UniFS: Universal Few-shot Instance Perception with Point Representations
This addresses the need for efficient few-shot learning in industrial visual applications, though it appears incremental as it builds on existing point representation frameworks.
The paper tackles the problem of high labeling costs in instance perception tasks by proposing UniFS, a universal few-shot learning model that unifies tasks like object detection and segmentation using point representations, achieving competitive results compared to specialized models.
Instance perception tasks (object detection, instance segmentation, pose estimation, counting) play a key role in industrial applications of visual models. As supervised learning methods suffer from high labeling cost, few-shot learning methods which effectively learn from a limited number of labeled examples are desired. Existing few-shot learning methods primarily focus on a restricted set of tasks, presumably due to the challenges involved in designing a generic model capable of representing diverse tasks in a unified manner. In this paper, we propose UniFS, a universal few-shot instance perception model that unifies a wide range of instance perception tasks by reformulating them into a dynamic point representation learning framework. Additionally, we propose Structure-Aware Point Learning (SAPL) to exploit the higher-order structural relationship among points to further enhance representation learning. Our approach makes minimal assumptions about the tasks, yet it achieves competitive results compared to highly specialized and well optimized specialist models. Codes and data are available at https://github.com/jin-s13/UniFS.