UniFS: Universal Few-shot Instance Perception with Point Representations

TL;DR

UniFS introduces a unified few-shot instance perception framework that reformulates diverse tasks into point representation learning, leveraging structural relationships to improve performance with minimal task assumptions.

Contribution

The paper presents UniFS, a novel universal model for few-shot instance perception that unifies multiple tasks through dynamic point representations and structure-aware learning.

Findings

Achieves competitive results across various instance perception tasks.

Introduces Structure-Aware Point Learning (SAPL) for better representation.

Demonstrates minimal task assumptions with broad applicability.

Abstract

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.