The Cityscapes Dataset for Semantic Urban Scene Understanding
Marius Cordts,Mohamed Omran,Sebastian Ramos,Timo Rehfeld,Markus Enzweiler,Rodrigo Benenson,Uwe Franke,Stefan Roth,Bernt Schiele +8 more
- pp 3213-3223
TLDR
This work introduces Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling, and exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity.Abstract:
Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban scene understanding, however, no current dataset adequately captures the complexity of real-world urban scenes. To address this, we introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. Cityscapes is comprised of a large, diverse set of stereo video sequences recorded in streets from 50 different cities. 5000 of these images have high quality pixel-level annotations, 20 000 additional images have coarse annotations to enable methods that leverage large volumes of weakly-labeled data. Crucially, our effort exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity. Our accompanying empirical study provides an in-depth analysis of the dataset characteristics, as well as a performance evaluation of several state-of-the-art approaches based on our benchmark.read more
Citations
More filters
Journal ArticleDOI
Multi-task, multi-domain learning
Damien Fourure,Rmi Emonet,Elisa Fromont,Damien Muselet,Natalia Neverova,Alain Trmeau,Christian Wolf +6 more
TL;DR: It is shown that the gradient-reversal approach for domain adaptation can be used in this setup to additionally handle domain shifts and an auto-context approach that further captures existing correlations across tasks is proposed.
Posted Content
Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images
TL;DR: A real-time fusion semantic segmentation network termed RFNet that effectively exploits complementary cross-modal information and is capable of running swiftly, which satisfies autonomous vehicles applications.
Journal ArticleDOI
A survey of semi- and weakly supervised semantic segmentation of images
Man Zhang,Man Zhang,Yong Zhou,Yong Zhou,Jiaqi Zhao,Jiaqi Zhao,Yiyun Man,Bing Liu,Bing Liu,Rui Yao,Rui Yao +10 more
TL;DR: This paper focuses on the core methods and reviews the semi- and weakly supervised semantic segmentation models in recent years, based on the commonly used models such as convolutional neural networks, fully Convolutional networks, generative adversarial networks.
Posted Content
DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networks
TL;DR: A theoretical framework to approximate Bayesian inference for DNNs by imposing a Bernoulli distribution on the model weights, called Monte Carlo DropConnect (MC-DropConnect), which yields significant improvement in both prediction accuracy and uncertainty estimation quality compared to the state of the art.
Proceedings ArticleDOI
Scaling Up Your Kernels to 31×31: Revisiting Large Kernel Design in CNNs
TL;DR: RepLKNet as discussed by the authors proposes to use a few large convolutional kernels instead of a stack of small kernels to close the performance gap between CNNs and ViTs, achieving comparable or superior results than Swin Transformer on ImageNet.
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: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
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.
Journal ArticleDOI
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Journal ArticleDOI
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.