RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
This work addresses resolution degradation in semantic segmentation for computer vision applications, representing a strong incremental improvement over existing methods.
The paper tackles the problem of resolution loss in deep CNNs for semantic segmentation by introducing RefineNet, a multi-path refinement network that uses long-range residual connections to combine high-level semantic features with fine-grained details, achieving state-of-the-art results including an 83.4 intersection-over-union score on PASCAL VOC 2012.
Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated subsampling operations like pooling or convolution striding in deep CNNs lead to a significant decrease in the initial image resolution. Here, we present RefineNet, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections. In this way, the deeper layers that capture high-level semantic features can be directly refined using fine-grained features from earlier convolutions. The individual components of RefineNet employ residual connections following the identity mapping mindset, which allows for effective end-to-end training. Further, we introduce chained residual pooling, which captures rich background context in an efficient manner. We carry out comprehensive experiments and set new state-of-the-art results on seven public datasets. In particular, we achieve an intersection-over-union score of 83.4 on the challenging PASCAL VOC 2012 dataset, which is the best reported result to date.