Fully convolutional networks for semantic segmentation
Jonathan Long,Evan Shelhamer,Trevor Darrell +2 more
- pp 3431-3440
TLDR
The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.Abstract:
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, exceed the state-of-the-art in semantic segmentation. Our key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet [20], the VGG net [31], and GoogLeNet [32]) into fully convolutional networks and transfer their learned representations by fine-tuning [3] to the segmentation task. We then define a skip architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves state-of-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes less than one fifth of a second for a typical image.read more
Citations
More filters
Proceedings ArticleDOI
Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation
TL;DR: In this article, a generic classification network equipped with convolutional blocks of different dilated rates was designed to produce dense and reliable object localization maps and effectively benefit both weakly and semi-supervised semantic segmentation.
Posted Content
High-Resolution Representations for Labeling Pixels and Regions
Ke Sun,Yang Zhao,Borui Jiang,Tianheng Cheng,Bin Xiao,Dong Liu,Yadong Mu,Xinggang Wang,Wenyu Liu,Jingdong Wang +9 more
TL;DR: A simple modification is introduced to augment the high-resolution representation by aggregating the (upsampled) representations from all the parallel convolutions rather than only the representation from thehigh-resolution convolution, which leads to stronger representations, evidenced by superior results.
Journal ArticleDOI
Automated cardiovascular magnetic resonance image analysis with fully convolutional networks
Wenjia Bai,Matthew Sinclair,Giacomo Tarroni,Ozan Oktay,Martin Rajchl,Ghislain Vaillant,Aaron M. Lee,Nay Aung,Elena Lukaschuk,Mihir M. Sanghvi,Filip Zemrak,Kenneth Fung,José Miguel Paiva,Valentina Carapella,Young Jin Kim,Hideaki Suzuki,Bernhard Kainz,Paul M. Matthews,Steffen E. Petersen,Stefan K. Piechnik,Stefan Neubauer,Ben Glocker,Daniel Rueckert +22 more
TL;DR: An automated analysis method based on a fully convolutional network achieves a performance on par with human experts in analysing CMR images and deriving clinically relevant measures.
Journal ArticleDOI
AggNet: Deep Learning From Crowds for Mitosis Detection in Breast Cancer Histology Images
Shadi Albarqouni,Christoph Baur,Felix Achilles,Vasileios Belagiannis,Stefanie Demirci,Nassir Navab +5 more
TL;DR: An experimental study on learning from crowds that handles data aggregation directly as part of the learning process of the convolutional neural network (CNN) via additional crowdsourcing layer (AggNet), which gives valuable insights into the functionality of deep CNN learning from crowd annotations and proves the necessity of data aggregation integration.
Proceedings ArticleDOI
Generative Face Completion
TL;DR: Zhang et al. as mentioned in this paper proposed an effective face completion algorithm using a deep generative model, which is trained with a combination of a reconstruction loss, two adversarial losses and a semantic parsing loss to ensure pixel faithfulness and local-global contents consistency.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Book
Pattern Recognition and Machine Learning
TL;DR: Probability Distributions, linear models for Regression, Linear Models for Classification, Neural Networks, Graphical Models, Mixture Models and EM, Sampling Methods, Continuous Latent Variables, Sequential Data are studied.
Proceedings ArticleDOI
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
Book
A wavelet tour of signal processing
TL;DR: An introduction to a Transient World and an Approximation Tour of Wavelet Packet and Local Cosine Bases.