Compile Error

Hinet is a ResNet based network which is specialized in image restoration, designed by Liangyu Chen et.al. The most important part of HINet is that it uses its own regularization method which normalizes only half of the instances. HINet is reaching SOTA in various denoising and image restoration tasks, and showed quite amazing performance on my own DACON project. https://arxiv.org/abs/2105.06086..

CycleGAN, proposed by Jun-Yan et al. is a generative adversarial model which is capable of translating images from source to target domain in the absence of paired training data. This was a relatively astonishing result compared to other models, because its core concept was very simple while generating highly realistic images. Therefore CycleGAN could be applied to various tasks and datasets. Cl..

Learning from Simulated and Unsupervised Images through Adversarial Training by Ashish Shrivastava et al. is published in 2016 which introduced a new method which transforms synthetic images to look real in order to use in adverarial training. This paper led various models to reach SOTA by only transforming input images which is fed to those models. https://arxiv.org/abs/1612.07828 Learning from..

Batch normalization is a normalization method used to prevent gradient explosion or vanish while training DNNs which is announced as a paper in 2015 by Sergey et al. When it was first presented, it led various DNN models to achieve higher performance matrics by simply adding BN layers between original layers. https://arxiv.org/abs/1502.03167 Batch Normalization: Accelerating Deep Network Trainin..

Article Introduction YOLO was outstanding CNN model specialized in object detection with extreamly low latency. However there was some drawbacks including the lack of ability to discriminate multiple small objects in the image (details are in the previous article). To improve this model, YOLOv2 and YOLO9000 was introduced newly by Joseph Redmon et al. again, in 2016. YOLOv2 & YOLO9000 YOLOv2 is ..

Article Introduction YOLO which refers to You Only Look (not Live!) Once became this paper's title, because it was the main advantage of the new object detection model. As designed by Joseph Redmon at el, YOLO brought a huge sensation on object detection realm for increasing prediction speed upto almost real-time while trading small amount of precision. In this article I'll explain the main arch..

Article Introduction The paper which introduces CloneCloud is written by Byung-Gon Chun et al, in 2011, which is a mobile program transformer to utilize the benefit of cloud system. This paper was and still is influencial today, with being rewarded as the most influencial paper published in 10 years by EuroSys 2021. In this article,we will summarize the main ideas and implemental details of Clon..

1. Introduction Learning representations by back-propagating error has introduced the very first idea of back-propagation for training multi layers of Perceptrons(MLP) on 1986, written by David E. Rumelhart, Geoffrey E. Hinton & Ronald J. Williams. In this short article, I'll explain some core concepts of the paper and focus on how each equation is induced from the formal ones. 2. Preliminary As..

본 포스팅은 리액트를 처음으로 공부하기 시작하는 사람들을 위해 제작되었다. 구글에 영어로 react라고만 쳐봐도 기본적인 개념을 배울만한 블로그는 아주 많지만 막상 처음부터 하나하나 따라할 수 있는 튜토리얼과 같은 게시글이 없는 것 같아 이 부분에 초점을 맞춰 포스팅을 써보려 한다. 자바스크립트의 라이브러리 우선 리액트는 페이스북이 직접 개발한 자바스크립트의 라이브러리이다. 즉, 문법과 기능에 확장이나 변화가 있을 수는 있지만 그 뼈대는 자바스크립트에 있다는 것이다. 따라서 리액트를 공부하기 전에 자바스크립트의 기본적인 변수선언(const, let, var 등) 같은 문법을 알아둔 후 공부하는 것이 좋다. 참고하면 좋을만한 사이트 : https://opentutorials.org/course/743 Vi..

1. CSRF란 무엇인가? CSRF(Cross Site Request Forgery)는 end user가 서버 내부 시스템에 직접적인 피해를 주도록 의도하는 행위를 의미한다. 여기서 "피해를 주도록 의도한다" 라는 부분이 중요한데 실제로 end user는 의도하지 않았지만 서버에 피해를 준 격이 되기 때문이다. 말로만 들으면 이해가 잘 되지 않으니 간단한 예시를 통해 알아보자. 즉시 100만원 지급 100% 당첨 이 버튼을 누른 사람은 분명 100만원을 받으려고 눌렀겠지만 아무도 모르는 사이에 href에 적힌 주소로 api call이 전송되고 실제로 서버에서 이 call을 처리하게 된다. 만약 악의를 품고 api call을 POST 또는 DELETE로 보낸다면 서버의 DB에 심각한 피해를 줄 수도 있다...