Newly Blog

Home Archives
2026-03-15
paper note

Training Categories and Test Categories

Let us use $S$ to denote the set of training categories and $T$ to denote the set of testing categories.

  • $S=T$: the most common case
  • $S\cap T=\emptyset$: zero-shot learning
  • $S\subset T$: generalized zero-shot learning
  • $S\supset T$: pretrained model
Share
Newer
Unsupervised Attribute Learning
Older
Synthetic Text Images

Categories

  • OS
  • compiler
  • hardware
    • GPU
    • camera
  • network
  • paper note
  • programming language
    • Android
    • C++
    • HTML
    • MATLAB
    • Python
    • cross-language
  • software
    • IDE
    • library
    • version control

Tags

  • 3D
  • Adroid
  • Anaconda
  • BIOS
  • C
  • C++
  • CMake
  • CSS
  • CUDA
  • Caffe
  • CuDNN
  • EM
  • Eclipse
  • FFmpeg
  • GAN
  • GNN
  • GPU
  • GStreamer
  • GUI
  • Git
  • GitHub
  • HTML
  • Hexo
  • JDK
  • Java
  • LaTeX
  • Line detection
  • MATLAB
  • MI
  • MLLM
  • Makefile
  • MarkdownPad
  • MoE
  • OpenCV
  • PyTorch
  • Python
  • ROI
  • SSH
  • SVM
  • Shell
  • TensorFlow
  • Ubuntu
  • VAE
  • VNC
  • VQA
  • VirtualBox
  • Windows
  • action recognition
  • adversarial attack
  • aesthetic cropping
  • attention
  • attribute
  • blending
  • boundary
  • camera
  • causality
  • composition
  • crontab
  • cross-modal retrieval
  • diffusion model
  • disentangle
  • distillation
  • docker
  • domain adaptation
  • domain translation
  • edge detection
  • efficiency
  • face recognition
  • face verification
  • few-shot
  • fine-grained
  • gaze estimation
  • generative model
  • harmonization
  • hyper-parameter
  • image editing
  • image generation
  • image manipulation
  • image translation
  • inpainting
  • instance segmentation
  • knowledge graph
  • lifelong learning
  • matting
  • medical
  • memory
  • meta learning
  • mount
  • network structure
  • object detection
  • object tracking
  • optical flow
  • outlier detection
  • paper
  • privileged information
  • proposal
  • rendering
  • representation learning
  • scene text
  • segmentation
  • self-supervised
  • semantic segmentation
  • semi-supervised
  • shadow
  • style transfer
  • surgery
  • video object segmentation
  • visual sentiment
  • watermark
  • weakly-supervised
  • webly-supervised
  • word vector
  • wxPython
  • zero-shot

Tag Cloud

3D Adroid Anaconda BIOS C C++ CMake CSS CUDA Caffe CuDNN EM Eclipse FFmpeg GAN GNN GPU GStreamer GUI Git GitHub HTML Hexo JDK Java LaTeX Line detection MATLAB MI MLLM Makefile MarkdownPad MoE OpenCV PyTorch Python ROI SSH SVM Shell TensorFlow Ubuntu VAE VNC VQA VirtualBox Windows action recognition adversarial attack aesthetic cropping attention attribute blending boundary camera causality composition crontab cross-modal retrieval diffusion model disentangle distillation docker domain adaptation domain translation edge detection efficiency face recognition face verification few-shot fine-grained gaze estimation generative model harmonization hyper-parameter image editing image generation image manipulation image translation inpainting instance segmentation knowledge graph lifelong learning matting medical memory meta learning mount network structure object detection object tracking optical flow outlier detection paper privileged information proposal rendering representation learning scene text segmentation self-supervised semantic segmentation semi-supervised shadow style transfer surgery video object segmentation visual sentiment watermark weakly-supervised webly-supervised word vector wxPython zero-shot

Archives

  • March 2026

Recent Posts

  • Install VirtualBox Guest Addition
  • Enlarge VirtualBox vdi
  • Git
  • Ubuntu JDK
  • OpenCV
© 2026 Li Niu
Powered by Hexo
Home Archives