issues
search
JisuHann
/
One-day-One-paper
Review paper
3
stars
0
forks
source link
ProDA: Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
#42
Open
JisuHann
opened
2 years ago
JisuHann
commented
2 years ago
ProDA: Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
Problem of self-training
Pseudo labels are noisy
The target features are dispersed due to the discrepancy between source and target domains.
Idea
focus on Representative prototypes, the feature centroids of classes
Exploit the feature distances from prototypes that provide richer information than mere prototypes
Estimate the likelihood of pseudo labels to
facilitate online correction
in the course of training
rectify the pseudo labels by estimating the class-wise likelihoods according to its relative feature dis- tances to all class prototypes
propose to align soft pro- totypical assignments for different views of the same target, which produces a more compact target feature space.
Distilling the already learned knowledge to a self-supervised pertained model further boosts the performance
ProDA: Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
Problem of self-training
Idea