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 Article
Convolutional Neural Fabrics
Shreyas Saxena,Jakob Verbeek +1 more
TL;DR: A "fabric" that embeds an exponentially large number of architectures that is competitive with the state of the art for image classification on MNIST and CIFAR10, and for semantic segmentation on the Part Labels dataset.
Journal ArticleDOI
Weakly Supervised Learning Based on Coupled Convolutional Neural Networks for Aircraft Detection
TL;DR: A coupled CNN method, which combines a candidate region proposal network and a localization network to extract the proposals and simultaneously locate the aircraft, which is more efficient and accurate, even in large-scale VHR images.
Posted Content
Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights
TL;DR: This work learns binary masks that “piggyback” on an existing network, or are applied to unmodified weights of that network to provide good performance on a new task, and shows performance comparable to dedicated fine-tuned networks for a variety of classification tasks.
Proceedings ArticleDOI
SE3-nets: Learning rigid body motion using deep neural networks
Arunkumar Byravan,Dieter Fox +1 more
TL;DR: SE3-Nets as discussed by the authors are deep neural networks designed to model and learn rigid body motion from raw point cloud data based on sequences of depth images along with action vectors and point wise data associations.
Journal ArticleDOI
Multimodal Gesture Recognition Using 3-D Convolution and Convolutional LSTM
TL;DR: This paper presents a multimodal gesture recognition method based on 3-D convolution and convolutional long-short-term-memory (LSTM) networks and finds that it can be considered as an optional skill to prevent overfitting when no pre-trained models exist.
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.