Submit Search
Upload
[DL輪読会]Taskonomy: Disentangling Task Transfer Learning
•
4 likes
•
3,379 views
Deep Learning JP
Follow
2018/07/06 Deep Learning JP: http://deeplearning.jp/seminar-2/
Read less
Read more
Technology
Report
Share
Report
Share
1 of 30
Download now
Download to read offline
Recommended
【DL輪読会】Scaling Laws for Neural Language Models
【DL輪読会】Scaling Laws for Neural Language Models
Deep Learning JP
【メタサーベイ】数式ドリブン教師あり学習
【メタサーベイ】数式ドリブン教師あり学習
cvpaper. challenge
[DL輪読会]When Does Label Smoothing Help?
[DL輪読会]When Does Label Smoothing Help?
Deep Learning JP
モデルではなく、データセットを蒸留する
モデルではなく、データセットを蒸留する
Takahiro Kubo
「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
Curriculum Learning (関東CV勉強会)
Curriculum Learning (関東CV勉強会)
Yoshitaka Ushiku
[DL輪読会]近年のオフライン強化学習のまとめ —Offline Reinforcement Learning: Tutorial, Review, an...
[DL輪読会]近年のオフライン強化学習のまとめ —Offline Reinforcement Learning: Tutorial, Review, an...
Deep Learning JP
[DL輪読会]Temporal Abstraction in NeurIPS2019
[DL輪読会]Temporal Abstraction in NeurIPS2019
Deep Learning JP
Recommended
【DL輪読会】Scaling Laws for Neural Language Models
【DL輪読会】Scaling Laws for Neural Language Models
Deep Learning JP
【メタサーベイ】数式ドリブン教師あり学習
【メタサーベイ】数式ドリブン教師あり学習
cvpaper. challenge
[DL輪読会]When Does Label Smoothing Help?
[DL輪読会]When Does Label Smoothing Help?
Deep Learning JP
モデルではなく、データセットを蒸留する
モデルではなく、データセットを蒸留する
Takahiro Kubo
「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
Curriculum Learning (関東CV勉強会)
Curriculum Learning (関東CV勉強会)
Yoshitaka Ushiku
[DL輪読会]近年のオフライン強化学習のまとめ —Offline Reinforcement Learning: Tutorial, Review, an...
[DL輪読会]近年のオフライン強化学習のまとめ —Offline Reinforcement Learning: Tutorial, Review, an...
Deep Learning JP
[DL輪読会]Temporal Abstraction in NeurIPS2019
[DL輪読会]Temporal Abstraction in NeurIPS2019
Deep Learning JP
【DL輪読会】Perceiver io a general architecture for structured inputs & outputs
【DL輪読会】Perceiver io a general architecture for structured inputs & outputs
Deep Learning JP
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Yusuke Uchida
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
SSII
[DL輪読会]ICLR2020の分布外検知速報
[DL輪読会]ICLR2020の分布外検知速報
Deep Learning JP
[DL輪読会]AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
[DL輪読会]AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
Deep Learning JP
[DL輪読会]Control as Inferenceと発展
[DL輪読会]Control as Inferenceと発展
Deep Learning JP
ConvNetの歴史とResNet亜種、ベストプラクティス
ConvNetの歴史とResNet亜種、ベストプラクティス
Yusuke Uchida
【DL輪読会】Factory: Fast Contact for Robotic Assembly
【DL輪読会】Factory: Fast Contact for Robotic Assembly
Deep Learning JP
Attentionの基礎からTransformerの入門まで
Attentionの基礎からTransformerの入門まで
AGIRobots
【DL輪読会】Mastering Diverse Domains through World Models
【DL輪読会】Mastering Diverse Domains through World Models
Deep Learning JP
深層生成モデルと世界モデル
深層生成モデルと世界モデル
Masahiro Suzuki
[DL輪読会]World Models
[DL輪読会]World Models
Deep Learning JP
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
Deep Learning JP
【DL輪読会】A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
【DL輪読会】A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
Deep Learning JP
畳み込みLstm
畳み込みLstm
tak9029
ゼロから始める深層強化学習(NLP2018講演資料)/ Introduction of Deep Reinforcement Learning
ゼロから始める深層強化学習(NLP2018講演資料)/ Introduction of Deep Reinforcement Learning
Preferred Networks
backbone としての timm 入門
backbone としての timm 入門
Takuji Tahara
Layer Normalization@NIPS+読み会・関西
Layer Normalization@NIPS+読み会・関西
Keigo Nishida
不老におけるOptunaを利用した分散ハイパーパラメータ最適化 - 今村秀明(名古屋大学 Optuna講習会)
不老におけるOptunaを利用した分散ハイパーパラメータ最適化 - 今村秀明(名古屋大学 Optuna講習会)
Preferred Networks
近年のHierarchical Vision Transformer
近年のHierarchical Vision Transformer
Yusuke Uchida
【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
Deep Learning JP
More Related Content
What's hot
【DL輪読会】Perceiver io a general architecture for structured inputs & outputs
【DL輪読会】Perceiver io a general architecture for structured inputs & outputs
Deep Learning JP
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Yusuke Uchida
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
SSII
[DL輪読会]ICLR2020の分布外検知速報
[DL輪読会]ICLR2020の分布外検知速報
Deep Learning JP
[DL輪読会]AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
[DL輪読会]AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
Deep Learning JP
[DL輪読会]Control as Inferenceと発展
[DL輪読会]Control as Inferenceと発展
Deep Learning JP
ConvNetの歴史とResNet亜種、ベストプラクティス
ConvNetの歴史とResNet亜種、ベストプラクティス
Yusuke Uchida
【DL輪読会】Factory: Fast Contact for Robotic Assembly
【DL輪読会】Factory: Fast Contact for Robotic Assembly
Deep Learning JP
Attentionの基礎からTransformerの入門まで
Attentionの基礎からTransformerの入門まで
AGIRobots
【DL輪読会】Mastering Diverse Domains through World Models
【DL輪読会】Mastering Diverse Domains through World Models
Deep Learning JP
深層生成モデルと世界モデル
深層生成モデルと世界モデル
Masahiro Suzuki
[DL輪読会]World Models
[DL輪読会]World Models
Deep Learning JP
