Advances in Transfer Learning MultiTask Learning Presenting Niv
- Slides: 55
Advances in Transfer Learning & Multi-Task Learning Presenting: Niv Granot, Lior Yariv
Human-Brain Aspect • We have an inherent ability to transfer knowledge across tasks: • Know how to throw a ball Learn how to play basketball • Know math and statistics Learn machine learning • We naturally combine tasks to learn better • Learn how to read and write simultaneously • Learn Deep Learning and Computer Vision
Transfer Learning Tasks Relation in Deep Learning Multi-Task Learning
Coming to Solve a New Task Traditional Learning from scratch VS Transfer Learning Use learned and related tasks
Key Motivation for Transfer Learning • Deep-Learning Need a whole lot of (labeled) data! • Why not just use what we already know? Extracted features contain valuable information!
What is Transfer Learning? • Take a network trained on a source domain for a source task • Adapt it for the target domain to solve a new target task
Two Main Scenarios: • Different task, same domain: • Different label space • Completely different task • Different domain, same task: • Different feature space • Different distribution
Taskonomy: Disentangling Task Transfer Learning Amir Zamir, Alexander Sax, William Shen, Leonidas Guibas, Jitendra Malik, Silvio Savarese Best Paper CVPR 2018
Which Visual Tasks Can we Transfer? • Which tasks can be transferred? Need some relation!
Which Visual Tasks Can we Transfer? • Which tasks can be transferred? Need some relation! • Are computer vision tasks related? Input Image Depth Estimation Surface Normals Can we trust our intuition? Moreover- How strong is this relationship? How is it useful?
Taskonomy = Task Taxonomy Modeling the structure of space of visual tasks: • Existence of (nontrivial? ) relationships • First and higher order dependencies • Measurements of the relations • Reduce demand for labeled data Efficient Transfer Learning !
Taskonomy: Dig Into Details • Fully computational method for quantifying task relationships • Focus on Supervised tasks • Task Bank: 26 semantic, 2 D, 3 D task • Data Set: - 4 million real images - Annotated for every task • Objective: Maximize collective performance While minimizing the used supervision
Taskonomy: Modeling 1. Task-specific Modeling 2. Transfer Modeling 3. Task Affinity Normalization 4. Compute Taxonomy
1. Task-specific Modeling • Train a fully supervised network for each task • Encoder-Decoder architecture (homogeneous) • Freeze their weights
1. Task-specific Modeling
Taskonomy: Modeling 1. Task-specific Modeling 2. Transfer Modeling 3. Task Affinity Normalization 4. Compute Taxonomy
2. Transfer Modeling • Given a representation from the source task encoder • Train a small readout (decoder) for the target task • The performance determine the task affinity
2. Transfer Modeling • First order: All source-target combinations • Higher-Order: • Multiple source tasks • Receive multiple representations in the input
Taskonomy: Modeling 1. Task-specific Modeling 2. Transfer Modeling 3. Task Affinity Normalization 4. Compute Taxonomy
3. Normalization • Have affinity matrix of transferability across tasks • Tasks live in different spaces • Need normalization!
Taskonomy: Modeling 1. Task-specific Modeling 2. Transfer Modeling 3. Task Affinity Normalization 4. Compute Taxonomy
4. Compute Taxonomy • Given: Normalized task affinity matrix • Goal: Taxonomical structure • Optimal subgraph selection • Maximize the performance for all tasks • Constraint of source budget • Outcomes: • What are best source tasks • Best sources for each target • Solve a novel task with little data
Taskonomy: Modeling 1. Task-specific Modeling 2. Transfer Modeling 3. Task Affinity Normalization 4. Compute Taxonomy
Taskonomy: Experiments • 26 Task-Specific Networks • ~3000 Transfer Networks • Transfer training data: 8 x – 120 x less • 47, 829 GPU hours
Taskonomy: Results • Live API
Break
Two Main Scenarios: • Different task, same domain: • Different label space • Completely different task • Different domain, same task: • Different feature space • Different distribution
Partial Transfer Learning with Selective Adversarial Networks Zhangjie Cao, Mingsheng Long, Jianmin Wang, Michael I. Jordan CVPR 2018
Domain Adaptation • Assume: Same label space, different feature distributions • Learning: Domain-invariant feature representations • The classifier learned on source task is used for the target task
Partial Transfer Learning •
How to Solve it ? What happens if we apply domain adaptation ? Negative Transfer Matching the whole source and target domains may perform worse than using original classifier!
