Skip to content

Source code for ICASSP'23 paper: Cross-head Supervision for Crowd Counting with Noisy Annotations

Notifications You must be signed in to change notification settings

RaccoonDML/CHSNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Cross-head Supervision for Crowd Counting with Noisy Annotations

This is the official implementation for ICASSP 2023 paper: cross-head supervision for crowd counting with noisy annotations.

to run

  1. pip install -r requirements.txt
  2. download dataset to ./DATASET
  3. run preprocess_dataset_xxx_dmap.py in ./preprocess
  4. sh run.sh

use wandb to record experiments result

Refer to wandb for config.

About

Source code for ICASSP'23 paper: Cross-head Supervision for Crowd Counting with Noisy Annotations

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published