SlideShare a Scribd company logo
DEEP LEARNING JP
[DL Papers] Representation Learning via Invariant Causal Mechanisms
XIN ZHANG, Matsuo Lab
http://deeplearning.jp/
書誌情報
● Representation Learning via Invariant Causal Mechanisms
● 著者:Jovana Mitrovic, Brian McWilliams, Jacob Walker, Lars Buesing, Charles Blundell
● 研究機関:DeepMind, Oct 2020(Arxiv)
● 概要
○ Contrastive Learning(CL)が上手くいっている理由を因果論で解釈する論文
○ データ拡張に注目して、画像のStyleがdowntasksに影響しないため(仮説のもとで)、
事前学習のTaskにおいても影響しないようにすれば良い
○ CLのLoss関数に、Styleによる影響を抑える制限を加える
○ 学習した表現の良さは、Baselineと同等だが、ロバスト性や汎化性が優れている
2
Introduction:Representation Learning
Representation Learning via Invariant Causal Mechanisms
BYOL
Representation Learning via Invariant Causal Mechanisms
Target Network
Reprensentation(Self-supervised) learningはMIだけでは解釈でき
ない
[DL輪読会]相互情報量最大化による表現学習、岩澤先生より
Representation Learning via Invariant Causal Mechanisms
Alignment and Uniformity on the Hypersphere
Proposed method:RELIC
議論:仮説に異論はあるかもだが、(自分は)納得
できる
Representation Learning via Invariant Causal Mechanisms
Assumptions:
1. 画像(X)はコンテンツ(C)とスタイル(S)から生
成される
2. Cのみが下流タスク(Y_1...)に影響する
3. CとSはお互いに独立
理論上:Instance Classificationは最も難しいタス
クであり、これさえできれば、下流のどんなタス
クに対しても解けるはず。(証明付き)
自分の理解:個々の分類よりも細かい分類がない
Representation Learning via Invariant Causal Mechanisms
事前学習のタスク(Y^R)で表現f(X)を学習する。
Y^RはInstance Classification(入力画像と他の画像
と区別する)。
Representation Learning via Invariant Causal Mechanisms
Y^Rでf(X)で事前学習する際に、Sの変化による影
響を無くすように制限をかける。
Relationship between RELIC and other methods.
EXPERIMENTS
Linear evalution:線形分類のしやすさで表現の良さを評価
Fischer’s linear discriminant ratio(Friedman et al., 2009)
大きければ大きいほど、線形分離しやすい。
SimCLRより良いことがわかる。
Linear evalution:ImageNetで線形評価を行う(スタンダード)
2種類のArchitectureで、それぞれSOTAと同等程度な精度
- ただし、InfoMin AugとSwAVはより強力データ拡張を使
った。(5%ほど精度上げられるもの)
議論:より強力データ拡張を使った結果は気になる
ImageNet-R:ImageNetの画像を拡張したデータセット。
Top-1 Error%がSimCLRより低く、Supervisedより高い。
Robustness and Generalization
Robustness and Generalization
ImageNet-C:ImageNetの画像に異なる程度な異なるノイズを
加えたデータセット。
複数のError率では、SimCLRとBYOLより低い(良い)。
Reinforcement Learning
R2D2の入力画像に対する拡張で精度を比較。
(R2D2:RNN+DQN+Tricksで大幅当時のSOTAを超えた。)
感想:RLは普段しない実験で新鮮。CURLよりも良かった。
Conclusion
Related Work
A causal view of compositional zero-shot
recognition(NIPS 2020)
Self-Supervised Learning with Data
Augmentations Provably Isolates Content
from Style(Jun 2021)
ContentがStyleに影響する!を仮定する
まとめ:
- Self-supervised learning(Contrastive Learning)を因果の枠組みで解釈してみた研究。
- 特徴は、RELIC Lossが必要であることをを因果論?の数式で証明した(Appendixを参考)。
感想:
- Contrastive Learningの新しい手法がどんどん提案されているに対して、その理論解析の研究が少な
い(追いついていない)。
- 実装公開してほしい。
Ad

More Related Content

What's hot (20)

