Purpose
Common Techniques - intr Star Dist
Regression
Network Architecture
Loss
Disadv
general ideas - any shape can be modeled as a collection of gaussians
memory advantage
some other advantages ( we will talk abt in next slides)
1. Estimation of Distance parameters from Masks
2. Training
3. Non Maxima + Inference
1. IOU loss
2. Equations ( c and t)
3. predicts 6 parameters
4. Negative, Unormalized GMM
5. UpperBound - best we can get
3 figures, IOU, StarDist (64, 128, 256)
1. Elephant
2. Potato
3. Fingers
(table - 3 rows, 4 cols)
1. re-explain stardist loss, architecture drawing
2. explain our strategy
3. talk about distance of gaussians (our loss), also KL divergence
4. our t and c are know, so we only predict gaussian parameters and compare GMMs
1. Stardist NMS
2. Our NMS (L2 loss, IOU loss)
1. Datasets 1 and 2
2. mention some steps
1. re-explain stardist loss, architecture drawing
2. explain our strategy
3. talk about distance of gaussians (our loss)