Home page

Deconstructing Deep Learning + ╬┤eviations

Drop me an email | RSS feed link : Click
Format : Date | Title
  TL; DR

Total posts : 78

View My GitHub Profile


Index page

LightSeg (only notes for now)

[36] LightSeg (only notes for now) - Emara, T., Abd El Munim, H. E., & Abbas, H. M. (2019, December). LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation. In 2019 Digital Image Computing: Techniques and Applications (DICTA) (pp. 1-7). IEEE. Link

(P.S. This was done for an internship so is a bit more formal than usual)

Notes

TL;DR -> Faster Semantic Segmentation with a modified ASPP module(from the DeepLab paper) + MobileNetV2

Objective

Modules used

Atrous -> Dilated conv

- Decrease receptive field
- Upsample by adding 0s b/w two filter vals along spatial dimensions with a dilation factor
- Note for Pytorch -> Conv2d has dilation as a param

ASPP

- Take feature map -> Add 4 parallel atrous convs with different rates

Deeper Atrous Spatial Pooling(DASPP)

- Take ASPP
- Add 3x3 convs after 3x3 atrous convs

Depthwise separable conv

- Replace normal convs
- Split input and output into channels
- Convolve pointwise
- Note for Pytorch -> Add groups = no of in_channels in Conv2d

Residuals

- Take residual/skip connections 
  - H(X) = F(X) + X  ; H(X) is output; F(X) is residual  ; X is input feature map
- Long -> Across larger no of layers
- Short -> Smaller no of layers (as memory units)
- Fuse them both 
- Use 1x1 convs
- End up with richer features

Encoder

- MobileNetV2 with output stride of 32

Decoder

- DeepLabv3+ decoder with ASPP modified to DASPP

Whats new

Misc training info

Results (mIOU)