1st pass

1. Category: what type of paper is this?

   Introduction of DenseNet architecture and advantage compared with other CNNs

2. Context: What other papers are related? Which theories were
   used to analyze the problem?

   related with ResNet. They confirm the accuracy of this model by four highly competitive object recognition benchmark tasks.

3. Correctness: Are the assumptions valid?

   They said the accuracy of this model is better than any other thing.

4. Contributions: What are the papers’ main contributions?

   high accuracy, parameter & computational efficiency and regularization effect.

5. Clarity: Is the paper well written?

   Of course. 😁

---

with study

"collective knowledge" = connection + 새롭게 생성된 feature (쌓아진 느낌)

classifier는 맨 마지막에만 있는게 아니고 implicit deep supervision에도 implicitly 있는 거 아닐까?

deep supervision 설명 : https://eremo2002.tistory.com/116

bottle neck은 왜 Improve computational efficiency?
: https://hoya012.github.io/blog/DenseNet-Tutorial-1/

왜 valid set으로만 했을까???

---