通过形态学优化对抗数据中的不可行包含以实现语义分割
Optimizing against Infeasible Inclusions from Data for Semantic Segmentation through Morphology
AI总结:
InSeIn通过提取空间类关系约束并采用可微形态学损失优化语义分割,提升预测可行性与性能。
摘要:
当前最先进的语义分割模型通常以数据驱动的方式进行优化,仅在训练数据上最小化每个像素或每个分割的分类目标。这种纯粹的数据驱动范式往往导致荒谬的分割结果,尤其是在输入图像域从训练时遇到的领域发生变化时。例如,最先进的模型可能将一个被另一个分别标记为
英文摘要:
State-of-the-art semantic segmentation models are typically optimized in a data-driven fashion, minimizing solely per-pixel or per-segment classification objectives on their training data. This purely data-driven paradigm often leads to absurd segmentations, especially when the domain of input images is shifted from the one encountered during training. For instance, state-of-the-art models may assign the label "road" to a segment that is included by another segment that is respectively labeled as "sky". However, the ground truth of the existing dataset at hand dictates that such inclusion is not feasible. Our method, Infeasible Semantic Inclusions (InSeIn), first extracts explicit inclusion constraints that govern spatial class relations from the semantic segmentation training set at hand in an offline, data-driven fashion, and then enforces a morphological yet differentiable loss that penalizes violations of these constraints during training to promote prediction feasibility. InSeIn is a light-weight plug-and-play method, constitutes a novel step towards minimizing infeasible semantic inclusions in the predictions of learned segmentation models, and yields consistent and significant performance improvements over diverse state-of-the-art networks across the ADE20K, Cityscapes, and ACDC datasets. https://github.com/SHAMIK-97/InSeIn
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。