$$ \newcommand{\floor}[1]{\left\lfloor #1 \right\rfloor} \newcommand{\ceil}[1]{\left\lceil #1 \right\rceil} \newcommand{\N}{\mathbb{N}} \newcommand{\R}{\mathbb{R}} \newcommand{\Z}{\mathbb{Z}} \newcommand{\Q}{\mathbb{Q}} \newcommand{\C}{\mathbb{C}} \renewcommand{\L}{\mathcal{L}} \newcommand{\x}{\times} \newcommand{\contra}{\scalebox{1.5}{$\lightning$}} \newcommand{\inner}[2]{\left\langle #1 , #2 \right\rangle} \newcommand{\st}{\text{ such that }} \newcommand{\for}{\text{ for }} \newcommand{\Setcond}[2]{ \left\{\, #1 \mid #2 \, \right\}} \newcommand{\setcond}[2]{\Setcond{#1}{#2}} \newcommand{\seq}[1]{ \left\langle #1 \right\rangle} \newcommand{\Set}[1]{ \left\{ #1 \right\}} \newcommand{\set}[1]{ \set{#1} } \newcommand{\sgn}{\text{sign}} \newcommand{\halfline}{\vspace{0.5em}} \newcommand{\diag}{\text{diag}} \newcommand{\legn}[2]{\left(\frac{#1}{#2}\right)} \newcommand{\ord}{\text{ord}} \newcommand{\di}{\mathrel{|}} \newcommand{\gen}[1] \newcommand{\irr}{\mathrm{irr }} \renewcommand{\deg}{\mathrm{deg }} \newcommand{\nsgeq}{\trianglelefteq} \newcommand{\nsg}{\triangleleft} \newcommand{\argmin}{\mathrm{argmin}} \newcommand{\argmax}{\mathrm{argmax}} \newcommand{\minimize}{\mathrm{minimize}} \newcommand{\maximize}{\mathrm{maximize}} \newcommand{\subto}{\mathrm{subject\ to}} \newcommand{\DKL}[2]{D_{\mathrm{KL}}\left(#1 \di\di #2\right)} \newcommand{\ReLU}{\mathrm{ReLU}} \newcommand{\E}{\mathsf{E}} \newcommand{\V}{\mathsf{Var}} \newcommand{\Corr}{\mathsf{Corr}} \newcommand{\Cov}{\mathsf{Cov}} \newcommand{\covariance}[1]{\Cov\left(#1\right)} \newcommand{\variance}[1]{\V\left[#1\right]} \newcommand{\variancewith}[1]{\V\left[#1\right]} \newcommand{\expect}[1]{\E\left[#1\right]} \newcommand{\expectwith}[2]{\E_{#1}\left[#2\right]} \renewcommand{\P}{\mathsf{P}} \newcommand{\uniform}[2]{\mathrm{Uniform}\left(#1 \dots #2\right)} \newcommand{\gdist}[2]{\mathcal{N}\left(#1, #2\right)} $$ \everymath{\displaystyle}

Image Segmentation

Project for Bachelor's Thesis is Mathematics, comparing DL/pre-DL image segmentation methods

Total views

Thumbnail image source : Tensorflow Image segmentation1

Pre-DL Image segmentation methods

๋”ฅ๋Ÿฌ๋‹์ด ๋ณธ๊ฒฉํ™”๋˜๊ธฐ ์ด์ „์—๋Š” ์–ด๋–ค ๋ฐฉ๋ฒ•๋“ค์ด image segmentation์— ์‚ฌ์šฉ๋˜์—ˆ๋Š”์ง€ ๊ณต๋ถ€ํ–ˆ์Šต๋‹ˆ๋‹ค.

Deep Learning methods

Github Link ์—์„œ ์ฝ”๋“œ๋ฅผ ๋ชจ๋‘ ํ™•์ธํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

๊ฐ€๋ณ๊ฒŒ ๊ฐ ๋ชจ๋ธ๋“ค์„ ๋น„๊ตํ•  ๊ฒƒ์ด๋ฏ€๋กœ, ์ž‘์€ ๋ฐ์ดํ„ฐ์…‹์„ ์จ๋ณด๋ ค๊ณ  ํ•ฉ๋‹ˆ๋‹ค. Graz Univ์—์„œ ์ œ๊ณตํ•˜๋Š” ๋“œ๋ก  ํ•ญ๊ณต ์‚ฌ์ง„ ๋ฐ์ดํ„ฐ์…‹ ์„ ์ด์šฉํ•ด ๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค. ๋จผ์ € ๋ฐ์ดํ„ฐ๋ฅผ ๋กœ๋”ฉํ•  ์ค€๋น„๋ฅผ ํ•˜๊ณ , ๊ธฐ๋ณธ ์„ธํŒ…๋“ค์„ ํ•ฉ๋‹ˆ๋‹ค. ๋ชจ๋ธ์„ ๊ตฌํ˜„ํ•˜๊ณ  ๋‚˜์„œ ๋ฐ์ดํ„ฐ๋ฅผ ๋กœ๋”ฉํ•ด์„œ ํ…Œ์ŠคํŠธํ•  ์ˆ˜ ์žˆ๋„๋ก..

๋ฐ์ดํ„ฐ๊ฐ€ ๋„ˆ๋ฌด ํฌ๊ณ , ๋„ˆ๋ฌด ์ ์–ด์„œ ๋ฌธ์ œ๊ฐ€ ๋งŽ์ด ๋ฐœ์ƒํ–ˆ๊ธฐ ๋•Œ๋ฌธ์—, ๋ฐ์ดํ„ฐ๋ฅผ PASCALVOC 2012๋ฅผ ์“ฐ๊ธฐ๋กœ ๋ฐ”๊ฟจ์Šต๋‹ˆ๋‹ค.

Prep์ด ์ œ๋Œ€๋กœ ๋˜์—ˆ๋Š”์ง€ ํ™•์ธํ•˜๊ณ  ์‹ถ์Šต๋‹ˆ๋‹ค. 1-Layer CNN์—๋‹ค๊ฐ€ ์ด๋ฏธ์ง€๋ฅผ ๋จน์ด๋ฉด ์กฐ๊ธˆ์ด๋ผ๋„ Nontrivialํ•œ ๋ญ”๊ฐ€๋ฅผ ๋ฐฐ์šธ ์ˆ˜ ์žˆ์„๊นŒ์š”?

Fully Convolutional Network (FCN) ์„ ๊ณต๋ถ€ํ•˜๊ณ  ๊ตฌํ˜„ํ•ฉ๋‹ˆ๋‹ค.

U-Net์„ ๊ณต๋ถ€ํ•˜๊ณ  ๊ตฌํ˜„ํ•ฉ๋‹ˆ๋‹ค.

  • [U-Net ์ •๋ฆฌ]
  • [U-Net ๊ตฌํ˜„]

  1. Ironically, this project will use pytorch.ย โ†ฉ