Segmenting unknown or anomalous object instances is a critical task in autonomous driving applications, and it is approached traditionally as a per-pixel classification problem. However, reasoning individually about each pixel without considering their contextual semantics results in high uncertainty around the objects' boundaries and numerous false positives. We propose a paradigm change by shifting from a per-pixel classification to a mask classification. Our mask-based method, Mask2Anomaly, demonstrates the feasibility of integrating a mask-classification architecture to jointly address anomaly segmentation, open-set semantic segmentation, and open-set panoptic segmentation. Mask2Anomaly includes several technical novelties that are designed to improve the detection of anomalies/unknown objects: i) a global masked attention module to focus individually on the foreground and background regions; ii) a mask contrastive learning that maximizes the margin between an anomaly and known classes; iii) a mask refinement solution to reduce false positives; and iv) a novel approach to mine unknown instances based on the mask- architecture properties. By comprehensive qualitative and qualitative evaluation, we show Mask2Anomaly achieves new state-of-the-art results across the benchmarks of anomaly segmentation, open-set semantic segmentation, and open-set panoptic segmentation.燭he code and pre-trained models are available: https://github.com/shyam671/Mask2Anomaly-Unmasking-Anomalies-in-Road-Scene-Segmentation/tree/main.

中文翻译：

---

Mask2Anomaly：用于通用开集分割的掩模变压器


分割未知或异常对象实例是自动驾驶应用中的一项关键任务，传统上将其视为每像素分类问题。然而，单独推理每个像素而不考虑其上下文语义会导致对象边界周围的高度不确定性和大量误报。我们提出了一种范式改变，从每像素分类转变为掩模分类。我们基于掩模的方法 Mask2Anomaly 展示了集成掩模分类架构来联合解决异常分割、开放集语义分割和开放集全景分割的可行性。 Mask2Anomaly 包括多项技术新颖性，旨在改进异常/未知物体的检测： i) 全局屏蔽注意模块，用于单独关注前景和背景区域； ii) 掩码对比学习，最大化异常类和已知类之间的差距； iii) 掩模细化解决方案以减少误报； iv）一种基于掩码架构属性来挖掘未知实例的新方法。通过全面的定性和定性评估，我们表明 Mask2Anomaly 在异常分割、开放集语义分割和开放集全景分割的基准上取得了新的最先进的结果。代码和预训练模型可用：https://github.com/shyam671/Mask2Anomaly-Unmasking-Anomalies-in-Road-Scene-Segmentation/tree/main。