논문리뷰
1.[논문리뷰]DCN
Deformable Convolutional Networks(DCN) > Author: Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, Yichen Wei
2.[논문리뷰]GoogLeNet
Going deeper with convolutions > Author: Christian Szegedy [1],Wei Liu[2],Yangqing Jia [1],Pierre Sermanet [1],Scott Reed[3],Dragomir Anguelov [1],Dum
3.[논문리뷰]Rethinking the Inception Architecture for Computer Vision
Rethinking the Inception Architecture for Computer Vision > Author: Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens 이 논문에서 모바일 비전
4.[논문리뷰]Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads
Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads >Author: Myeongjae Jeon†, Shivaram Venkataraman‡, Amar Phanishayee[], Jun
5.[논문리뷰] REP: Resource-Efficient Prompting for On-device Continual Learning
REP: Resource-Efficient Prompting for On-device Continual Learning https://arxiv.org/pdf/2406.04772 >Sungho Jeon[1], Xinyue Ma[1], Kwang In Kim[2], M
6.[논문리뷰] ResNet(2015)
Deep Residual Learning for Image Recognition https://arxiv.org/pdf/1512.03385v1 >Author: Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun [Microsof
7.[논문리뷰]DenseNet(2017)
Densely Connected Convolutional Networks https://arxiv.org/pdf/1608.06993v5 > Author: Gao Huang∗, Zhuang Liu∗, Laurens van der Maaten, Kilian Q. Weinb
8.[논문리뷰]SIPSA-Net
SIPSA-Net: Shift-Invariant Pan Sharpening with Moving Object Alignment for Satellite Imagery > Author: Jaehyup Lee, Soomin Seo, Munchurl Kim* https:
9.[논문리뷰] DAKD
DAKD: Data Augmentation and Knowledge Distillation using Diffusion Models for SAR Oil Spill Segmentation Abstract 본 논문에서는 해양에서 발생하는 유출 사고는 심각한 환경적 위
10.[논문리뷰] FCN: Fully Convolutional Networks for Semantic Segmentation(2015)
https://arxiv.org/pdf/1411.4038Author: Jonathan Long∗, Evan Shelhamer∗, Trevor DarrellCNN을 end-to-end방식, pixel-to-pixel방식으로 학습하여 semantic segment
11.[논문리뷰]U-Net: Convolutional Networks for Biomedical Image Segmentation(2015)
https://arxiv.org/pdf/1505.04597 >Author: Olaf Ronneberger, Philipp Fischer, and Thomas Brox Abstract Data Augmentation을 활용하여 적은 갯수의 데이터로도 학습 가능한 네트워
12.[논문리뷰]VAE(Auto-Encoding Variational Bayes)(2013)
https://arxiv.org/pdf/1312.6114 > Author: Diederik P. Kingma, Max Welling Background AutoEncoder Encoder 와 Decoder로 구성된 딥러닝 모델을 의미한다. input 과 outpu
13.[논문리뷰]DDPM(2020)
https://arxiv.org/pdf/2006.11239 >Author: Jonathan Ho, Ajay Jain, Pieter Abbeel GAN(Generative Adversarial Network):Generator 와 Discriminator로 구분되어
14.[논문리뷰]ControlNet(2023)
https://arxiv.org/pdf/2302.05543Author: Lvmin Zhang, Anyi Rao, and Maneesh Agrawala기존의 text-to-image는 성능이 좋지만 text 하나로만은 복잡한 표현들을 control 할 수 없다.