Binary Semantic Segmentation

Vladimir Iglovikov

Computer Vision Engineer at Lyft, Level5

Approach

• Q: What is the DeepHammer for binary segmentation?
• A: UNet.

UNet: strong baseline for nearly every binary image segmentation problem

Vladimir's approach

TernausNet (UNet with pre-trained VGG11) encoder. 

1. 5 folds
2. Input 1920x1280
3. HSV / grayscale augmentations
4. Cyclic Learning Rate
5. Optimizer: Adam
6. Batch size: 4
7. Pseudo Labeling

Q: Does pre-trained encoder help UNet?

A: It depends.

1. Pre-trained on 8Bit RGB will speed up convergence on 8bit RGB
2. Pre-trained on 8bit RGB will not help on 11bit images. (Satellite)

Vladimir Iglovikov, Alexey Shvets TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation

Vladimir's approach

TernausNet (UNet with pre-trained VGG11) encoder. 

Pseudo Labeling (useful at work)

1. Train: 5088
2. Public Test: 1200
3. Private Test: 3664
4. Unlabeled in test: 95200

Typically works if:

1. A lot of unlabeled data.
2. Prediction accuracy is high (in our case 0.997+)

Idea: pick the most confident predictions and add them to train data

Works well if you add more than the train set.

Alexander's approach

Had a set of GTX 1080 (not 1080 Ti) => No UNet in full HD

UNet => LinkNet (VGG encoder => Resnet encoder)

Alexander's approach

1. 5 folds, 6 models
2. LinkNet
3. Augmentations: Horizontal flips, shifts, scaling, rotations, HSV augmentations
4. Loss: BCE + 1 - Dice
5. TTA: horizontal flips
6. Optimizer: Adam, RMSProp
7. Cyclic Learning Rate
8. Hard negative mining
9. CLAHE for preprocessing

Well written fast code for data augmentations: https://github.com/asanakoy/kaggle_carvana_segmentation/blob/master/albu/src/transforms.py

Artsiom's approach

1. 7 folds, 2 models
2. Initialization: ImageNet / Random
3. Loss: Weighted BCE + 1 - Dice
4. Optimizer: SGD
5. Cyclic learning rate
6. Augmentations: translation, scaling, rotations, contrast, saturation, grayscale

Merging and ​post-processing

1. Simple average
2. Convex hull for non-confident regions
3. Thresholding at 0.5

Conclusion

• 1st out of 735
• $12,000 prize
• 10 evenings spent
• 20 GPUs used
• Full reproduction of training on one Titan Pascal X will take 90 days.
• Full reproduction of inference on one Titan Pascal X will take 13 days.
• We never met each other in person :D

Vladimir's DevBox.

Deep Learning and Crypto mining

• Blog post: http://blog.kaggle.com/2017/12/22/carvana-image-masking-first-place-interview/
• Code: https://github.com/asanakoy/kaggle_carvana_segmentation​
• Code and weights for TernausNet: https://github.com/ternaus/TernausNet​