Several recent papers have explored self-supervised learning methods for vision transformers (ViT). Key approaches include:
1. Masked prediction tasks that predict masked patches of the input image.
2. Contrastive learning using techniques like MoCo to learn representations by contrasting augmented views of the same image.
3. Self-distillation methods like DINO that distill a teacher ViT into a student ViT using different views of the same image.
4. Hybrid approaches that combine masked prediction with self-distillation, such as iBOT.
本スライドは、弊社の梅本により弊社内の技術勉強会で使用されたものです。
近年注目を集めるアーキテクチャーである「Transformer」の解説スライドとなっております。
"Arithmer Seminar" is weekly held, where professionals from within and outside our company give lectures on their respective expertise.
The slides are made by the lecturer from outside our company, and shared here with his/her permission.
Arithmer株式会社は東京大学大学院数理科学研究科発の数学の会社です。私達は現代数学を応用して、様々な分野のソリューションに、新しい高度AIシステムを導入しています。AIをいかに上手に使って仕事を効率化するか、そして人々の役に立つ結果を生み出すのか、それを考えるのが私たちの仕事です。
Arithmer began at the University of Tokyo Graduate School of Mathematical Sciences. Today, our research of modern mathematics and AI systems has the capability of providing solutions when dealing with tough complex issues. At Arithmer we believe it is our job to realize the functions of AI through improving work efficiency and producing more useful results for society.
This document summarizes a research paper on scaling laws for neural language models. Some key findings of the paper include:
- Language model performance depends strongly on model scale and weakly on model shape. With enough compute and data, performance scales as a power law of parameters, compute, and data.
- Overfitting is universal, with penalties depending on the ratio of parameters to data.
- Large models have higher sample efficiency and can reach the same performance levels with less optimization steps and data points.
- The paper motivated subsequent work by OpenAI on applying scaling laws to other domains like computer vision and developing increasingly large language models like GPT-3.
This document summarizes recent research on applying self-attention mechanisms from Transformers to domains other than language, such as computer vision. It discusses models that use self-attention for images, including ViT, DeiT, and T2T, which apply Transformers to divided image patches. It also covers more general attention modules like the Perceiver that aims to be domain-agnostic. Finally, it discusses work on transferring pretrained language Transformers to other modalities through frozen weights, showing they can function as universal computation engines.
本スライドは、弊社の梅本により弊社内の技術勉強会で使用されたものです。
近年注目を集めるアーキテクチャーである「Transformer」の解説スライドとなっております。
"Arithmer Seminar" is weekly held, where professionals from within and outside our company give lectures on their respective expertise.
The slides are made by the lecturer from outside our company, and shared here with his/her permission.
Arithmer株式会社は東京大学大学院数理科学研究科発の数学の会社です。私達は現代数学を応用して、様々な分野のソリューションに、新しい高度AIシステムを導入しています。AIをいかに上手に使って仕事を効率化するか、そして人々の役に立つ結果を生み出すのか、それを考えるのが私たちの仕事です。
Arithmer began at the University of Tokyo Graduate School of Mathematical Sciences. Today, our research of modern mathematics and AI systems has the capability of providing solutions when dealing with tough complex issues. At Arithmer we believe it is our job to realize the functions of AI through improving work efficiency and producing more useful results for society.
This document summarizes a research paper on scaling laws for neural language models. Some key findings of the paper include:
- Language model performance depends strongly on model scale and weakly on model shape. With enough compute and data, performance scales as a power law of parameters, compute, and data.
- Overfitting is universal, with penalties depending on the ratio of parameters to data.
- Large models have higher sample efficiency and can reach the same performance levels with less optimization steps and data points.
- The paper motivated subsequent work by OpenAI on applying scaling laws to other domains like computer vision and developing increasingly large language models like GPT-3.
This document summarizes recent research on applying self-attention mechanisms from Transformers to domains other than language, such as computer vision. It discusses models that use self-attention for images, including ViT, DeiT, and T2T, which apply Transformers to divided image patches. It also covers more general attention modules like the Perceiver that aims to be domain-agnostic. Finally, it discusses work on transferring pretrained language Transformers to other modalities through frozen weights, showing they can function as universal computation engines.
7. 基本的な使い方(1/)
create_model 関数
◦ model_name で model を指定
◦ pretrained=True とするだけで pretrained model
が読み込まれる(初回は download される)
◦ ImageNet が基準なので入力のチャネルが 3 で
出力の次元が 1000 というのが基本
注意事項
◦ pretrained model が無い model を指定して
pretrained=Trueにしても何も言ってくれない
◦ 既に download 済な場合も何も表示されない
8. 基本的な使い方(2/)
head を置き換える
◦ 引数 num_classes を使うことで、任意の出力
次元の head に置き換えられる
◦ head は基本的に1層の全結合層
◦ head の名前等は model によってまちまちだ
が、そこは timm が勝手に処理してくれる
◦ あとは学習させるだけ。めっちゃ便利!
12. ちょっとだけ凝った使い方(4/)
自分で model を定義してみる
◦ self.backbone は timm.create_model で
head を無効化したものを使用
◦ head として非線形な全結合層を実装
◦ head の入力の次元を設定するために
num_features にアクセス
◦ Linear -> ReLU -> Drooput -> Linear