The fully convolutional network (FCN) has achieved tremendous success in dense visual recognition tasks, such as scene segmentation. The last layer of FCN is typically a global classifier (1×1 convolution) to recognize each pixel to a semantic label. We empirically show that this global classifier, ignoring the intra-class distinction, may lead to sub-optimal results. In this work, we present a conditional classifier to replace the traditional global classifier, where the kernels of the classifier are generated dynamically conditioned on the input. The main advantages of the new classifier consist of: (i) it attends on the intra-class distinction, leading to stronger dense recognition capability; (ii) the conditional classifier is simple and flexible to be integrated into almost arbitrary FCN architectures to improve the prediction. Extensive experiments demonstrate that the proposed classifier performs favourably against the traditional classifier on the FCN architecture. The framework equipped with the conditional classifier (called CondNet) achieves new state-of-the-art performances on two datasets. The code and models are available at https://git.io/CondNet.

中文翻译：

---

CondNet：场景分割的条件分类器


全卷积网络（FCN）在场景分割等密集视觉识别任务中取得了巨大成功。 FCN 的最后一层通常是全局分类器（1×1 卷积），用于将每个像素识别为语义标签。我们凭经验表明，这种全局分类器忽略了类内差异，可能会导致次优结果。在这项工作中，我们提出了一个条件分类器来代替传统的全局分类器，其中分类器的内核是根据输入动态生成的。新分类器的主要优点包括：（i）它注重类内区分，导致更强的密集识别能力； (ii) 条件分类器简单且灵活，可以集成到几乎任意的 FCN 架构中以改进预测。大量实验表明，所提出的分类器在 FCN 架构上的性能优于传统分类器。配备条件分类器（称为 CondNet）的框架在两个数据集上实现了新的最先进的性能。代码和模型可在 https://git.io/CondNet 上获取。