Paper
ReSeg: A Recurrent Neural Network for Object Segmentation
We propose a structured prediction architecture for images centered around deep recurrent neural networks. The proposed network, called ReSeg, is based on the recently introduced ReNet model for object classification. We modify and extend it to perform object segmentation, noting that the avoidance of pooling can greatly simplify pixel-wise tasks for images. The ReSeg layer is composed of four recurrent neural networks that sweep the image horizontally and vertically in both directions, along with a final layer that expands the prediction back to the original image size. ReSeg combines multiple ReSeg layers with several possible input layers as well as a final layer which expands the prediction back to the original image size, making it suitable for a variety of structured prediction tasks. We evaluate ReSeg on the specific task of object segmentation with three widely-used image segmentation datasets, namely Weizmann Horse, Fashionista and Oxford Flower. The results suggest that ReSeg can challenge the state of the art in object segmentation, and may have further applications in structured prediction at large.
Authors: Francesco Visin · Kyle Kastner · Aaron Courville · Yoshua Bengio · Matteo Matteucci · Kyunghyun Cho