Recurrent Neural Networks for Semantic Instance Segmentation
This work addresses the problem of instance segmentation for computer vision applications, offering an end-to-end trainable alternative to proposal-based methods, though it appears incremental as it builds on existing recurrent and segmentation techniques.
The authors tackled semantic instance segmentation by proposing a recurrent model that sequentially generates binary masks and class probabilities for each object in an image, achieving results comparable to state-of-the-art methods on benchmarks like Pascal VOC 2012, CVPPP Plant Leaf Segmentation, and Cityscapes without requiring post-processing.
We present a recurrent model for semantic instance segmentation that sequentially generates binary masks and their associated class probabilities for every object in an image. Our proposed system is trainable end-to-end from an input image to a sequence of labeled masks and, compared to methods relying on object proposals, does not require post-processing steps on its output. We study the suitability of our recurrent model on three different instance segmentation benchmarks, namely Pascal VOC 2012, CVPPP Plant Leaf Segmentation and Cityscapes. Further, we analyze the object sorting patterns generated by our model and observe that it learns to follow a consistent pattern, which correlates with the activations learned in the encoder part of our network. Source code and models are available at https://imatge-upc.github.io/rsis/