NaokiTemporal Convolutional NetworksCan CNNs handle sequential data and maintain a more effective history than LSTM?Sep 12, 2021Sep 12, 2021
NaokiVAE: Variational Auto-Encoder (2013)Understanding the Auto-Encoding Variational Bayes PaperAug 23, 20232Aug 23, 20232
NaokiLearning Transferable Visual Models From Natural Language Supervision (2021)Bridging the Gap Between Vision and Language — A Look at OpenAI’s CLIP ModelAug 13, 2023Aug 13, 2023
NaokiSwin Transformer (2021)Hierarchical Vision Transformer using Shifted WindowsNov 4, 2022Nov 4, 2022
NaokiViT: Vision Transformer (2020)An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleNov 2, 2022Nov 2, 2022
NaokiFCN: Fully Convolutional Networks (2014)A simple way to adopt robust image classification networks into segmentation tasksSep 8, 2022Sep 8, 2022
NaokiDeepLab v3 (2017)Hands-on Semantic Segmentation with DeepLab v3 with ResNet-101Sep 4, 2022Sep 4, 2022
NaokiSSD: Single Shot MultiBox DetectorWhy SSD is Faster Than YOLO v1 and More Accurate than Faster R-CNN?Jul 31, 2022Jul 31, 2022
NaokiFast R-CNNUnderstanding why it’s 213 Times Faster than R-CNN and More AccurateJun 21, 2022Jun 21, 2022
NaokiR-CNN: Region-based Convolutional Neural NetworkR-CNN = CNN Extracting Features + SVM ClassifierJun 11, 2022Jun 11, 2022
