Sitemap
Nerd For Tech

NFT is an Educational Media House. Our mission is to bring the invaluable knowledge and experiences of experts from all over the world to the novice. To know more about us, visit https://www.nerdfortech.org/.

Follow publication

Review — EncNet: Context Encoding for Semantic Segmentation (Semantic Segmentation)

6 min readMay 2, 2021

--

Narrowing the list of probable categories based on scene context makes labeling much easier.
@ Medium)

Outline

1. Context Encoding Module

Context Encoding Module & Semantic Encoding Losses (SE-loss)

1.1. Overall Architecture

1.2. Encoding Layer (Proposed by Deep TEN)

Encoding Layer (Deep Ten). In this paper, descriptors are the input feature maps

1.3. Feature Map Attention

2. Semantic Encoding Losses

Dilation strategy and losses

3. Semantic Segmentation Results

3.1. Ablation Study on PASCAL-Context

Ablation Study on PASCAL-Context dataset
The effect of weights of SE-loss α
The effect of number of codewords K

3.2. Results on PASCAL-Context

Segmentation results on PASCAL-Context dataset

3.3. Results on PASCAL VOC 2012

Results on PASCAL VOC 2012 testing set

3.4. Results on ADE20K

Segmentation results on ADE20K validation set
Result on ADE20K test set

4. Image Classification Results

Comparison of model depth, number of parameters (M), test errors (%) on CIFAR-10

--

--

Nerd For Tech
Nerd For Tech

Published in Nerd For Tech

NFT is an Educational Media House. Our mission is to bring the invaluable knowledge and experiences of experts from all over the world to the novice. To know more about us, visit https://www.nerdfortech.org/.

Sik-Ho Tsang
Sik-Ho Tsang

Written by Sik-Ho Tsang

PhD, Researcher. I share what I learn. :) Linktree: https://linktr.ee/shtsang for Twitter, LinkedIn, etc.

No responses yet