Exploring deep features: deeper fully convolutional neural network for image segmentation
MetadataShow full item record
Classiﬁcation of images has been a widely regarded challenge for the past decade, but a new type of object recognition problem which deals with pixellevel segmentation is posing a more complex task for both computer vision enthusiasts and researcher alike. The convolutional neural network has become a staple for any recognition task, but a new type of ConvNet which is Fully convolutional in architecture has yielded more ﬁne features and proponents. We propose a neural net where we take VGG19 , a well-known classiﬁcation CNN, make it fully convolutional for extracting deeper features and lastly use skip-architectures for getting ﬁner output. This yields better result than the pre-existing FCN segmentation architecture [15, 25, 6]. Training was done on augmented VOC12  with SBD training data and validation set was used from reduced VOC12 validation dataset. The model scored mIOU of 68.1 percent in PASCAL VOC 2012 Segmentation challenge.