Image segmentation in the urban scene has recently attracted much attention due to its success in autonomous driving systems. However, the poor performance of concerned foreground targets, e.g., traffic lights and poles, still limits its further practical applications. In urban scenes, foreground targets are always concealed in their surrounding stuff because of the special camera position and 3D perspective projection. What's worse, it exacerbates the unbalance between foreground and background classes in high-level features due to the continuous expansion of the reception field. We call it Feature Camouflage. In this paper, we present a novel add-on module, named Feature Balance Network (FBNet), to eliminate the feature camouflage in urban-scene segmentation. FBNet consists of two key components, i.e., Block-wise BCE(BwBCE) and Dual Feature Modulator(DFM). BwBCE serves as an auxiliary loss to ensure uniform gradients for foreground classes and their surroundings during backpropagation. At the same time, DFM intends to enhance the deep representation of foreground classes in high-level features adaptively under the supervision of BwBCE. These two modules facilitate each other as a whole to ease feature camouflage effectively. Our proposed method achieves a new state-of-the-art segmentation performance on two challenging urban-scene benchmarks, i.e., Cityscapes and BDD100K. Code will be released for reproduction.
翻译:城市景色的图像分割最近因其在自主驱动系统中的成功而引起人们的极大关注。 但是,由于城市景色的图像分割最近因其在自主驱动系统中的成功而引起人们的极大关注。 但是,相关的前景目标,例如交通灯和电线杆的性能不佳,仍然限制了其进一步的实际应用。 在城市景色中,前景目标总是隐藏在周围的东西中,因为特殊的摄像头位置和3D视角投影。更糟糕的是,由于接收场的不断扩展,这加剧了地表层和背景类之间在高层次特征中的不平衡。我们称它为“FaterK Camouflafle ” 。在本文中,我们提出了一个新的附加模块,称为“FBBween平衡网络”(FBNet),以消除城市景色分割中的隐蔽伪装。FBBNet由两个关键组成部分组成,即“CEblock-B(BwB)”和“DFWB(D)-B(D)-deal-deal-levelopment)两个新的成本模块,将有效促进我们城市地表层平级的深度展示。在两个高级城市平面的模型中,将使得每个城市平整地平面的模型的模型结构结构结构平整。