Global and Local Features through Gaussian Mixture Models on Image Semantic Segmentation

Abstract

The semantic segmentation task aims at dense classification at the pixel-wise level. Deep models exhibited progress in tackling this task. However, one remaining problem with these approaches is the loss of spatial precision, often produced at the segmented objects' boundaries. Our proposed model addresses this problem by providing an internal structure for the feature representations while extracting a global representation that supports the former. To fit the internal structure, during training, we predict a Gaussian Mixture Model from the data, which, merged with the skip connections and the decoding stage, helps avoid wrong inductive biases. Furthermore, our results show that we can improve semantic segmentation by providing both learning representations (global and local) with a clustering behavior and combining them. Finally, we present results demonstrating our advances in Cityscapes and Synthia datasets.

arXiv commentPre-print to appear in IEEE Access. Code available at https://gitlab.com/mipl/phgmm

References in corpus (17)

• Auto-Encoding Variational Bayes
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Brain Tumor Segmentation with Deep Neural Networks
• Conditional Random Fields as Recurrent Neural Networks
• ParseNet: Looking Wider to See Better
• DUNet: A deformable network for retinal vessel segmentation
• OCNet: Object Context Network for Scene Parsing
• Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation
• Dense semantic labeling of sub-decimeter resolution images with convolutional neural networks
• Hierarchical Multi-Scale Attention for Semantic Segmentation
• Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery
• Self-Supervised Model Adaptation for Multimodal Semantic Segmentation
• Automated Evaluation of Semantic Segmentation Robustness for Autonomous Driving
• Adaptive feature recombination and recalibration for semantic segmentation with Fully Convolutional Networks
• XNet: A convolutional neural network (CNN) implementation for medical X-Ray image segmentation suitable for small datasets
• Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task