Learning the Superpixel in a Non-iterative and Lifelong Manner

by   Lei Zhu, et al.

Superpixel is generated by automatically clustering pixels in an image into hundreds of compact partitions, which is widely used to perceive the object contours for its excellent contour adherence. Although some works use the Convolution Neural Network (CNN) to generate high-quality superpixel, we challenge the design principles of these networks, specifically for their dependence on manual labels and excess computation resources, which limits their flexibility compared with the traditional unsupervised segmentation methods. We target at redefining the CNN-based superpixel segmentation as a lifelong clustering task and propose an unsupervised CNN-based method called LNS-Net. The LNS-Net can learn superpixel in a non-iterative and lifelong manner without any manual labels. Specifically, a lightweight feature embedder is proposed for LNS-Net to efficiently generate the cluster-friendly features. With those features, seed nodes can be automatically assigned to cluster pixels in a non-iterative way. Additionally, our LNS-Net can adapt the sequentially lifelong learning by rescaling the gradient of weight based on both channel and spatial context to avoid overfitting. Experiments show that the proposed LNS-Net achieves significantly better performance on three benchmarks with nearly ten times lower complexity compared with other state-of-the-art methods.


page 4

page 8


SRG-Net: Unsupervised Segmentation for Terracotta Warrior Point Cloud with 3D Pointwise CNN methods

In this paper, we present a seed-region-growing CNN(SRG-Net) for unsuper...

W-Net: A CNN-based Architecture for White Blood Cells Image Classification

Computer-aided methods for analyzing white blood cells (WBC) have become...

GPU-Net: Lightweight U-Net with more diverse features

Image segmentation is an important task in the medical image field and m...

An Efficient Pattern Mining Convolution Neural Network (CNN) algorithm with Grey Wolf Optimization (GWO)

Automation of feature analysis in the dynamic image frame dataset deals ...

Unsupervised Segmentation for Terracotta Warrior with Seed-Region-Growing CNN(SRG-Net)

The repairing work of terracotta warriors in Emperor Qinshihuang Mausole...

CEU-Net: Ensemble Semantic Segmentation of Hyperspectral Images Using Clustering

Most semantic segmentation approaches of Hyperspectral images (HSIs) use...

Please sign up or login with your details

Forgot password? Click here to reset