We introduce a new 'bilateral inception' module that can be inserted in existing CNN architectures and performs bilateral filtering, at multiple feature-scales, between superpixels in an image.
Recent deep learning approaches have incorporated CRFs into Convolutional Neural Networks (CNNs), with some even training the CRF end-to-end with the rest of the network.
The proposed network produces a high quality segmentation of a single image by leveraging information from additional views of the same scene.
Quantitative and qualitative evaluation on a number of computer vision applications was conducted, demonstrating that the proposed method is the top performer.
Focusing on the problem of strictly unsupervised video object segmentation, we devise a method called supervoxel gerrymandering that links masks of foregroundness and backgroundness via local and non-local consensus measures.
In this paper, we present a Robust Interpolation method of Correspondences (called RicFlow) to overcome the weakness.
Hence, we propose a curriculum-style learning approach to minimize the domain gap in urban scenery semantic segmentation.
Most of the approaches for indoor RGBD semantic la- beling focus on using pixels or superpixels to train a classi- fier.
Image segmentation is widely used as an initial phase of many image analysis tasks.
Region growing is a classical image segmentation method based on hierarchical region aggregation using local similarity rules.