# FOCUS: Towards Universal Foreground Segmentation

arXiv: https://arxiv.org/abs/2501.05238 · HTML: https://mlsanity.com/paper/2501.05238/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jan 2025.

## Built on by (most cited first, 10 of 10)

- [Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning](https://mlsanity.com/paper/2506.22624/) (2025)
- [Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Art](https://mlsanity.com/paper/2503.08695/) (2025)
- [DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidance](https://mlsanity.com/paper/2606.08906/) (2026)
- [DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2601.20064/) (2026)
- [On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNs](https://mlsanity.com/paper/2504.08602/) (2025)
- [Learning Accurate Segmentation Purely from Self-Supervision](https://mlsanity.com/paper/2602.23759/) (2026)
- [DRRNet: Macro-Micro Feature Fusion and Dual Reverse Refinement for Camouflaged Object Detection](https://mlsanity.com/paper/2505.09168/) (2025)
- [Revisiting Salient Object Detection from an Observer-Centric Perspective](https://mlsanity.com/paper/2602.06369/) (2026)
- [Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detection](https://mlsanity.com/paper/2604.12380/) (2026)
- [When Does Resolution Help a Frozen Backbone? Global Attention at Resolution Predicts Scalable Adaptation for Camouflaged and Marine Animal Segmentation](https://mlsanity.com/paper/2607.02708/) (2026)

## Abstract (arXiv)

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.