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
Rethinking BiSeNet For Real-time Semantic Segmentation
TL;DR: A novel and efficient structure named Short-Term Dense Concatenate network (STDC network) is proposed by removing structure redundancy by gradually reducing the dimension of feature maps and use the aggregation of them for image representation, which forms the basic module of STDC network.
Proceedings ArticleDOI
Boosting Self-Supervised Learning via Knowledge Transfer
TL;DR: Li et al. as mentioned in this paper proposed a novel framework for self-supervised learning that overcomes limitations in designing and comparing different tasks, models, and data domains by decoupling the structure of the self-vised model from the final task-specific fine-tuned model.
Proceedings ArticleDOI
Weakly Supervised Instance Segmentation Using Class Peak Response
TL;DR: This paper addresses the challenging image-level supervised instance segmentation task by exploiting class peak responses to enable a classification network for instance mask extraction, and reports state-of-the-art results on popular benchmarks, including PASCAL VOC 2012 and MS COCO.
Journal ArticleDOI
Segment-before-detect: Vehicle detection and classification through semantic segmentation of aerial images
TL;DR: This work presents a deep-learning based segment-before-detect method for segmentation and subsequent detection and classification of several varieties of wheeled vehicles in high resolution remote sensing images to show that deep learning is also suitable for object-oriented analysis of Earth Observation data as effective object detection can be obtained as a byproduct of accurate semantic segmentation.
Posted Content
A Metric Learning Reality Check
TL;DR: Flaws in the experimental methodology of numerous metric learning papers are found, and it is shown that the actual improvements over time have been marginal at best.
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.