Bottom-up top-down cues for weakly-supervised semantic segmentation

We consider the task of learning a classifier for semantic segmentation using weak supervision in the form of image labels specifying objects present in the image. Our method uses deep convolutional neural networks (cnns) and adopts an Expectation-Maximization (EM) based approach. We focus on the fo...

Cijeli opis

Bibliografski detalji
Glavni autori: Hou, Q, Massiceti, D, Dokania, P, Wei, Y, Cheng, M, Torr, P
Format: Conference item
Izdano: Springer, Cham 2018

Slični predmeti