-based vs. Low-resource ## 李老師 1. Instruction of task 的變化 - 不根據[Q]來變動 - 不見得效果好 2. Hint 順序 檢查hint差異度跟難度 4. 為什麼不使用相同模型 5. Hint 視覺化 ## 黃老師 1. 找不到答案的case 2. $n_\text{bin} = 1000$ 3. 為什麼使用Pix2Seq ## 阿雯 任務:記口委的問題 粉色口罩 黃老師 綠色口罩 李老師 朱老師 高老師 === 晴雯的筆記 === Iccv 2015 VG 任務 Wsdm'23 toloka VQA Dataset 更具挑戰的 Visual Grounding Region proposals 因為 2-stage 太依賴第一階段 rp 了,所以採用 1-stage pipeline,不過後者的缺點是缺乏可解釋性 Prompt tuning 在 ACL 22 A good prompt is worth a million params 裡面成功和 vl 結合:encoder-decoder based,但是生出的是 object detect answer。1. FewVLM VQA如何套用到 VG 2. Input method for img and q? 3. Supervision? 不透過 Fast(er) R-CNN 來 encode img,改參考 SimVLM(類似 ViT):在 ViT 之前先過 cnn。 Loc tokens 用力臭一下其他人8張a100還輸我們家庭神 === 口委的問題 === 大概15:15開始 過程中都沒有問任何問題 1. 朱:我學到不少,謝謝。 2. 11頁已經summarize了主要解決的問題與可能的目標和優勢。優勢的部分,可解釋性如何評估比別人高?(庭:給錯誤的 hint 的確有辦法改變模型的 output)其他VG Models 如何定義他們的可解釋性?(庭:可解釋性是和1-stage比較) 3. 你們是最早的將動態prompt 引入 VG 任務的work嗎?(庭:算是) 4. P.34 為什麼用 CE Loss? 為什麼讓他變成分類任務?(回答沒聽懂,庭神自己看影片) 5. P.37 leaderboard 第一名的做法? (庭:使用 ViT Adapter 去做 finetuned。依賴較複雜的模型與大量的資料) 6. Low-resource setting:在設計的過程中有無刻意去減少 resource consumption?(庭:沒有,主要是想利用 prompt tuning 的技巧在 VL 任務) 7. 李老師: instructional task 具體而言只有這句?IoQ的部分可以調整嗎?p.30(庭:對,要固定,引導效果才會穩定) 8. 有問題沒辦法找到對應 region 或需要多個 regions來回答嗎 ? 9. 我認為你的方法亮點是 hint design,hints 之間有先後順序與重要性關係嗎?(我感覺目前只有探討不同預訓練ofa產出的hint的品質。好像沒有去探討這件事,庭神回答的意思應該是目前當他們都是獨立的)老師覺得它們可以用其他方式結合看看。如果後面有人接手或extend,要不要看看 hint composition。 10. 黃老師:比賽資料集有些題目找不到答案對吧,這個要怎麼辦?(庭神:我沒有做這個)應該要 study 這些 cases 11. 不同 size 的 bbox 的 dictionary 值不一樣嗎?(庭神:ㄟ是用 bin 來看,我們最後的 size 是選 1000 當作 vocab size)。 12. P.12 pix2seq 為什麼要 supervise 這個模型呀 (庭神:一大堆話...)簡單來說就是只想用cross entropy loss?然後要想這整個架構的設計之類的因為以往的模型會有超多雜七雜八的 loss,還要考慮什麼 img-text alignment ,還要看文字產生的正確性啥的,但現在變成這樣所以要想要怎麼選擇合適的 loss 13. 提示的架構 prompt template p.30 有想換嗎?(我覺得老師的意思就是換句話問的結果如何?但這個prompt template 就是 discrete的,要換有超多種可以換)

    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

    By clicking below, you agree to our terms of service.

    Sign in via Facebook Sign in via Twitter Sign in via GitHub Sign in via Dropbox Sign in with Wallet
    Wallet ( )
    Connect another wallet

    New to HackMD? Sign up

    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