Unsupervised Instance Segmentation with Superpixels
Instance segmentation is essential for numerous computer vision applications, including robotics, human-computer interaction, and autonomous driving. Currently, popular models bring impressive performance in instance segmentation by training with a large number of human annotations, which are costly to collect. For this reason, we present a new framework that efficiently and effectively segments objects without the need for human annotations. Firstly, a MultiCut algorithm is applied to self-supervised features for coarse mask segmentation. Then, a mask filter is employed to obtain high-quality coarse masks. To train the segmentation network, we compute a novel superpixel-guided mask loss, comprising hard loss and soft loss, with high-quality coarse masks and superpixels segmented from low-level image features. Lastly, a self-training process with a new adaptive loss is proposed to improve the quality of predicted masks. We conduct experiments on public datasets in instance segmentation and object detection to demonstrate the effectiveness of the proposed framework. The results show that the proposed framework outperforms previous state-of-the-art methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Unsupervised Instance SegmentationAutonomous DrivingObject DetectionSimilar Papers 제목 키워드 기반
Supervised and unsupervised segmentation using superpixels, model estimation, and Graph Cut.
Image segmentation is widely used as an initial phase of many image analysis tasks. It is often advantageous to first group pixels into compact, edge-respecting superpixels, because these reduce the size of the segmentat…
Image SegmentationSegmentationSemantic SegmentationSuperpixelsDeep Superpixel Cut for Unsupervised Image Segmentation
Image segmentation, one of the most critical vision tasks, has been studied for many years. Most of the early algorithms are unsupervised methods, which use hand-crafted features to divide the image into many regions. Re…
ClusteringImage SegmentationSegmentationSemantic Segmentation+2A regularization-based approach for unsupervised image segmentation
We propose a novel unsupervised image segmentation algorithm, which aims to segment an image into several coherent parts. It requires no user input, no supervised learning phase and assumes an unknown number of segments.…
Image SegmentationSemantic SegmentationSuperpixelsUnsupervised Image SegmentationSuperpixel Segmentation via Convolutional Neural Networks with Regularized Information Maximization
We propose an unsupervised superpixel segmentation method by optimizing a randomly-initialized convolutional neural network (CNN) in inference time. Our method generates superpixels via CNN from a single image without an…
SegmentationSuperpixelsUnsupervised Segmentation of Hyperspectral Remote Sensing Images with Superpixels
In this paper, we propose an unsupervised method for hyperspectral remote sensing image segmentation. The method exploits the mean-shift clustering algorithm that takes as input a preliminary hyperspectral superpixels se…
ClusteringImage SegmentationSegmentationSemantic Segmentation+1