DIC: Deep Image Clustering for Unsupervised Image Segmentation

Abstract

Unsupervised segmentation is an essential pre-processing technique in many computer vision tasks. However, current unsupervised segmentation techniques are sensitive to the parameters such as the segmentation numbers or of high training and inference complexity. Encouraged by neural networks' flexibility and their ability for modelling intricate patterns, an unsupervised segmentation framework based on a novel deep image clustering (DIC) model is proposed. The DIC consists of a feature transformation subnetwork (FTS) and a trainable deep clustering subnetwork (DCS) for unsupervised image clustering. FTS is built on a simple and capable network architecture. DCS can assign pixels with different cluster numbers by updating cluster associations and cluster centers iteratively. Moreover, a superpixel guided iterative refinement loss is designed to optimize the DIC parameters in an overfitting manner. Extensive experiments have been conducted on the Berkley Segmentation Database. The experimental results show that DCS is more effective in aggregating features during the clustering procedure. DIC has also proven to be less sensitive to varying segmentation parameters and of lower computation costs, and DIC can achieve significantly better segmentation performance compared to the state-of-the-art techniques. The source code is available on https://github.com/zmbhou/DIC.

Artificial intelligence in tumor subregion analysis based on medical imaging: A review

“…For clinical tasks for which it is difficult to obtain manually‐annotated ground truth data, unsupervised CNNs have been applied to solve the segmentation problem. Zhou et al proposed a deep image clustering model to assign pixels to different clusters by updating cluster associations and cluster centers iteratively 185 . CNN could also be used to generate radiomic signatures for various clinical applications based on tumor subregions and be used in OS prediction, treatment response prediction, and clinical risk stratification.…”

Clustering and Graph Convolution of Sub-Regions for Unsupervised Image Segmentation

“…Cheng et al [14] proposed a real-time segmentation system called Hierarchical Feature Selection (HFS) that first uses over-segmentation to acquire seed regions. Zhou and Wei [15] proposed a deep image clustering (DIC) model, which consists of a feature transformation subnetwork (FTS) and a differentiable deep clustering subnetwork (DCS) for dividing the image space into different clusters. Ilyas et al [16] proposed a CNN-based architecture for unsupervised segmentation that combined CNN architecture with a graphbased method to generate the target segments.…”

“…These methods include PEF+K-means [29], MCG [30], gPbowt-ucm [2], LGM [31], and HFS method [14]. In addition, we evaluate the proposed method with two unsupervised segmentation methods based on convolution networks: W-Net [32] and DIC [15].…”

A Robust SVM Color-Based Food Segmentation Algorithm for the Production Process of a Traditional Carasau Bread

“…[51] A large quantity of research studies have recently applied the correlation clustering framework to image segmentation, and there was a lot of effort to extract better region-based features between neighboring superpixels [52], [53], [54], [55]. Zhou and Wei [56] proposed an unsupervised segmentation framework based on a novel deep image clustering (DIC) model and the results showed that DIC is less affected by the segmentation parameter, such as cluster numbers, and of lower computation cost. The Kmeans algorithm (or Lloyd's algorithm) is the most commonly used technique in the clustering-based segmentation field.…”