DeepAI AI Chat
Log In Sign Up

Unsupervised Superpixel Generation using Edge-Sparse Embedding

by   Jakob Geusen, et al.

Partitioning an image into superpixels based on the similarity of pixels with respect to features such as colour or spatial location can significantly reduce data complexity and improve subsequent image processing tasks. Initial algorithms for unsupervised superpixel generation solely relied on local cues without prioritizing significant edges over arbitrary ones. On the other hand, more recent methods based on unsupervised deep learning either fail to properly address the trade-off between superpixel edge adherence and compactness or lack control over the generated number of superpixels. By using random images with strong spatial correlation as input, , blurred noise images, in a non-convolutional image decoder we can reduce the expected number of contrasts and enforce smooth, connected edges in the reconstructed image. We generate edge-sparse pixel embeddings by encoding additional spatial information into the piece-wise smooth activation maps from the decoder's last hidden layer and use a standard clustering algorithm to extract high quality superpixels. Our proposed method reaches state-of-the-art performance on the BSDS500, PASCAL-Context and a microscopy dataset.


page 2

page 4

page 7

page 8

page 12

page 15

page 16

page 17


Combining contextual and local edges for line segment extraction in cluttered images

Automatic extraction methods typically assume that line segments are pro...

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling

We propose a novel deep architecture, SegNet, for semantic pixel wise im...

Spatial Feature Extraction in Airborne Hyperspectral Images Using Local Spectral Similarity

Local spectral similarity (LSS) algorithm has been developed for detecti...

A novel centroid update approach for clustering-based superpixel method and superpixel-based edge detection

Superpixel is widely used in image processing. And among the methods for...

Cartoon Explanations of Image Classifiers

We present CartoonX (Cartoon Explanation), a novel model-agnostic explan...

Unsupervised Deep Features for Privacy Image Classification

Sharing images online poses security threats to a wide range of users du...