「世界モデル」と関連研究について
「世界モデル」と関連研究について「世界モデル」と関連研究について
「世界モデル」と関連研究について
Masahiro Suzuki
 
グラフニューラルネットワーク入門
グラフニューラルネットワーク入門グラフニューラルネットワーク入門
グラフニューラルネットワーク入門
ryosuke-kojima
 
強化学習 DQNからPPOまで
強化学習 DQNからPPOまで強化学習 DQNからPPOまで
強化学習 DQNからPPOまで
harmonylab
 
Transformer メタサーベイ
Transformer メタサーベイTransformer メタサーベイ
Transformer メタサーベイ
cvpaper. challenge
 
強化学習アルゴリズムPPOの解説と実験
強化学習アルゴリズムPPOの解説と実験強化学習アルゴリズムPPOの解説と実験
強化学習アルゴリズムPPOの解説と実験
克海 納谷
 
【DL輪読会】Scaling Laws for Neural Language Models
【DL輪読会】Scaling Laws for Neural Language Models【DL輪読会】Scaling Laws for Neural Language Models
【DL輪読会】Scaling Laws for Neural Language Models
Deep Learning JP
 
実装レベルで学ぶVQVAE
実装レベルで学ぶVQVAE実装レベルで学ぶVQVAE
実装レベルで学ぶVQVAE
ぱんいち すみもと
 
【DL輪読会】Contrastive Learning as Goal-Conditioned Reinforcement Learning
【DL輪読会】Contrastive Learning as Goal-Conditioned Reinforcement Learning【DL輪読会】Contrastive Learning as Goal-Conditioned Reinforcement Learning
【DL輪読会】Contrastive Learning as Goal-Conditioned Reinforcement Learning
Deep Learning JP
 
StyleGAN解説 CVPR2019読み会@DeNA
StyleGAN解説 CVPR2019読み会@DeNAStyleGAN解説 CVPR2019読み会@DeNA
StyleGAN解説 CVPR2019読み会@DeNA
Kento Doi
 
[DL輪読会]Wasserstein GAN/Towards Principled Methods for Training Generative Adv...
[DL輪読会]Wasserstein GAN/Towards Principled Methods for Training Generative Adv...[DL輪読会]Wasserstein GAN/Towards Principled Methods for Training Generative Adv...
[DL輪読会]Wasserstein GAN/Towards Principled Methods for Training Generative Adv...
Deep Learning JP
 
【DL輪読会】The Forward-Forward Algorithm: Some Preliminary
【DL輪読会】The Forward-Forward Algorithm: Some Preliminary【DL輪読会】The Forward-Forward Algorithm: Some Preliminary
【DL輪読会】The Forward-Forward Algorithm: Some Preliminary
Deep Learning JP
 
最適輸送の解き方
最適輸送の解き方最適輸送の解き方
最適輸送の解き方
joisino
 
強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)
強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)
強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)
Shota Imai
 
【DL輪読会】Scaling laws for single-agent reinforcement learning
【DL輪読会】Scaling laws for single-agent reinforcement learning【DL輪読会】Scaling laws for single-agent reinforcement learning
【DL輪読会】Scaling laws for single-agent reinforcement learning
Deep Learning JP
 
【DL輪読会】Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
【DL輪読会】Diffusion Policy: Visuomotor Policy Learning via Action Diffusion【DL輪読会】Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
【DL輪読会】Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
Deep Learning JP
 
報酬設計と逆強化学習
報酬設計と逆強化学習報酬設計と逆強化学習
報酬設計と逆強化学習
Yusuke Nakata
 
【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ
Deep Learning JP
 
全力解説!Transformer
全力解説!Transformer全力解説!Transformer
全力解説!Transformer
Arithmer Inc.
 
