Recurrent Instance Segmentation

TL;DR

This paper introduces a novel end-to-end recurrent neural network approach for instance segmentation that sequentially detects and segments objects, effectively handling occlusions and outperforming existing methods on multiple datasets.

Contribution

It proposes a new paradigm for instance segmentation using a recurrent model with spatial memory, enabling joint learning and sequential object segmentation.

Findings

Outperforms recent methods on multiple person segmentation datasets.

Achieves state-of-the-art results on the Plant Phenotyping dataset for leaf counting.

Demonstrates effective occlusion handling through spatial memory.

Abstract

Instance segmentation is the problem of detecting and delineating each distinct object of interest appearing in an image. Current instance segmentation approaches consist of ensembles of modules that are trained independently of each other, thus missing opportunities for joint learning. Here we propose a new instance segmentation paradigm consisting in an end-to-end method that learns how to segment instances sequentially. The model is based on a recurrent neural network that sequentially finds objects and their segmentations one at a time. This net is provided with a spatial memory that keeps track of what pixels have been explained and allows occlusion handling. In order to train the model we designed a principled loss function that accurately represents the properties of the instance segmentation problem. In the experiments carried out, we found that our method outperforms recent approaches on multiple person segmentation, and all state of the art approaches on the Plant Phenotyping dataset for leaf counting.