arXiv (Cornell University)· 2017· Preprint
Rethinking Atrous Convolution for Semantic Image Segmentation
- 7,457citations
- 2017year
Short summary
DeepLabv3 introduces a novel system for semantic image segmentation that captures multi-scale context using cascaded or parallel atrous convolutions with multiple rates, and enhances it with image-level global context features.
AI-generated from the title and abstract; the full text is not read.
Key points
- Atrous convolution is used to explicitly adjust filter's field-of-view and control feature resolution in Deep Convolutional Neural Networks.
- A system is designed to capture multi-scale context by employing atrous convolutions in cascade or parallel with multiple atrous rates.
- The Atrous Spatial Pyramid Pooling module is augmented with image-level features for improved performance.
- The DeepLabv3 system achieves state-of-the-art results on the PASCAL VOC 2012 semantic image segmentation benchmark.
AI-generated from the title and abstract; the full text is not read.
Abstract
In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of semantic image segmentation. To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates. Furthermore, we propose to augment our previously proposed Atrous Spatial Pyramid Pooling module, which probes convolutional features at multiple scales, with image-level features encoding global context and further boost performance. We also elaborate on implementation details and share our experience on training our system. The proposed `DeepLabv3' system significantly improves over our previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.
The authors' abstract, as published at the source. arXiv (Cornell University), 2017 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science