FOCUS: Towards Universal Foreground Segmentation

TL;DR

FOCUS introduces a universal framework for foreground segmentation that effectively handles multiple tasks by leveraging edge information and contrastive learning, outperforming task-specific models across diverse datasets.

Contribution

The paper presents a novel universal segmentation framework that unifies multiple foreground tasks using multi-scale features and a boundary-aware distillation method.

Findings

Outperforms state-of-the-art models on 13 datasets across 5 tasks

Effectively distinguishes foreground objects from backgrounds

Enhances segmentation accuracy with boundary-aware techniques

Abstract

Foreground segmentation is a fundamental task in computer vision, encompassing various subdivision tasks. Previous research has typically designed task-specific architectures for each task, leading to a lack of unification. Moreover, they primarily focus on recognizing foreground objects without effectively distinguishing them from the background. In this paper, we emphasize the importance of the background and its relationship with the foreground. We introduce FOCUS, the Foreground ObjeCts Universal Segmentation framework that can handle multiple foreground tasks. We develop a multi-scale semantic network using the edge information of objects to enhance image features. To achieve boundary-aware segmentation, we propose a novel distillation method, integrating the contrastive learning strategy to refine the prediction mask in multi-modal feature space. We conduct extensive experiments on a total of 13 datasets across 5 tasks, and the results demonstrate that FOCUS consistently outperforms the state-of-the-art task-specific models on most metrics.