Invariant Information Distillation for Unsupervised Image Segmentation and Clustering

07/17/2018
by   Xu Ji, et al.
2

We present a new method that learns to segment and cluster images without labels of any kind. A simple loss based on information theory is used to extract meaningful representations directly from raw images. This is achieved by maximising mutual information of images known to be related by spatial proximity or randomized transformations, which distills their shared abstract content. Unlike much of the work in unsupervised deep learning, our learned function outputs segmentation heatmaps and discrete classifications labels directly, rather than embeddings that need further processing to be usable. The loss can be formulated as a convolution, making it the first end-to-end unsupervised learning method that learns densely and efficiently (i.e. without sampling) for semantic segmentation. Implemented using realistic settings on generic deep neural network architectures, our method attains superior performance on COCO-Stuff and ISPRS-Potsdam for segmentation and STL for clustering, beating state-of-the-art baselines.

READ FULL TEXT

page 2

page 4

page 9

research
07/01/2021

Unsupervised Image Segmentation by Mutual Information Maximization and Adversarial Regularization

Semantic segmentation is one of the basic, yet essential scene understan...
research
07/30/2021

Iterative, Deep, and Unsupervised Synthetic Aperture Sonar Image Segmentation

Deep learning has not been routinely employed for semantic segmentation ...
research
07/16/2020

Autoregressive Unsupervised Image Segmentation

In this work, we propose a new unsupervised image segmentation approach ...
research
01/16/2021

DeepMI: A Mutual Information Based Framework For Unsupervised Deep Learning of Tasks

In this work, we propose an information theory based framework DeepMI to...
research
12/05/2019

Multi-Modal Deep Clustering: Unsupervised Partitioning of Images

The clustering of unlabeled raw images is a daunting task, which has rec...
research
07/20/2020

Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering

The usage of convolutional neural networks (CNNs) for unsupervised image...
research
10/16/2019

Generalized Clustering by Learning to Optimize Expected Normalized Cuts

We introduce a novel end-to-end approach for learning to cluster in the ...

Please sign up or login with your details

Forgot password? Click here to reset