In this assignment's first question, we implemented a convolutional neural network for semantic segmentation. Semantic segmentation is used in various domains, such as scene understanding, inferring support relationships among objects, and autonomous driving. In this assignment, we used the SegNet[1] architecture to be implemented. We use the CamVid road scenes dataset to evaluate our segmentation network. It includes 711 RGB images at 720 * 960 resolution.
[1] V. Badrinarayanan, A. Kendall and R. Cipolla, "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 12, pp. 2481-2495, 1 Dec. 2017, doi: 10.1109/TPAMI.2016.2644615.
Camvid dataset: https://s3.amazonaws.com/fast-ai-imagelocal/camvid.tgz http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/data/LabeledApproved_full.zip