Rethinking Atrous Convolution for Semantic Image Segmentation — mentioned by andreykurenkov

Mon, 12 Mar 2018 20:32:44 GMT

Link to Arxiv (DeepLabv1): https://arxiv.org/abs/1606.00915 Link to Arxiv (DeepLabv3): https://arxiv.org/abs/1706.05587 Link to GitHub: https://github.com/tensorflow/models/tree/master/research/de... The README on there has a very neat TLDR of the model: "DeepLabv1 [1]: We use atrous convolution ['s a shorthand for convolution with upsampled filter'] to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. DeepLabv2 [2]: We use atrous spatial pyramid pooling (ASPP) ['a computationally efficient scheme of resampling a given feature…

Paper and discussion history. A mention is not an endorsement.

Rethinking Atrous Convolution for Semantic Image Segmentation · HackerPapers discussions

Rethinking Atrous Convolution for Semantic Image Segmentation — mentioned by andreykurenkov