Count crowds accurately even after add new domain with FLCB
Count crowds accurately even after add new domain with FLCB
Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting
arXiv paper abstract https://arxiv.org/abs/2205.03307v1
arXiv PDF paper https://arxiv.org/pdf/2205.03307v1.pdf
... crowd counting system has to be capable of continuously learning with the new-coming domain data in real-world scenarios instead of fitting one domain only.
Off-the-shelf methods have some drawbacks to handle multiple domains.
... investigate a new task of crowd counting under the incremental domains training setting, namely, Lifelong Crowd Counting.
It aims at alleviating the catastrophic forgetting and improving the generalization ability using a single model updated by the incremental domains.
... propose a self-distillation learning framework as a benchmark (Forget Less, Count Better, FLCB) for lifelong crowd counting, which helps the model sustainably leverage previous meaningful knowledge for better crowd counting to mitigate the forgetting when the new data arrive.
... demonstrate the superiority of ... proposed benchmark in achieving a low catastrophic forgetting degree and strong generalization ability.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments