统一处理多种前景分割任务，提升边界识别精度
FOCUS: Towards Universal Foreground Segmentation
- 基于多尺度语义网络与边缘信息增强特征
- 提出对比学习蒸馏法，实现边界感知分割
- 在13个数据集上超越主流专用模型
前景分割是计算机视觉中的基础任务，包含多种子任务。以往研究通常为每个任务设计专用架构，缺乏统一性，且主要关注前景识别而忽略与背景的区分。本文强调背景的重要性及其与前景的关系，提出FOCUS（Foreground Objects Universal Segmentation）框架，可统一处理多种前景分割任务。通过利用物体边缘信息构建多尺度语义网络以增强图像特征，并提出一种新颖的蒸馏方法，结合对比学习策略，在多模态特征空间中优化预测掩码。我们在5个任务、共13个数据集上进行大量实验，结果表明，FOCUS在多数指标上持续优于现有最先进任务专用模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。