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
Journal ArticleDOI
Semantic segmentation of aerial images with an ensemble of cnns
Dimitrios Marmanis,Dimitrios Marmanis,Jan Dirk Wegner,Silvano Galliani,Konrad Schindler,Mihai Datcu,Uwe Stilla +6 more
TL;DR: A FCN is designed which takes as input intensity and range data and, with the help of aggressive deconvolution and recycling of early network layers, converts them into a pixelwise classification at full resolution, and discusses design choices and intricacies of such a network.
Proceedings ArticleDOI
Recurrent Attentional Networks for Saliency Detection
TL;DR: Zhang et al. as discussed by the authors proposed a recurrent attentional convolutional-deconvolutional network (RACDNN) which uses spatial transformer and recurrent network units to iteratively attend to selected image subregions to perform saliency refinement progressively.
Proceedings ArticleDOI
Categorical Depth Distribution Network for Monocular 3D Object Detection
TL;DR: Categorical Depth Distribution Network (CaDDN) as mentioned in this paper uses a predicted categorical depth distribution for each pixel to project rich contextual feature information to the appropriate depth interval in 3D space.
Journal ArticleDOI
Monocular human pose estimation: A survey of deep learning-based methods
TL;DR: This survey extensively reviews the recent deep learning-based 2D and 3D human pose estimation methods published since 2014 and summarizes the challenges, main frameworks, benchmark datasets, evaluation metrics, performance comparison, and discusses some promising future research directions.
Book ChapterDOI
Regressing Heatmaps for Multiple Landmark Localization Using CNNs
TL;DR: Evaluation of different architectures on 2D and 3D hand image datasets show that heatmap regression based on CNNs achieves state-of-the-art landmark localization performance, with SpatialConfiguration-Net being robust even in case of limited amounts of training data.
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.