Adaptive Context Encoding Module for Semantic Segmentation
This work addresses the need for adaptive context aggregation in semantic segmentation, offering an incremental improvement over manual design methods.
The paper tackles the problem of capturing multi-scale context information for semantic segmentation by proposing an Adaptive Context Encoding (ACE) module based on deformable convolution, which outperforms existing methods like PPM and ASPP in terms of mIoU on Pascal-Context and ADE20K datasets.
The object sizes in images are diverse, therefore, capturing multiple scale context information is essential for semantic segmentation. Existing context aggregation methods such as pyramid pooling module (PPM) and atrous spatial pyramid pooling (ASPP) design different pooling size or atrous rate, such that multiple scale information is captured. However, the pooling sizes and atrous rates are chosen manually and empirically. In order to capture object context information adaptively, in this paper, we propose an adaptive context encoding (ACE) module based on deformable convolution operation to argument multiple scale information. Our ACE module can be embedded into other Convolutional Neural Networks (CNN) easily for context aggregation. The effectiveness of the proposed module is demonstrated on Pascal-Context and ADE20K datasets. Although our proposed ACE only consists of three deformable convolution blocks, it outperforms PPM and ASPP in terms of mean Intersection of Union (mIoU) on both datasets. All the experiment study confirms that our proposed module is effective as compared to the state-of-the-art methods.