用于无监督图像分割的像素级聚类网络
Pixel-Level Clustering Network for Unsupervised Image Segmentation
AI总结：
本文提出一种无需真实标注的像素级聚类框架，通过特征嵌入、超像素分割及多级一致性训练策略实现无监督图像分割，并在三个公开数据集上超越现有最先进方法。
摘要：
尽管图像分割在自动驾驶、抓取和机器人导航等各种计算机视觉应用中至关重要，但在像素级为训练标注所有对象几乎是不可能的。因此，研究无监督图像分割方法至关重要。本文提出了一个像素级聚类框架，无需使用真实标注即可将图像分割为多个区域。该框架包含带有注意力机制的特征嵌入模块、特征统计计算模块、图像重建和超像素分割，以实现准确的无监督分割。此外，我们提出了一种训练策略，利用每个超像素内部的致性、相邻超像素之间的相似性/不相似性以及图像间的结构相似性。为避免基于超像素的损失导致过度分割，我们还提出了一种后处理方法。此外，我们扩展了该方法以实现无监督语义分割。我们在三个公开数据集（Berkeley分割数据集、PASCAL VOC 2012数据集和COCO-Stuff数据集）上进行了实验，以证明该框架的有效性。实验结果表明，该框架优于之前的最先进方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
