A paper on learning from a limited data for human body/pose estimation from TAILOR researcher Hossein Rahmani, Lancaster University, has been accepted in the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR 2022) for oral presentation (acceptance rate is ~4%). This work has been done in collaboration with researchers from Singapore, US and Australia.
Meta Agent Teaming Active Learning for Pose Estimation
Jia Gong, Zhipeng Fan, Qiuhong Ke, Hossein Rahmani, Jun Liu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
Abstract
The existing pose estimation approaches often require a large number of annotated images to attain good estimation performance, which are laborious to acquire. To reduce the human efforts on pose annotations, we propose a novel Meta Agent Teaming Active Learning (MATAL) framework to actively select and label informative images for effective learning. Our MATAL formulates the image selection procedure as a Markov Decision Process and learns an optimal sampling policy that directly maximizes the performance of the pose estimator based on the reward. Our framework consists of a novel state-action representation as well as a multi-agent team to enable batch sampling in the active learning procedure.
The framework could be effectively optimized via Meta-Optimization to accelerate the adaptation to the gradually expanded labeled data during deployment. Finally, we show experimental results on both human hand and body pose estimation benchmark datasets and demonstrate that our method significantly outperforms all baselines continuously under the same amount of annotation budget. Moreover, to obtain similar pose estimation accuracy, our MATAL framework can save around 40% labeling efforts on average compared to state-of-the-art active learning frameworks.
