Instance Segmentation and Tracking with Cosine Embeddings and Recurrent Hourglass Networks

TL;DR

This paper introduces a recurrent hourglass network with cosine embedding loss for improved instance segmentation and tracking in videos, demonstrating state-of-the-art results across multiple datasets.

Contribution

It presents a novel recurrent fully convolutional architecture integrating ConvGRU and a cosine similarity-based embedding loss for consistent instance tracking.

Findings

Outperforms non-recurrent networks in cardiac MRI segmentation.

Effective in segmenting plant leaves in still images.

Achieves state-of-the-art results on ISBI celltracking datasets.

Abstract

Different to semantic segmentation, instance segmentation assigns unique labels to each individual instance of the same class. In this work, we propose a novel recurrent fully convolutional network architecture for tracking such instance segmentations over time. The network architecture incorporates convolutional gated recurrent units (ConvGRU) into a stacked hourglass network to utilize temporal video information. Furthermore, we train the network with a novel embedding loss based on cosine similarities, such that the network predicts unique embeddings for every instance throughout videos. Afterwards, these embeddings are clustered among subsequent video frames to create the final tracked instance segmentations. We evaluate the recurrent hourglass network by segmenting left ventricles in MR videos of the heart, where it outperforms a network that does not incorporate video information. Furthermore, we show applicability of the cosine embedding loss for segmenting leaf instances on still images of plants. Finally, we evaluate the framework for instance segmentation and tracking on six datasets of the ISBI celltracking challenge, where it shows state-of-the-art performance.