๐Ÿข ETRI (2024.01.11)

๐Ÿ“Œ 01.10-TODO List:

1. ๋…ผ๋ฌธ review: A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data
โˆ™ Source free Domain Adaptive Object Detection (์ •๋ฆฌ๋Š” ์™„๋ฃŒ, ํ†บ์•„๋ณด๊ธฐ ํ•„์š”โ—๏ธ)
์•„ ๊ทธ๋ฆฌ๊ณ  pseudo labeling in FN Simulation์—์„œ Detection์—์„œ TN์–˜๊ธฐ๊ฐ€ ๋‚˜์™”๋‹ค.
Detection์—์„œ๋Š” TN์ด ์•ˆ์“ฐ์ธ๋‹ค๊ณ  ์•Œ๊ณ ์žˆ์–ด์„œ ์ด์— ๋Œ€ํ•ด์„œ๋„ ์ข€ ์•Œ์•„๋ด์•ผํ•œ๋‹ค.

โˆ™ Experiments (2๋ฒˆ์งธ๋กœ ๋งŽ์Œ - ๋ชฉ)


2. ์ฃผ์ค‘์— ํ•  ๊ฒƒ: Deep Learning 2024(Bishop)-Chapter 2 ์ฝ๊ณ  ๊ณต๋ถ€ํ•˜๊ธฐ
โˆ™ 2.1  The Rule of Probability
โˆ™ 2.2  Probability Densities
โˆ™ 2.3  The Gaussian Distribution
โˆ™ 2.4  Transformation of Densities
โˆ™ 2.5  Information Theory 
โˆ™ 2.6. Bayesian Probabilites

A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data | Proceedings of the AAAI Conference o

ojs.aaai.org

 

 
 

 
 

๐Ÿš ์ถœ๊ทผ! (8:10 - 8:25)

๊ทธ๋ƒฅ 7์‹œ์— ์•Œ๋žŒ ๋งž์ถฐ๋ฒ„๋ ธ๋‹ค ใ…‹ใ…‹ใ…‹
๊ทธ๋ž˜๋„ ๋ฐฅ์€ ๋ง›์žˆ๊ฒŒ ์•ผ๋ฌด์ง€๊ฒŒ ๋จน๊ณ ์™”๋‹ค ํžˆํžˆ๐Ÿคฃ
์ถœํ‡ด๊ทผ์€ ์…”ํ‹€๋ฒ„์Šค๊ฐ€ ์—ญ์‰ฌ ์ œ์ผ ๋น ๋ฅธ๊ฑฐ ๊ฐ™๋‹ค. (Shortest Path Algorithm?)
 
 
 
 
 

๐Ÿ“– ๊ณต๋ถ€! (8:30-12:00)

์…”ํ‹€๋ฒ„์Šค ํƒ€๊ณ  ์˜ค๋Š”๊ฒŒ ์ผ์ฐ๊ณต๋ถ€ํ•  ์ˆ˜ ์žˆ์–ด์„œ ์ด๋“์ธ๊ฑฐ ๊ฐ™๋‹ค.
์ด์ œ ๋‚จ์€ ํ• ์ผ:
โˆ™ ๋…ผ๋ฌธ review: Experiments
โˆ™ Deep Learning(Bishop 2024): Chapter 2 ์ด๋‹ค.
    2.5  Information Theory 
 
 
 
 
 
 
 
 

๐Ÿš ๋ฐฅ์ด๋‹ค ๋ฐฅ! (12:30~13:00)

๋งˆ์ฐฌ๊ฐ€์ง€๋กœ ๋™ํŽธ์ œ(ํ•œ์‹): ๋ฐ๋ฆฌ์•ผ๋ผ ๋‹ญ --> ๋ฉ์–ด๋ฆฌ ์ปค์„œ ์ข‹์•˜๋‹ค.

