Semantic Segmentation with Second-Order Pooling

Weakly Supervised Semantic Segmentation Using Superpixel Pooling Network

We propose a weakly supervised semantic segmentation algorithm based on deep neural networks, which relies on imagelevel class labels only. The proposed algorithm alternates between generating segmentation annotations and learning a semantic segmentation network using the generated annotations. A key determinant of success in this framework is the capability to construct reliable initial annota...

Face Identification with Second-Order Pooling

Automatic face recognition has received significant performance improvement by developing specialised facial image representations. On the other hand, generic object recognition has rarely been applied to the face recognition. Spatial pyramid pooling of features encoded by an over-complete dictionary has been the key component of many state-of-the-art image classification systems. Inspired by i...

STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling Supplementary Material

In the supplementary material, we present the analysis of semantic boundary accurary in Section 1. In section 2, we evaluate the oracle performance on NYUDv2 40-class task with our spatio-temporal data-driven pooling. In section 3, we analyze the groundtruth annotations of the NYUDv2 40class task. In section 4, we provide the qualitative results of the semantic segmentation results of the NYUDv...

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradual...

Pooling-free fully convolutional networks with dense skip connections for semantic segmentation, with application to segmentation of white matter lesions