Improving Pixel Embedding Learning through Intermediate Distance Regression Supervision for Instance Segmentation

TL;DR

This paper introduces an improved pixel embedding learning method for instance segmentation that incorporates a distance regression module, significantly enhancing segmentation accuracy and achieving top results on a challenging benchmark.

Contribution

It proposes a novel architecture with a distance regression module that boosts embedding learning effectiveness and clustering speed for instance segmentation.

Findings

mSBD scores improved by over 8% with the new method

Achieved the best overall result on the CVPPP Leaf Segmentation Challenge

Features from the regression module enhance embedding accuracy

Abstract

As a proposal-free approach, instance segmentation through pixel embedding learning and clustering is gaining more emphasis. Compared with bounding box refinement approaches, such as Mask R-CNN, it has potential advantages in handling complex shapes and dense objects. In this work, we propose a simple, yet highly effective, architecture for object-aware embedding learning. A distance regression module is incorporated into our architecture to generate seeds for fast clustering. At the same time, we show that the features learned by the distance regression module are able to promote the accuracy of learned object-aware embeddings significantly. By simply concatenating features of the distance regression module to the images as inputs of the embedding module, the mSBD scores on the CVPPP Leaf Segmentation Challenge can be further improved by more than 8% compared to the identical set-up without concatenation, yielding the best overall result amongst the leaderboard at CodaLab.