Multi-Scale Context Aggregation by Dilated Convolutions

[guanfuchen]

related paper

摘要

State-of-the-art models for semantic segmentation are based on adaptations of convolutional networks that had originally been designed for image classification. However, dense prediction problems such as semantic segmentation are structurally different from image classification. In this work, we develop a new convolutional network module that is specifically designed for dense prediction. The presented module uses dilated convolutions to systematically aggregate multi-scale contextual information without losing resolution. The architecture is based on the fact that dilated convolutions support exponential expansion of the receptive field without loss of resolution or coverage. We show that the presented context module increases the accuracy of state-of-the-art semantic segmentation systems. In addition, we examine the adaptation of image classification networks to dense prediction and show that simplifying the adapted network can increase accuracy.

[guanfuchen]

空洞卷积原理

[guanfuchen]

多尺度上下文聚合单元

该单元需要不同的初始化策略

Caffe模型中的可视化

[guanfuchen]

结果

使用了空洞卷积作为前端的结果更为精细

数据集上的性能比较

[guanfuchen]

总结与展望