Improving residual block for semantic image segmentation

F Liu, J Liu, J Fu, LU Hanqing - 2018 IEEE Fourth International …, 2018 - ieeexplore.ieee.org
F Liu, J Liu, J Fu, LU Hanqing
2018 IEEE Fourth International Conference on Multimedia Big Data …, 2018ieeexplore.ieee.org
Currently, most state-of-the-art semantic segmentation methods employ residual network as
base network. Residual network is composed of residual blocks. In this paper, we present an
improved residual block called pyramid residual block to explicitly exploit context information
and enhance useful features. In contrast to the standard residual block, the proposed
pyramid residual block contains two newly added components: pyramid pooling module and
attention mechanism. The former aggregates different-region-based context information …
Currently, most state-of-the-art semantic segmentation methods employ residual network as base network. Residual network is composed of residual blocks. In this paper, we present an improved residual block called pyramid residual block to explicitly exploit context information and enhance useful features. In contrast to the standard residual block, the proposed pyramid residual block contains two newly added components: pyramid pooling module and attention mechanism. The former aggregates different-region-based context information. And the latter is able to adaptively re-calibrate feature responses through element-wise multiplication operation, thus enhancing useful features and suppressing less useful ones. Our proposed pyramid residual block demonstrates outstanding performance in PASCAL VOC 2012 segmentation datasets, and improve the segmentation accuracy by a large margin over the standard residual block.
ieeexplore.ieee.org
以上显示的是最相近的搜索结果。 查看全部搜索结果