Pixel-Level Clustering Network for Unsupervised Image Segmentation

Abstract

While image segmentation is crucial in various computer vision applications, such as autonomous driving, grasping, and robot navigation, annotating all objects at the pixel-level for training is nearly impossible. Therefore, the study of unsupervised image segmentation methods is essential. In this paper, we present a pixel-level clustering framework for segmenting images into regions without using ground truth annotations. The proposed framework includes feature embedding modules with an attention mechanism, a feature statistics computing module, image reconstruction, and superpixel segmentation to achieve accurate unsupervised segmentation. Additionally, we propose a training strategy that utilizes intra-consistency within each superpixel, inter-similarity/dissimilarity between neighboring superpixels, and structural similarity between images. To avoid potential over-segmentation caused by superpixel-based losses, we also propose a post-processing method. Furthermore, we present an extension of the proposed method for unsupervised semantic segmentation. We conducted experiments on three publicly available datasets (Berkeley segmentation dataset, PASCAL VOC 2012 dataset, and COCO-Stuff dataset) to demonstrate the effectiveness of the proposed framework. The experimental results show that the proposed framework outperforms previous state-of-the-art methods.

13 pages

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering
• W-Net: A Deep Model for Fully Unsupervised Image Segmentation
• Unsupervised Semantic Segmentation by Distilling Feature Correspondences
• Depth Adaptive Deep Neural Network for Semantic Segmentation
• Random Forest with Learned Representations for Semantic Segmentation