Main Goals • Avoid negative transfer Selecting out the outlier classes • Promote positive learning Adapting the shared label space
Successful method for Domain Adaptation: Domain Adversarial Networks Prone to negative transfer!
Selective Adversarial Networks (SAN) Align shared classes Distribution Select outlier classes Alleviates negative transfer Promotes positive transfer
SAN - Architecture x Feature Extractor Classifier Discrim-1 Discrim-k
SAN - Loss • x Cls FE Discr 1 Discrk
Partial Transfer Leaning with SAN Method Image. Net 1 K Caltech 84 Caltech 256 Image. Net 84 Alex. Net 52. 37 47. 35 Rev. Grad – Domain Adverserial Learning 51. 34 47. 02 SAN-selective 66. 78 51. 25 SAN-entropy 55. 27 52. 31 SAN 68. 45 55. 61
Partial Transfer Leaning with SAN 2 D Projection of bottleneck representations
Partial Transfer Leaning with SAN 2 D Projection of bottleneck representations Source classes Target classes
Transfer Learning Tasks Relation in Deep Learning Multi-Task Muli-Task Learning
Multi Task Learning (MTL)
Motivation – Inductive Bias
How to Solve MTL? •
Multi-Task Learning as Multi. Objective Optimization Ozan Sener, Vladlen Koltun NIPS 2018
Multi Objective Optimization • Find Pareto-optimal solution • Not dominated by any other Can be solved by - Multiple Gradient Descent Algorithm (MGDA)
MGDA
Issues with Optimization Problem
Issues with Optimization Problem
Multi. Mnist • Classify two digits in a single image: • Task L – Classify upper-left digit • Task R – Classify lower-right digit
Multi. Mnist Results
celeb. A
celeb. A Each attribute Binary classification task 40 -way MTL Method Single Task Uniform Scaling Kendall et al. 2018 Average Error 8. 77 9. 62 9. 53 Grad. Norm Multi-Objective Optimization 8. 44 8. 25
Scene Understanding Semantic Segmentation Instance Segmentation Depth Estimation
Scene Understanding Results (2 D Projections) Y-axis: Depth Estimation X-axis: Semantic Segmentation Y-axis: Instance Segmentation X-axis: Semantic Segmentation
Questions ?
- Chapter 17 section 2 the axis advances
- Taly payroll
- Advances in technology during wwii
- Chapter 9 intellectual development of infants
- Advances in real time rendering
- Photodesintegration
- Short term loans and advances
- Opto-electronic advances
- Recent advances in ceramics
- Irac norms
- Lurbinectedin posologie
- Advances in memory technology
- Self-taught learning: transfer learning from unlabeled data
- A disturbance that transfers energy is called
- The total exterior of a business includes the entranceways
- How to set up trays and trolleys in a room service
- Name of presenting organization meaning
- Ways of presenting information
- Format penyajian berita radio
- Types of brow presentation
- A chemist shorthand way of
- Presenting insights and findings using written reports
- Presenting another person's language or ideas as one's own.
- A chemists shorthand way of representing chemical reaction
- Is any paid form of nonpersonal presentation
- Ocar structure
- Research project proposal presentation
- Presentation and data response meaning
- Presenting problem
- Presenting the product
- Presenting complaints of hypertension
- Review writing structure
- Thank you, ladies
- Definisi report text
- Death of cleopatra edmonia lewis
- Additional comments uc application
- Organizing qualitative data
- What are the principles in presenting appetizer
- Global, patchwork, and incremental are forms of
- Anna neary
- Presenting research findings
- The act of presenting someone else's work as your own is
- Lie presentation position attitude
- Presenting complaint
- Name of presenting organization
- Plating presenting poultry dishes
- Presenting complaint
- Organizing qualitative data
- Cuadro comparativo e-learning m-learning b-learning
- Formal discipline theory of transfer of learning
- Transductive learning for unsupervised text style transfer
- Transductive transfer learning
- Lateral transfer of learning
- Transfer of learning theory
- Transfer of learning theory
- Heterogeneous transfer learning