Completed
Key Idea: "convolutional-ization"
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Region Mutual Information Loss for Semantic Segmentation
Automatically move to the next video in the Classroom when playback concludes
- 1 tl;dr / one line summary
- 2 Sections
- 3 Semantic Segmentation
- 4 Key Idea: "convolutional-ization"
- 5 Key Idea: Encoder-decoder architecture
- 6 Key Idea #1: Convolutionalization with "à trous convolutions"
- 7 Key Idea #2: CRF Post-Processing
- 8 Key Idea: Multi-Scale Features
- 9 Key Idea: Deeper with à trous convolutions
- 10 Key Idea: À trous Spatial Pyramid Pooling
- 11 DeepLabv3+: Failure Cases
- 12 Motivation for Region Mutual Information Loss
- 13 Mutual Information: Entropy View
- 14 Mutual Information: Probability View
- 15 Overall Loss Function
- 16 Experimental Setup
- 17 Datasets
- 18 Results: PASCAL VOC 2012
- 19 Ablation Studies: PASCAL VOC 2012
