A Self-Supervised Method for Body Part Segmentation and Keypoint Detection of Rat Images
This addresses the time and cost issues in medical research for behavior analysis of laboratory animals, though it is incremental as it builds on existing self-supervised and augmentation techniques.
The paper tackles the problem of reducing the need for manual labeling for instance segmentation, keypoint detection, and body part segmentation of laboratory rats by proposing a self-supervised method that generates initial annotations with computer vision and trains a deep neural network on augmented data, achieving robust performance even under heavy occlusion.
Recognition of individual components and keypoint detection supported by instance segmentation is crucial to analyze the behavior of agents on the scene. Such systems could be used for surveillance, self-driving cars, and also for medical research, where behavior analysis of laboratory animals is used to confirm the aftereffects of a given medicine. A method capable of solving the aforementioned tasks usually requires a large amount of high-quality hand-annotated data, which takes time and money to produce. In this paper, we propose a method that alleviates the need for manual labeling of laboratory rats. To do so, first, we generate initial annotations with a computer vision-based approach, then through extensive augmentation, we train a deep neural network on the generated data. The final system is capable of instance segmentation, keypoint detection, and body part segmentation even when the objects are heavily occluded.