Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning
This addresses the problem of deploying crowd counting models in real-world scenarios where adaptation to specific camera scenes is needed with minimal labeled data, representing an incremental improvement in domain-specific applications.
The paper tackles few-shot scene adaptive crowd counting by using meta-learning to enable fast model adaptation to new camera scenes with only a few labeled images, and it shows that the proposed approach outperforms other methods in experiments.
We consider the problem of few-shot scene adaptive crowd counting. Given a target camera scene, our goal is to adapt a model to this specific scene with only a few labeled images of that scene. The solution to this problem has potential applications in numerous real-world scenarios, where we ideally like to deploy a crowd counting model specially adapted to a target camera. We accomplish this challenge by taking inspiration from the recently introduced learning-to-learn paradigm in the context of few-shot regime. In training, our method learns the model parameters in a way that facilitates the fast adaptation to the target scene. At test time, given a target scene with a small number of labeled data, our method quickly adapts to that scene with a few gradient updates to the learned parameters. Our extensive experimental results show that the proposed approach outperforms other alternatives in few-shot scene adaptive crowd counting. Code is available at https://github.com/maheshkkumar/fscc.