PinnedMorisinComputer Vision NoteMulti-Modal Face Anti-Spoofing Based on Central Difference Networks該論文於2020年發表於CVPR, 有42個ReferenceJan 13, 2023Jan 13, 2023
PinnedMorisinComputer Vision NoteRecognizing Multi-Modal Face Spoofing with Face Recognition Networks該論文於2019年發表於CVPR, 有57個ReferenceDec 6, 2022Dec 6, 2022
PinnedMorisinComputer Vision NoteInception-v4 — Evolved From GoogLeNet, Merged with ResNet Idea (Image Classification)Aug 23, 2021Aug 23, 2021
MorisinComputer Vision NoteStyleGAN2Analyzing and Improving the Image Quality of StyleGANMar 18Mar 18
MorisinComputer Vision NoteStyleGAN-A Style-Based Generator Architecture for GANsGenerating and Tuning Realistic Artificial FacesMar 18Mar 18
MorisinComputer Vision NoteImagen- Photorealistic Text-to-Image Diffusion Models with Deep LanguagePaper ExplainedMar 14Mar 14
MorisinComputer Vision NoteDALL·E: Zero-Shot Text-to-Image GenerationDALL·E, or DALL-E, Using GPT-3 for Text-to-Image GenerationMar 14Mar 14
MorisinComputer Vision NoteStable diffusion — High-Resolution Image Synthesis with Latent Diffusion Models雖然OpenAI的生成文本模型在自然語言處理領域獨佔鰲頭,但他們的圖像生成對手DALL·E現在面臨了一個可行的開源競爭者Stable Diffusion。本文深入探討了Latent Diffusion論文,Stable Diffusion就是基於這篇論文。Mar 14Mar 14
MorisinLinux & Backend NotesKubernetes RoadmapKubernetes已迅速成為容器編排和管理的事實標準。隨著越來越多的組織採用Kubernetes,對Kubernetes技能和專業知識的需求也在增長。這份全面的路線圖將帶領您從Kubernetes的基礎知識一路了解到進階的管理、安全和治理。Feb 29Feb 29