Unifying Visual Perception by Dispersible Points Learning

TL;DR

UniHead introduces a universal visual perception head that unifies multiple tasks like classification, detection, segmentation, and pose estimation using dispersible points learning with transformer encoders, achieving competitive results across various benchmarks.

Contribution

The paper proposes UniHead, a simple and flexible transformer-based head that unifies multiple visual perception tasks within a single framework, simplifying model design.

Findings

Achieves comparable performance to specialized models on COCO and ImageNet.

Unifies multiple tasks with a single head design, reducing complexity.

Demonstrates versatility across different frameworks and tasks.

Abstract

We present a conceptually simple, flexible, and universal visual perception head for variant visual tasks, e.g., classification, object detection, instance segmentation and pose estimation, and different frameworks, such as one-stage or two-stage pipelines. Our approach effectively identifies an object in an image while simultaneously generating a high-quality bounding box or contour-based segmentation mask or set of keypoints. The method, called UniHead, views different visual perception tasks as the dispersible points learning via the transformer encoder architecture. Given a fixed spatial coordinate, UniHead adaptively scatters it to different spatial points and reasons about their relations by transformer encoder. It directly outputs the final set of predictions in the form of multiple points, allowing us to perform different visual tasks in different frameworks with the same head design. We show extensive evaluations on ImageNet classification and all three tracks of the COCO suite of challenges, including object detection, instance segmentation and pose estimation. Without bells and whistles, UniHead can unify these visual tasks via a single visual head design and achieve comparable performance compared to expert models developed for each task.We hope our simple and universal UniHead will serve as a solid baseline and help promote universal visual perception research. Code and models are available at https://github.com/Sense-X/UniHead.