Skip to content
/ TDP-codes Public

Task-driven feature pooling for image classification ICCV15

Notifications You must be signed in to change notification settings

gsx0/TDP-codes

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

TDP-codes

TDP-code example dataset: Flower17 We show experimental settings of three partitions (two tasks, i.e., two scales as inputs for extracting VGG-19 features) on Flower17 datasets. Due to that the extracted deep CNN features are large, we can not upload them through github; authors can extract features by themselves, or contact me, then I will send you the extracted features through other ways.

Running Instructions:

  1. TDP_main_par1_t1_selftune.m is the main function for conducting Experiments on task 1 of partition 1 on Flower17 datasets.
  2. after you run all these six functions, you can obtain specific numbers of recognition accuracy.
  3. for multiple task optimization, the parameters from each single task should be used as the initializing parameters.

If having any problems, please contact:

[email protected]

About

Task-driven feature pooling for image classification ICCV15

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages