scispace - formally typeset
Open AccessProceedings ArticleDOI

The Cityscapes Dataset for Semantic Urban Scene Understanding

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
Book ChapterDOI

Learning Monocular Depth by Distilling Cross-Domain Stereo Networks

TL;DR: This paper proposes to use the stereo matching network as a proxy to learn depth from synthetic data and use predicted stereo disparity maps for supervising the monocular depth estimation network.
Proceedings ArticleDOI

Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery

TL;DR: Li et al. as discussed by the authors proposed a novel architecture called Local Feature Extraction (LFE) module attached on top of dilated front-end module, which is based on their findings that aggressively increasing dilation factors fails to aggregate local features due to sparsity of the kernel, and detrimental to small objects.
Proceedings ArticleDOI

Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation

TL;DR: This work proposes a data-dependent upsampling (DUpsampling) to replace bilinear, which takes advantages of the redundancy in the label space of semantic segmentation and is able to recover the pixel-wise prediction from low-resolution outputs of CNNs.
Proceedings ArticleDOI

Domain Adaptation for Structured Output via Discriminative Patch Representations

TL;DR: A domain adaptation method to adapt the source data to the unlabeled target domain by discovering multiple modes of patch-wise output distribution through the construction of a clustered space and using an adversarial learning scheme to push the feature representations of target patches in the clustered space closer to the distributions of source patches.
Proceedings ArticleDOI

Semantic Video Segmentation by Gated Recurrent Flow Propagation

TL;DR: A deep, end-to-end trainable methodology for video segmentation that is capable of leveraging the information present in unlabeled data, besides sparsely labeled frames, in order to improve semantic estimates.
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

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

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

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.
Related Papers (5)
Trending Questions (1)
What is city scene understanding?

City scene understanding involves pixel-level and instance-level semantic labeling in urban environments. The Cityscapes dataset provides a benchmark for training and testing approaches in this area.