Completed
How do we Train New Attribute Task Heads?
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Computer Vision and NLP for Multi-Task Fashion Modeling
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Attribute Modeling at Shoprunner
- 3 Overview
- 4 Why Images and Text?: Jeans
- 5 Multi-Task Learning: Karate Kid Example
- 6 Multi-Task Learning: Shoprunner Example
- 7 Example Multi-Task Network
- 8 General Training Protocols
- 9 Image Model Architecture: Centercrops
- 10 Clothing Detection RED
- 11 Clothing Segmentation R&D
- 12 Text Model Architecture: BERT
- 13 BERT Implementation
- 14 Ensemble Architecture
- 15 Expanding to New Attributes
- 16 Franken Model Process
- 17 How do we Train New Attribute Task Heads?
- 18 Multi-Dataset Multi-Task Learning
- 19 Ongoing Work
- 20 Questions?
- 21 Contact Info
