avatar
Articles
165
Tags
34
Categories
0

Home
Archives
Tags
Categories
List
  • Music
  • Movie
Link
About
ALTNT's Hexo Blog
Home
Archives
Tags
Categories
List
  • Music
  • Movie
Link
About

Context Encoders:Feature Learning by Inpainting

Created2024-10-28|Updated2025-02-28
|Post Views:
Author: ALTNT
Link: http://blog.705553939.xyz/2024/10/28/%E5%9B%BE%E5%83%8F%E5%A4%84%E7%90%86/2015-context-encoder/
Copyright Notice: All articles in this blog are licensed under CC BY-NC-SA 4.0 unless stating additionally.
Image Processing
Previous
Contrastive Graph Transformer Network for Personality Detection
Next
CDAM-Net:Channel shuffle dual attention based multi-scale CNN for efficient glaucoma detection using fundus images
Related Articles
2024-10-15
ImageNet Large Scale Visual Recognition Challenge
2025-02-04
AN IMAGE IS WORTH 16X16 WORDS——TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE
2025-02-07
Deep Sets
2024-10-28
CDAM-Net:Channel shuffle dual attention based multi-scale CNN for efficient glaucoma detection using fundus images
2025-03-03
BERT Pre-training of Deep Bidirectional Transformers for Language Understanding
2024-11-03
Self-Supervised Transformer for Sparse and Irregularly Sampled Multivariate Clinical Time-Series
avatar
ALTNT
Articles
165
Tags
34
Categories
0
Follow Me
Announcement
This is my Blog
Contents
  1. 1. Context Encoders: Feature Learning by Inpainting
    1. 1.1. 摘要:
    2. 1.2. 1、引言
    3. 1.3. 2、相关工作
      1. 1.3.1. 无监督学习
      2. 1.3.2. 弱监督和自监督学习
      3. 1.3.3. 图像生成
      4. 1.3.4. Inpainting and hole-filling
    4. 1.4. 3、用于图像生成的上下文编码器
      1. 1.4.1. 3.1. 编码器-解码器流程
        1. 1.4.1.1. 编码器
        2. 1.4.1.2. 通道全连接层
        3. 1.4.1.3. 解码器
      2. 1.4.2. 3.2.损失函数
        1. 1.4.2.1. 重建损失:
        2. 1.4.2.2. 对抗损失
        3. 1.4.2.3. 联合损失
      3. 1.4.3. 3.3. 区域掩码
        1. 1.4.3.1. 中部区域
        2. 1.4.3.2. 随机块
        3. 1.4.3.3. 随机区域
    5. 1.5. 4、实现细节
      1. 1.5.1. Pool-free encoders
    6. 1.6. 5、评估
      1. 1.6.1. 5.1. 语义修复
      2. 1.6.2. 5.2 特征学习
        1. 1.6.2.1. 5.2.1 分类预训练
        2. 1.6.2.2. 5.2.2 检测预训练
        3. 1.6.2.3. 5.2.3 语义分割预训练
    7. 1.7. 6、结论
Recent Post
周报2025年6月8日2025-06-09
The 20 m Africa rice distribution map of 20232025-06-04
DCM————DeepCropMapping: A multi-temporal deep learning approach with improved spatial generalizability for dynamic corn and soybean mapping2025-06-04
重新复现CACM记录2025-06-04
机器学习相关概念2025-05-26
©2020 - 2025 By ALTNT
Framework Hexo|Theme Butterfly