[AI] 논문 리스트

* Rethinking Atrous Convolution for Semantic Image Segmentation (Google)

=> atrous convolution, DeepLabv3

 

* Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (Google)

=> DeepLabv3+

 

* MentorNet, Regularizing Very Depp Neural Networks on Corrupted Lables

=> MentorNet

 

* Deep Neural Networks for YouTube Recommendations (Google)

* Attention-Based Models for Speech Recognition

* ASTER : An Attentional Scene Text Recognizer with Flexible Rectification (Baoguang Shi 등) - 2018

* FAN : Focusing Attention : Towards Accurate Text Recognition in Natural Images (Hikvision)

* CRAFT : Character Region Awareness for Text Detection (NAVER)

* What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis

* Beyond a Gaussian Denoiser : Residual Learning of Deep CNN for Image Denoising

* Hybrid Task Cascade for Instnace Segmentation

* Improving Semantic Segmentation via Video Propagation and Label Relaxation

=> synthesizing new training samples

* Fixing the train-test resolution discrepancy (Facebook AI Research)

* Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections 

* DeepTrianle : A Deep Learning Approach to Loss Reserving (Kasa AI)

* U-GAT-IT : Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation (NCSOFT)

* On the Properties of Neural Machine Translation: Encoder-Decoder Approaches (Yoshua Bengio)

* Chinese Text in the Wild

* TedEval : A Fair Evaluation Metric for Scene Text Detectors (NAVER)

* RARE : Robust Scene Text Recognition with Automatic Rectification (Huazhong Uni, Baoguang Shi) - 2016

* Multi-Scale Attention with Dense Encoder for Handwritten Mathematical Expression Recognition (University of Science and Technology of China, Hefei, Anhui, P.R.China)

* Sequence-to-Sequence Domain Adaptation Network for Tobust Text Image Recognition - 2019

* An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition (Huazhong Uni, Baoguang Shi)

* Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition (Kaiming He)

* YOLACT++ : Better Real-time Instance Segmentaion

* Aggregation Cross-Entropy for Sequence Recognition

=> ACE loss function

* Large scale deep neural network acoustic modeling with semi-supervised training data for youtube video transcription (Google)

* FASTERSEG : Searching for faster real-time semantic segmentation (Horizon Robotics)