 
 
 
 
 
 

 
 

๐Ÿ“– ๊ณต๋ถ€! (13:30-18:00)

๋…ผ๋ฌธ review ๊ณ„์† ์ง„ํ–‰. ์˜ค๋Š˜์€ ExperimentsํŒŒํŠธ๋ฅผ ์ฝ์—ˆ๋‹ค.
Experiments๋ผ ๊ทธ๋Ÿฐ์ง€ ๊ทธ๋ƒฅ ์‹คํ—˜ ๋ฐฉ๋ฒ•๋‚ด์šฉ๋“ค๋งŒ ๋‚˜์™€์„œ ์‰ฝ๊ฒŒ์‰ฝ๊ฒŒ ์ฝ์€ ๊ฒƒ ๊ฐ™๋‹ค.
์—ญ์‹œ Main Idea๋ถ€๋ถ„ ๋นผ๊ณ ๋Š” ๋‚˜๋จธ์ง€๋Š” ๊ทธ๋ ‡๊ฒŒ ๋จธ๋ฆฌ์“ธ ์ผ ์—†๋Š” ๋Š๋‚Œ์ด๋‹ค.
 
Abstract -> ์—ฌ๊ธฐ ๋‚ด์šฉ์€ ๋ฌด์กฐ๊ฑด ์ˆ™์ง€ํ•ด์•ผ๋จ
Introduction -> Abstract ์กฐ๊ธˆ ๊ตฌ์ฒดํ™” + Main Idea preview
Main Idea: ํž˜ ๋นก์ฃผ๊ณ  ์ฝ์–ด์•ผํ•จ ใ„นใ…‡...
etc.ใ…‹ใ…‹ใ…‹

 
 

 

๐Ÿš ํ‡ด๊ทผ! (18:30 - 19:00)

ํ‡ด๊ทผ์ด ์ œ์ผ ์ข‹๋‹ค๋Š” ์ง์žฅ์ธ์˜ ๋ง์— ๊ณต๊ฐ์ด ์ ์ ๋œ๋‹คใ…‹ใ…‹ใ…‹
์•„์นจ์ถœ๊ทผ๋•Œ๋ฌธ์— ๊ทธ๋ƒฅ ์กธ๋ฆฌ๋‹คใ…‹ใ…‹ ํ”ผ๊ณค๐Ÿฉธํ•˜๊ณ ใ… ใ… 


 
 
 
 

๐Ÿ‹๐Ÿป ์šด๋™!์•ˆํ• ๋ž˜ (19:00 -)

์˜ค๋Š˜์€ Benchpress๋ž‘ DeadLift๋งŒ ๊น”์Œˆํ•˜๊ฒŒ ์•ˆํ–ˆ๋‹คใ„ฒใ…‹ใ…‹ใ…‹ใ…‹
์˜ค๋Š˜ ๋„˜ํž˜๋“ค์–ด์„œ ๊ฑ ํฌ๊ธฐ!

 
 
 
 

 
 

๐Ÿ“Œ TODO List:

1. ๋…ผ๋ฌธ review: A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data
โˆ™ ๋…ผ๋ฌธ ์ •๋ฆฌ
โˆ™ ๋…ผ๋ฌธ review
โˆ™ PPT๋งŒ๋“ค๊ธฐ


2. ์ฃผ์ค‘์— ํ•  ๊ฒƒ: Deep Learning 2024(Bishop)-Chapter 2 ์ฝ๊ณ  ๊ณต๋ถ€ํ•˜๊ธฐ
โˆ™ 2.1  The Rule of Probability
โˆ™ 2.2  Probability Densities
โˆ™ 2.3  The Gaussian Distribution
โˆ™ 2.4  Transformation of Densities
โˆ™ 2.5  Information Theory
โˆ™ 2.6. Bayesian Probabilites

A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data | Proceedings of the AAAI Conference o

ojs.aaai.org

 

 
 

'2024 winter > ETRI(์ผ์ƒ)' ์นดํ…Œ๊ณ ๋ฆฌ์˜ ๋‹ค๋ฅธ ๊ธ€

[ETRI]2024.01.15  (0) 2024.01.15
[ETRI]2024.01.12  (2) 2024.01.12
[ETRI]2024.01.10  (4) 2024.01.10
[ETRI]2024.01.09  (2) 2024.01.09
[ETRI]2024.01.08  (4) 2024.01.08

+ Recent posts