[DL輪読会]NVAE: A Deep Hierarchical Variational Autoencoder
[DL輪読会]NVAE: A Deep Hierarchical Variational Autoencoder[DL輪読会]NVAE: A Deep Hierarchical Variational Autoencoder
[DL輪読会]NVAE: A Deep Hierarchical Variational Autoencoder
Deep Learning JP
 
[DL輪読会]Disentangling by Factorising
[DL輪読会]Disentangling by Factorising[DL輪読会]Disentangling by Factorising
[DL輪読会]Disentangling by Factorising
Deep Learning JP
 
「世界モデル」と関連研究について
「世界モデル」と関連研究について「世界モデル」と関連研究について
「世界モデル」と関連研究について
Masahiro Suzuki
 
グラフニューラルネットワーク入門
グラフニューラルネットワーク入門グラフニューラルネットワーク入門
グラフニューラルネットワーク入門
ryosuke-kojima
 
強化学習 DQNからPPOまで
強化学習 DQNからPPOまで強化学習 DQNからPPOまで
強化学習 DQNからPPOまで
harmonylab
 
Transformer メタサーベイ
Transformer メタサーベイTransformer メタサーベイ
Transformer メタサーベイ
cvpaper. challenge
 
強化学習アルゴリズムPPOの解説と実験
強化学習アルゴリズムPPOの解説と実験強化学習アルゴリズムPPOの解説と実験
強化学習アルゴリズムPPOの解説と実験
克海 納谷
 
【DL輪読会】Scaling Laws for Neural Language Models
【DL輪読会】Scaling Laws for Neural Language Models【DL輪読会】Scaling Laws for Neural Language Models
【DL輪読会】Scaling Laws for Neural Language Models
Deep Learning JP
 
【DL輪読会】Contrastive Learning as Goal-Conditioned Reinforcement Learning
【DL輪読会】Contrastive Learning as Goal-Conditioned Reinforcement Learning【DL輪読会】Contrastive Learning as Goal-Conditioned Reinforcement Learning
【DL輪読会】Contrastive Learning as Goal-Conditioned Reinforcement Learning
Deep Learning JP
 
StyleGAN解説 CVPR2019読み会@DeNA
StyleGAN解説 CVPR2019読み会@DeNAStyleGAN解説 CVPR2019読み会@DeNA
StyleGAN解説 CVPR2019読み会@DeNA
Kento Doi
 
[DL輪読会]Wasserstein GAN/Towards Principled Methods for Training Generative Adv...
[DL輪読会]Wasserstein GAN/Towards Principled Methods for Training Generative Adv...[DL輪読会]Wasserstein GAN/Towards Principled Methods for Training Generative Adv...
[DL輪読会]Wasserstein GAN/Towards Principled Methods for Training Generative Adv...
Deep Learning JP
 
【DL輪読会】The Forward-Forward Algorithm: Some Preliminary
【DL輪読会】The Forward-Forward Algorithm: Some Preliminary【DL輪読会】The Forward-Forward Algorithm: Some Preliminary
【DL輪読会】The Forward-Forward Algorithm: Some Preliminary
Deep Learning JP
 
最適輸送の解き方
最適輸送の解き方最適輸送の解き方
最適輸送の解き方
joisino
 
強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)
強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)
強化学習の基礎と深層強化学習(東京大学 松尾研究室 深層強化学習サマースクール講義資料)
Shota Imai
 
【DL輪読会】Scaling laws for single-agent reinforcement learning
【DL輪読会】Scaling laws for single-agent reinforcement learning【DL輪読会】Scaling laws for single-agent reinforcement learning
【DL輪読会】Scaling laws for single-agent reinforcement learning
Deep Learning JP
 
【DL輪読会】Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
【DL輪読会】Diffusion Policy: Visuomotor Policy Learning via Action Diffusion【DL輪読会】Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
【DL輪読会】Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
Deep Learning JP
 
報酬設計と逆強化学習
報酬設計と逆強化学習報酬設計と逆強化学習
報酬設計と逆強化学習
Yusuke Nakata
 
【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ
Deep Learning JP
 
全力解説!Transformer
全力解説!Transformer全力解説!Transformer
全力解説!Transformer
Arithmer Inc.
 
