Recurrent Neural Networks for Semantic Instance Segmentation

by   Amaia Salvador, et al.

We present a recurrent model for semantic instance segmentation that sequentially generates pairs of masks and their associated class probabilities for every object in an image. Our proposed system is trainable end-to-end, does not require post-processing steps on its output and is conceptually simpler than current methods relying on object proposals. We observe that our model learns to follow a consistent pattern to generate object sequences, which correlates with the activations learned in the encoder part of our network. We achieve competitive results on three different instance segmentation benchmarks (Pascal VOC 2012, Cityscapes and CVPPP Plant Leaf Segmentation). Code is available at .


page 5

page 6

page 7

page 8


Recurrent Instance Segmentation

Instance segmentation is the problem of detecting and delineating each d...

Consistent Recurrent Neural Networks for 3D Neuron Segmentation

We present a recurrent network for the 3D reconstruction of neurons that...

Reinforced Coloring for End-to-End Instance Segmentation

Instance segmentation is one of the actively studied research topics in ...

End-to-End Instance Segmentation with Recurrent Attention

While convolutional neural networks have gained impressive success recen...

ISDA: Position-Aware Instance Segmentation with Deformable Attention

Most instance segmentation models are not end-to-end trainable due to ei...

AdaptIS: Adaptive Instance Selection Network

We present Adaptive Instance Selection network architecture for class-ag...

RDCNet: Instance segmentation with a minimalist recurrent residual network

Instance segmentation is a key step for quantitative microscopy. While s...