A Unified Object Counting Network with Object Occupation Prior
(Accepted by IEEE Transactions on Circuits and Systems for Video Technology)
The counting task, which plays a fundamental role in numerous applications (e.g., crowd counting, traffic statistics), aims to predict the number of objects with various densities. Existing object counting tasks are designed for a single object class. However, it is inevitable to encounter newly coming data with new classes in our real world. We name this scenario as evolving object counting. In this paper, we build the first evolving object counting dataset and propose a unified object counting network as the first attempt to address evolving object counting.
Dataset:
Google disk: https://drive.google.com/drive/folders/1b5FLVQNPBHAILHO03MSVALZ1jWckHaX7?usp=sharing
Baidu Netdisk: https://pan.baidu.com/s/1OcdmDrKYLheIrWUrG4Flxw?pwd=njkt Code：njkt
Test:
- Download the pre-trained weights
Baidu Netdisk: https://pan.baidu.com/s/18B5R-NFY6YwF4PV-NTGyxQ?pwd=njkd Code：njkd
- Run the testing script. python test.py
Train:
Training code will be released soon.