[IPOL discuss] [IPOL announce] new article: Semantic Segmentation: A Zoology of Deep Architectures

[announcements about the IPOL journal]

A new article is available in IPOL: https://www.ipol.im/pub/art/2023/447/

Aitor Artola,
Semantic Segmentation: A Zoology of Deep Architectures,
Image Processing On Line, 13 (2023), pp. 167–182.
https://doi.org/10.5201/ipol.2023.447

Abstract
In this paper we review the evolution of deep architectures for semantic 
segmentation. The first successful model was fully convolutional network 
(FCN) published in CVPR in 2015. Since then, the subject has become very 
popular and many methods have been published, mainly proposing 
improvements of FCN. We describe in detail the Pyramid Scene Parsing 
Network (PSPnet) and DeepLabV3, in addition to FCN, which provide a 
multi-scale description and increase the resolution of segmentation. In 
recent years, convolutional architectures have reached a bottleneck and 
have been surpassed by transformers from natural language processing 
(NLP), even though these models are generally larger and slower. We have 
chosen to discuss about the Segmentation Transformer (SETR), a first 
architecture with a transformer backbone. We also discuss SegFormer, 
that includes a multi-scale interpretation and tricks to decrease the 
size and inference time of the network. The networks presented in the 
demo come from the MM-Segmentation library, an open source semantic 
segmentation toolbox based on PyTorch. We propose to compare these 
methods qualitatively on individual images, and not on global metrics on 
databases as is usually the case. We compare these architectures on 
images outside of their training set. We also invite the readers to make 
their own comparison and derive their own conclusions.




--
IPOL - Image Processing On Line   - http://ipol.im/

contact     edit at ipol.im          - http://www.ipol.im/meta/contact/
news+feeds  twitter @IPOL_journal - http://www.ipol.im/meta/feeds/
announces   announce at list.ipol.im - http://tools.ipol.im/mm/announce/
discussions discuss at list.ipol.im  - http://tools.ipol.im/mm/discuss/