[DL輪読会]NVAE: A Deep Hierarchical Variational Autoencoder
[DL輪読会]NVAE: A Deep Hierarchical Variational Autoencoder[DL輪読会]NVAE: A Deep Hierarchical Variational Autoencoder
[DL輪読会]NVAE: A Deep Hierarchical Variational Autoencoder
Deep Learning JP
 
[DL輪読会]Disentangling by Factorising
[DL輪読会]Disentangling by Factorising[DL輪読会]Disentangling by Factorising
[DL輪読会]Disentangling by Factorising
Deep Learning JP
 

More from Deep Learning JP (20)

【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
Deep Learning JP
 
【DL輪読会】事前学習用データセットについて
【DL輪読会】事前学習用データセットについて【DL輪読会】事前学習用データセットについて
【DL輪読会】事前学習用データセットについて
Deep Learning JP
 
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
Deep Learning JP
 
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
Deep Learning JP
 
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
Deep Learning JP
 
【DL輪読会】マルチモーダル LLM
【DL輪読会】マルチモーダル LLM【DL輪読会】マルチモーダル LLM
【DL輪読会】マルチモーダル LLM
Deep Learning JP
 
【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
 【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo... 【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
Deep Learning JP
 
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
Deep Learning JP
 
【DL輪読会】Can Neural Network Memorization Be Localized?
【DL輪読会】Can Neural Network Memorization Be Localized?【DL輪読会】Can Neural Network Memorization Be Localized?
【DL輪読会】Can Neural Network Memorization Be Localized?
Deep Learning JP
 
【DL輪読会】Hopfield network 関連研究について
【DL輪読会】Hopfield network 関連研究について【DL輪読会】Hopfield network 関連研究について
【DL輪読会】Hopfield network 関連研究について
Deep Learning JP
 
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
Deep Learning JP
 
【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...
【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...
【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...
Deep Learning JP
 
【DL輪読会】"Language Instructed Reinforcement Learning for Human-AI Coordination "
【DL輪読会】"Language Instructed Reinforcement Learning  for Human-AI Coordination "【DL輪読会】"Language Instructed Reinforcement Learning  for Human-AI Coordination "
【DL輪読会】"Language Instructed Reinforcement Learning for Human-AI Coordination "
Deep Learning JP
 
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
Deep Learning JP
 
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
Deep Learning JP
 
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
Deep Learning JP
 
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
Deep Learning JP
 
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
Deep Learning JP
 
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
Deep Learning JP
 
【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...
【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...
【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...
Deep Learning JP
 
【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
Deep Learning JP
 
【DL輪読会】事前学習用データセットについて
【DL輪読会】事前学習用データセットについて【DL輪読会】事前学習用データセットについて
【DL輪読会】事前学習用データセットについて
Deep Learning JP
 
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
Deep Learning JP
 
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
Deep Learning JP
 
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
Deep Learning JP
 
【DL輪読会】マルチモーダル LLM
【DL輪読会】マルチモーダル LLM【DL輪読会】マルチモーダル LLM
【DL輪読会】マルチモーダル LLM
Deep Learning JP
 
【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
 【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo... 【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
Deep Learning JP
 
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
Deep Learning JP
 
【DL輪読会】Can Neural Network Memorization Be Localized?
【DL輪読会】Can Neural Network Memorization Be Localized?【DL輪読会】Can Neural Network Memorization Be Localized?
【DL輪読会】Can Neural Network Memorization Be Localized?
Deep Learning JP
 
【DL輪読会】Hopfield network 関連研究について
【DL輪読会】Hopfield network 関連研究について【DL輪読会】Hopfield network 関連研究について
【DL輪読会】Hopfield network 関連研究について
Deep Learning JP
 
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
Deep Learning JP
 
【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...
【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...
【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...
Deep Learning JP
 
【DL輪読会】"Language Instructed Reinforcement Learning for Human-AI Coordination "
【DL輪読会】"Language Instructed Reinforcement Learning  for Human-AI Coordination "【DL輪読会】"Language Instructed Reinforcement Learning  for Human-AI Coordination "
【DL輪読会】"Language Instructed Reinforcement Learning for Human-AI Coordination "
Deep Learning JP
 
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
Deep Learning JP
 
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
Deep Learning JP
 
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
Deep Learning JP
 
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
Deep Learning JP
 
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
Deep Learning JP
 
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
Deep Learning JP
 
【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...
【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...
【DL輪読会】VIP: Towards Universal Visual Reward and Representation via Value-Impl...
Deep Learning JP
 
Ad

[DL輪読会]representation learning via invariant causal mechanisms