paper-with-me

Papers

Superpixel Segmentation via Convolutional Neural Networks with Regularized Information Maximization

2020-02-17 · Teppei Suzuki

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 any labels by minimizing a proposed objective function for superpixel segmentation in inference time. There are three advantages to our method compared with many of existing methods: (i) leverages an image prior of CNN for superpixel segmentation, (ii) adaptively changes the number of superpixels according to the given images, and (iii) controls the property of superpixels by adding an auxiliary cost to the objective function. We verify the advantages of our method quantitatively and qualitatively on BSDS500 and SBD datasets.

📄 PDF Abstract BibTeX arXiv:2002.06765

Code (1)

DensoITLab/ss-with-RIM 공식 구현 pytorch

Tasks

SegmentationSuperpixels

Methods 이 논문이 사용한 방법론

Spatial Broadcast Decoder Spatial Broadcast Decoder is an architecture that aims to improve disentangling, reconstruction accuracy, and generalization to held-out regions in data space. It provides a…

Similar Papers 제목 키워드 기반

Implicit Integration of Superpixel Segmentation into Fully Convolutional Networks

2021-03-05 · Teppei Suzuki

Superpixels are a useful representation to reduce the complexity of image data. However, to combine superpixels with convolutional neural networks (CNNs) in an end-to-end fashion, one requires extra models to generate su…

Depth EstimationMonocular Depth EstimationSegmentationSemantic Segmentation+1

A regularization-based approach for unsupervised image segmentation

2016-03-08 · Aleksandar Dimitriev, Matej Kristan

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 Segmentation

Supervised and unsupervised segmentation using superpixels, model estimation, and Graph Cut.

2017-11-06 · SPIE Journal of Electronic Imaging 2017 11 · Jiří Borovec, Jan Švihlík, Jan Kybic, David Habart

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 SegmentationSuperpixels

Unsupervised Image Semantic Segmentation through Superpixels and Graph Neural Networks

2022-10-21 · Moshe Eliasof, Nir Ben Zikri, Eran Treister

Unsupervised image segmentation is an important task in many real-world scenarios where labelled data is of scarce availability. In this paper we propose a novel approach that harnesses recent advances in unsupervised le…

Image SegmentationSegmentationSemantic SegmentationSuperpixels+2

Visual Object Tracking by Segmentation with Graph Convolutional Network

2020-09-05 · Bo Jiang, Panpan Zhang, Lili Huang

Segmentation-based tracking has been actively studied in computer vision and multimedia. Superpixel based object segmentation and tracking methods are usually developed for this task. However, they independently perform …

ObjectObject TrackingSegmentationSemantic Segmentation+2