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
Feedforward semantic segmentation with zoom-out features
TL;DR: In this article, a feed-forward architecture for semantic segmentation is proposed, which maps small image elements (superpixels) to rich feature representations extracted from a sequence of nested regions of increasing extent.
Posted Content
Pose-driven Deep Convolutional Model for Person Re-identification
TL;DR: A Pose-driven Deep Convolutional (PDC) model is proposed to learn improved feature extraction and matching models from end to end and explicitly leverages the human part cues to alleviate the pose variations and learn robust feature representations from both the global image and different local parts.
Proceedings ArticleDOI
Sparsity Invariant CNNs
TL;DR: This paper proposes a simple yet effective sparse convolution layer which explicitly considers the location of missing data during the convolution operation, and demonstrates the benefits of the proposed network architecture in synthetic and real experiments with respect to various baseline approaches.
Posted Content
Finding Tiny Faces
Peiyun Hu,Deva Ramanan +1 more
TL;DR: The role of scale in pre-trained deep networks is explored, providing ways to extrapolate networks tuned for limited scales to rather extreme ranges and demonstrating state-of-the-art results on massively-benchmarked face datasets.
Proceedings ArticleDOI
A Novel Focal Tversky Loss Function With Improved Attention U-Net for Lesion Segmentation
TL;DR: In this article, a generalized focal loss function based on the Tversky index was proposed to address the issue of data imbalance in medical image segmentation, which achieved a better trade off between precision and recall when training on small structures such as lesions.
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.