Progressive Semantic Segmentation

by   Chuong Huynh, et al.

The objective of this work is to segment high-resolution images without overloading GPU memory usage or losing the fine details in the output segmentation map. The memory constraint means that we must either downsample the big image or divide the image into local patches for separate processing. However, the former approach would lose the fine details, while the latter can be ambiguous due to the lack of a global picture. In this work, we present MagNet, a multi-scale framework that resolves local ambiguity by looking at the image at multiple magnification levels. MagNet has multiple processing stages, where each stage corresponds to a magnification level, and the output of one stage is fed into the next stage for coarse-to-fine information propagation. Each stage analyzes the image at a higher resolution than the previous stage, recovering the previously lost details due to the lossy downsampling step, and the segmentation output is progressively refined through the processing stages. Experiments on three high-resolution datasets of urban views, aerial scenes, and medical images show that MagNet consistently outperforms the state-of-the-art methods by a significant margin.


page 1

page 4

page 5

page 6

page 7


Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images

Segmentation of ultra-high resolution images is increasingly demanded, y...

Memory-efficient Segmentation of High-resolution Volumetric MicroCT Images

In recent years, 3D convolutional neural networks have become the domina...

Learning to Rearrange Voxels in Binary Segmentation Masks for Smooth Manifold Triangulation

Medical images, especially volumetric images, are of high resolution and...

Streamlined Global and Local Features Combinator (SGLC) for High Resolution Image Dehazing

Image Dehazing aims to remove atmospheric fog or haze from an image. Alt...

HighEr-Resolution Network for Image Demosaicing and Enhancing

Neural-networks based image restoration methods tend to use low-resoluti...

RAP-Net: Coarse-to-Fine Multi-Organ Segmentation with Single Random Anatomical Prior

Performing coarse-to-fine abdominal multi-organ segmentation facilitates...

Top-Down Networks: A coarse-to-fine reimagination of CNNs

Biological vision adopts a coarse-to-fine information processing pathway...

Please sign up or login with your details

Forgot password? Click here to reset