Towards Labeling-free Fine-grained Animal Pose Estimation

Dan Zeng, Yu Zhu, Shuiwang Li, Qijun Zhao, Qiaomu Shen, Bo Tang

Abstract: In this paper, we are interested in identifying denser and finer animals joints. The lack of standardized joint definitions across various APE datasets, e.g., AnimalPose with 20 joints, AP-10k with 17 joints, and TigDog with 19 joints, presents a significant challenge yet offers an opportunity to fully utilize annotation data. This paper challenges this new non-standardized annotation problem, aiming to learn fine-grained (e.g., 24 or more joints) pose estimators in datasets that lack complete annotations. To combat the unannotated joints, we propose FreeNet, comprising a base network and an adaptation network connected through a circuit feedback learning paradigm. FreeNet enhances the adaptation network's tolerance to unannotated joints via body part-aware learning, optimizing the sampling frequency of joints based on joint detection difficulty, and improves the base network's predictions for unannotated joints using feedback learning. This leverages the cognitive differences of the adaptation network between non-standardized labeled and large-scale unlabeled data. Experimental results on three non-standard datasets demonstrate the effectiveness of our method for fine-grained APE.