Computer Vision Note

Computer Vision Note

Pinned

Moris

FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing

該論文於2019年發表於CVPR, 有52個Reference

4 min readApr 7, 2023

--

FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing

--

Pinned

Moris

CLIP: Learning Transferable Visual Models From Natural Language Supervision

對比語言影像預訓練（CLIP），從影像字幕數據集中學習影像特徵表示

10 min readDec 25, 2023

--

CLIP: Learning Transferable Visual Models From Natural Language Supervision

--

Pinned

Moris

YOLACT :Real-time Instance Segmentation

從執行物件偵測到實體分割的世界是一個巨大的飛躍，執行物件的mask segmentation比在物件偵測中獲得物件的邊界框要困難得多。在本文中，作者嘗試實時獲取物件的segmentation mask，即instance segmentation。

19 min readDec 28, 2022

--

YOLACT :Real-time Instance Segmentation

--

Pinned

Moris

YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors (Object…

YOLOv7, Train From Scratch, Outperforms All Object Detectors

10 min readOct 6, 2022

--

1

YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors (Object…

--

1

Moris

StyleGAN3

Alias-Free Generative Adversarial Networks

14 min readMar 18, 2024

--

StyleGAN3

--

Moris

StyleGAN2

Analyzing and Improving the Image Quality of StyleGAN

9 min readMar 18, 2024

--

StyleGAN2

--

Moris

StyleGAN-A Style-Based Generator Architecture for GANs

Generating and Tuning Realistic Artificial Faces

10 min readMar 18, 2024

--

StyleGAN-A Style-Based Generator Architecture for GANs

--

Moris

Imagen- Photorealistic Text-to-Image Diffusion Models with Deep Language

Paper Explained

7 min readMar 14, 2024

--

Imagen- Photorealistic Text-to-Image Diffusion Models with Deep Language

--

Moris

DALL·E: Zero-Shot Text-to-Image Generation

DALL·E, or DALL-E, Using GPT-3 for Text-to-Image Generation

7 min readMar 14, 2024

--

DALL·E: Zero-Shot Text-to-Image Generation

--

Moris

Stable 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。

13 min readMar 14, 2024

--

Stable diffusion — High-Resolution Image Synthesis with Latent Diffusion Models

--

This Publication include Image Classification,  Semantic Segmentation,  Instance Segmentation,  Object Detection, Face Recognition and Traditional Image Processing method
Editors
Moris
An AI engineer who loves deep learning technology and is willing to share resources and learn new technologies

Help
Status
About
Careers
Blog
Privacy
Terms
Text to speech
Teams