AI 中文总结
该研究针对开放世界语义分割任务，在统一编码器-解码器架构中扩展出第三个敏感性解码器，结合Cityscapes和BDD-Anomaly数据集实验，在保持封闭集准确率的同时提升了异常分割与新类别发现性能。
AI 中文摘要
现代视觉系统必须在“开放世界”场景下运行，在此场景中，模型既要识别已知类别，又要检测未见过的或异常的内容。传统语义分割模型基于“封闭世界”假设运行，常对新内容产生过度自信的错误分类。我们针对开放世界语义分割这一任务展开研究，该任务需在无额外监督的情况下，同时完成已知类别的分割以及对新的或异常内容的检测与分组，具体做法是在统一的编码器-解码器架构中，为双解码器基线模型扩展第三个互补解码器。第一个解码器使用高斯原型对已知类别进行封闭集分割；第二个解码器采用对比特征学习，在嵌入空间中隔离未知区域；第三个解码器是我们的核心贡献，为敏感性解码器，它能捕捉表明语义不确定性的细粒度纹理不规则性与激活不稳定性，而语义原型和对比范数均无法可靠检测到这些特征。三个解码器提供了真正互补的信号：logit空间中的类级分布外（OOD）距离、嵌入空间中的全局特征能量，以及编码器各尺度间的局部激活不稳定性。在Cityscapes和BDD-Anomaly数据集上开展的实验表明，我们的方法在保持有竞争力的封闭集准确率的同时，提升了异常分割和新类别发现的性能，在BDD-Anomaly数据集上，相较于基线模型，我们的方法的AUROC提升了2.4%，FPR@95TPR降低了2.5个百分点。
英文摘要
Modern vision systems must operate in "open-world" settings, where models must recognize known categories and detect unseen or anomalous content. Conventional semantic segmentation models operate under a "closed-world" assumption, often producing overconfident misclassifications on novel content. We address open-world semantic segmentation, the joint task of segmenting known classes while detecting and grouping novel or anomalous content without additional supervision, by extending a dual-decoder baseline with a third, complementary decoder within a unified encoder-decoder design. The first decoder performs closed-set segmentation using Gaussian prototypes for known categories. The second uses contrastive feature learning to isolate unknown regions in embedding space. The third, our key contribution, is a sensitivity decoder that captures fine-grained texture irregularities and activation instabilities indicative of semantic uncertainty, which neither semantic prototypes nor contrastive norms can reliably detect. The three decoders provide genuinely complementary signals: class-level OOD distance in logit space, global feature energy in embedding space, and local activation instability across encoder scales. Experiments on Cityscapes and BDD-Anomaly show that our method improves anomaly segmentation and novel-class discovery while maintaining competitive closed-set accuracy, with gains of +2.4% AUROC and a 2.5 pp. reduction in FPR@95TPR on BDD-Anomaly over the baseline.
CommentsICIP 2026 Workshop M-PaSTIVE