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
Deep Learning JP
【DL輪読会】A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
【DL輪読会】A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
Deep Learning JP
畳み込みLstm
畳み込みLstm
tak9029
ゼロから始める深層強化学習(NLP2018講演資料)/ Introduction of Deep Reinforcement Learning
ゼロから始める深層強化学習(NLP2018講演資料)/ Introduction of Deep Reinforcement Learning
Preferred Networks
backbone としての timm 入門
backbone としての timm 入門
Takuji Tahara
Layer Normalization@NIPS+読み会・関西
Layer Normalization@NIPS+読み会・関西
Keigo Nishida
不老におけるOptunaを利用した分散ハイパーパラメータ最適化 - 今村秀明(名古屋大学 Optuna講習会)
不老におけるOptunaを利用した分散ハイパーパラメータ最適化 - 今村秀明(名古屋大学 Optuna講習会)
Preferred Networks
近年のHierarchical Vision Transformer
近年のHierarchical Vision Transformer
Yusuke Uchida
What's hot
(20)
【DL輪読会】Perceiver io a general architecture for structured inputs & outputs
【DL輪読会】Perceiver io a general architecture for structured inputs & outputs
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
[DL輪読会]ICLR2020の分布外検知速報
[DL輪読会]ICLR2020の分布外検知速報
[DL輪読会]AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
[DL輪読会]AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
[DL輪読会]Control as Inferenceと発展
[DL輪読会]Control as Inferenceと発展
ConvNetの歴史とResNet亜種、ベストプラクティス
ConvNetの歴史とResNet亜種、ベストプラクティス
【DL輪読会】Factory: Fast Contact for Robotic Assembly
【DL輪読会】Factory: Fast Contact for Robotic Assembly
Attentionの基礎からTransformerの入門まで
Attentionの基礎からTransformerの入門まで
【DL輪読会】Mastering Diverse Domains through World Models
【DL輪読会】Mastering Diverse Domains through World Models
深層生成モデルと世界モデル
深層生成モデルと世界モデル
[DL輪読会]World Models
[DL輪読会]World Models
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
[DL輪読会]Learning Transferable Visual Models From Natural Language Supervision
【DL輪読会】A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
【DL輪読会】A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
畳み込みLstm
畳み込みLstm
ゼロから始める深層強化学習(NLP2018講演資料)/ Introduction of Deep Reinforcement Learning
ゼロから始める深層強化学習(NLP2018講演資料)/ Introduction of Deep Reinforcement Learning
backbone としての timm 入門
backbone としての timm 入門
Layer Normalization@NIPS+読み会・関西
Layer Normalization@NIPS+読み会・関西
不老におけるOptunaを利用した分散ハイパーパラメータ最適化 - 今村秀明(名古屋大学 Optuna講習会)
不老におけるOptunaを利用した分散ハイパーパラメータ最適化 - 今村秀明(名古屋大学 Optuna講習会)
近年のHierarchical Vision Transformer
近年のHierarchical Vision Transformer
More from 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
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
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...
Deep Learning JP
【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
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
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...
Deep Learning JP
【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?
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
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 )
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...
Deep Learning JP
【DL輪読会】"Secrets of RLHF in Large Language Models Part I: PPO"
【DL輪読会】"Secrets of RLHF in Large Language Models Part I: PPO"
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 "
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
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"
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...
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 ...
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...
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...
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】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】 "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】Zero-Shot Dual-Lens Super-Resolution
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
【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】マルチモーダル LLM
【DL輪読会】マルチモーダル LLM
【 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】AnyLoc: Towards Universal Visual Place Recognition
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
【DL輪読会】Can Neural Network Memorization Be Localized?
【DL輪読会】Can Neural Network Memorization Be Localized?
【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】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】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】"Secrets of RLHF in Large Language Models Part I: PPO"
【DL輪読会】"Secrets of RLHF in Large Language Models Part I: PPO"
【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】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】"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】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】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】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】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
[DL輪読会]Taskonomy: Disentangling Task Transfer Learning
1.
