Autoregressive Unsupervised Image Segmentation

07/16/2020
by   Yassine Ouali, et al.
0

In this work, we propose a new unsupervised image segmentation approach based on mutual information maximization between different constructed views of the inputs. Taking inspiration from autoregressive generative models that predict the current pixel from past pixels in a raster-scan ordering created with masked convolutions, we propose to use different orderings over the inputs using various forms of masked convolutions to construct different views of the data. For a given input, the model produces a pair of predictions with two valid orderings, and is then trained to maximize the mutual information between the two outputs. These outputs can either be low-dimensional features for representation learning or output clusters corresponding to semantic labels for clustering. While masked convolutions are used during training, in inference, no masking is applied and we fall back to the standard convolution where the model has access to the full input. The proposed method outperforms current state-of-the-art on unsupervised image segmentation. It is simple and easy to implement, and can be extended to other visual tasks and integrated seamlessly into existing unsupervised learning methods requiring different views of the data.

READ FULL TEXT

page 22

page 24

page 25

page 26

research
10/07/2021

InfoSeg: Unsupervised Semantic Image Segmentation with Mutual Information Maximization

We propose a novel method for unsupervised semantic image segmentation b...
research
07/17/2018

Invariant Information Distillation for Unsupervised Image Segmentation and Clustering

We present a new method that learns to segment and cluster images withou...
research
04/11/2018

Unsupervised Pathology Image Segmentation Using Representation Learning with Spherical K-means

This paper presents a novel method for unsupervised segmentation of path...
research
10/21/2022

Unsupervised Image Semantic Segmentation through Superpixels and Graph Neural Networks

Unsupervised image segmentation is an important task in many real-world ...
research
06/03/2019

Learning Representations by Maximizing Mutual Information Across Views

We propose an approach to self-supervised representation learning based ...
research
10/14/2020

Viewmaker Networks: Learning Views for Unsupervised Representation Learning

Many recent methods for unsupervised representation learning involve tra...
research
06/08/2022

Orthonormal Convolutions for the Rotation Based Iterative Gaussianization

In this paper we elaborate an extension of rotation-based iterative Gaus...

Please sign up or login with your details

Forgot password? Click here to reset