Refining Semantic Segmentation with Superpixel by Transparent Initialization and Sparse Encoder
This work addresses edge refinement in semantic segmentation for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of inaccurate edges in semantic segmentation by jointly learning with trainable superpixels, using Transparent Initialization and a sparse encoder to preserve pretrained network effects and reduce computational costs, resulting in outperforming state-of-the-art methods on datasets like PASCAL VOC 2012 with enhanced edge accuracy.
Although deep learning greatly improves the performance of semantic segmentation, its success mainly lies in object central areas without accurate edges. As superpixels are a popular and effective auxiliary to preserve object edges, in this paper, we jointly learn semantic segmentation with trainable superpixels. We achieve it with fully-connected layers with Transparent Initialization (TI) and efficient logit consistency using a sparse encoder. The proposed TI preserves the effects of learned parameters of pretrained networks. This avoids a significant increase of the loss of pretrained networks, which otherwise may be caused by inappropriate parameter initialization of the additional layers. Meanwhile, consistent pixel labels in each superpixel are guaranteed by logit consistency. The sparse encoder with sparse matrix operations substantially reduces both the memory requirement and the computational complexity. We demonstrated the superiority of TI over other parameter initialization methods and tested its numerical stability. The effectiveness of our proposal was validated on PASCAL VOC 2012, ADE20K, and PASCAL Context showing enhanced semantic segmentation edges. With quantitative evaluations on segmentation edges using performance ratio and F-measure, our method outperforms the state-of-the-art.