DEEPLEARNINGJP [DL Papers] Taskonomy: Disentangling
Task Transfer Learning (CVPR2018) MasashiYokota, RESTAR inc. http://deeplearning.jp/ 1
2.
• 2 CBCAL
:BG B B 2 2 B : : B B • A 0 A : B : 1 A 1 :B :CB 8 , G:B . 1 C 1 : : • 1G B C B : GL B : GL C C B : : :L • /0 : G / D: J • GGD G CBCAL CB
3.
• • 3 = 36 2
4.
• 4 -
4 -2>D E 4 2 2D Segm 2D Edge4 24 2
5.
• 5 5
6.
! 6
7.
8.
• 8 6
2
9.
• 9 4 4
0 0
10.
- • 1 - 0
11.
• > 1 •
( ) () ) t: target task, s: source task Es: encoder, D: decoder, L: loss func, ft(I): grand truth
12.
• 2 F
1 2 > - 2 1 F 1 > F • 1 ES F TE 2 1 1 1
13.
( ) )
:) ) ) • 1 A 1 3
14.
) ( ( •
) ( 4 ( 1 4 )) ( s r c o • 1 !" !# g a t 1 gu t1 c L e 4
15.
) ( ( s1
s2 s3 s4 s1 1 0.8 0.5 0.9 s2 0.2 1 0.7 0.5 s3 0.5 0.3 1 0.8 s4 0.1 0.5 0.2 1 s1 s2 s3 s4 s1 1 0.2 0.5 0.1 s2 0.8 1 0.3 0.5 s3 0.5 0.7 1 0.2 s4 0.9 0.5 0.8 1 s1 s2 s3 s4 s1 1/1 0.8/ 0.2 0.5/ 0.5 0.9/ 0.1 s2 0.2/ 0.8 1/1 0.7/ 0.3 0.5/ 0.5 s3 0.5/ 0.5 0.3/ 0.7 1/1 0.8/ 0.2 s4 0.1/ 0.9 1 0.2/ 0.8 1/1 s1 s2 s3 s4 s1 1 4 1 9 s2 0.25 1 7/3 1 s3 1 3/7 1 4 s4 1/9 1 0.25 1 Source target 1 source W W 5 W 5
16.
) ( ( PE s1
0.47 s2 0.20 s3 0.25 s4 0.08 s1 s2 s3 s4 t1 0.47 0.20 0.25 0.08 t2 t3 t4 s1 s2 s3 s4 s1 1 4 1 9 s2 0.25 1 7/3 1 s3 1 3/7 1 4 s4 1/9 1 0.25 1 6 6 1 Normalize 1 Target
17.
) ( ( PE s1
0.47 s2 0.20 s3 0.25 s4 0.08 PE s1 0.47 s2 0.20 s3 0.25 s4 0.08 PE s1 0.47 s2 0.20 s3 0.25 s4 0.08 PE s1 0.47 s2 0.20 s3 0.25 s4 0.08 s1 s2 s3 s4 t1 0.47 0.20 0.25 0.08 t2 0.10 0.42 0.18 0.30 t3 0.21 0.11 0.33 0.35 t4 0.01 0.20 0.29 0.50 s1 s2 s3 s4 s1 1 4 1 9 s2 0.25 1 7/3 1 s3 1 3/7 1 4 s4 1/9 1 0.25 1 s1 s2 s3 s4 s1 1 4 1 9 s2 0.25 1 7/3 1 s3 1 3/7 1 4 s4 1/9 1 0.25 1 s1 s2 s3 s4 s1 1 4 1 9 s2 0.25 1 7/3 1 s3 1 3/7 1 4 s4 1/9 1 0.25 1 s1 s2 s3 s4 s1 1 4 1 9 s2 0.25 1 7/3 1 s3 1 3/7 1 4 s4 1/9 1 0.25 1 Target 7 1 1 Normalize target
18.
( ) )
:) ) ) • P 8 : 1 2 P ) )0 ,), (
19.
/ a e I •
1 9 /d c9 • 1 2 / k • 1 on
20.
• 0 target task AHP
21.
• V (
35 : 45 D 2 65 5 7 45 D !" # 2 65 5 • 2 65 6 3 8 U 0 ) ( TP U • ,2 2 5 – 28 2 538683 5 UG – 12:842 8 ( 2 65 6 3 8 UG – 5 ) G
22.
• 2 2
( • 2 2 2 2 • DC :E 2 )
23.
• % (
3 G G : G • 2 ) 3 G G G : G
24.
E : • 4 1 •
6 4 ( 1) 0 ( 2 2 1
25.
: • 5 .5
D [ O Q . ). • ( 2 G 5 .5 O Q G S :
26.
- - : • 2 6 6
27.
) ) )
( 7 7 7 2
28.
& & &
& N P & I E M • I 2M 8 N
29.
30.
• 2 .3 . •
6 .3 3 6 0 6 3 • 6 3 0 6 0 6 2
Download now