Abstract
We propose a novel semantic segmentation algorithm by learning a deep deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net. The deconvolution network is composed of deconvolution and unpooling layers, which identify pixelwise class labels and predict segmentation masks. We apply the trained network to each proposal in an input image, and construct the final semantic segmentation map by combining the results from all proposals in a simple manner. The proposed algorithm mitigates the limitations of the existing methods based on fully convolutional networks by integrating deep deconvolution network and proposal-wise prediction, our segmentation method typically identifies detailed structures and handles objects in multiple scales naturally. Our network demonstrates outstanding performance in PASCAL VOC 2012 dataset, and we achieve the best accuracy (72.5%) among the methods trained without using Microsoft COCO dataset through ensemble with the fully convolutional network.
Keywords
DeconvolutionComputer sciencePascal (unit)SegmentationArtificial intelligenceConvolution (computer science)Pattern recognition (psychology)Convolutional neural networkDeep learningImage segmentationData miningMachine learningAlgorithmArtificial neural network
Affiliated Institutions
Related Publications
Fully convolutional networks for semantic segmentation
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, ex...
Segment Anything
We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest ...
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite complex. Despite this, ...
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
Convolutional neural networks (CNN) have recently shown outstanding image classification performance in the large- scale visual recognition challenge (ILSVRC2012). The success o...
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that...
Publication Info
- Year
- 2015
- Type
- preprint
- Citations
- 3978
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
3978
OpenAlex
Cite This
Hyeonwoo Noh,
Seunghoon Hong,
Bohyung Han
(2015).
Learning Deconvolution Network for Semantic Segmentation.
.
https://doi.org/10.1109/iccv.2015.178
Identifiers
- DOI
- 10.1109/iccv.2015.178