The Cityscapes Dataset for Semantic Urban Scene Understanding
01 Jun 2016-pp 3213-3223
TL;DR: 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.
Citations
More filters
Posted Content•
TL;DR: The ROOAD dataset as discussed by the authors provides high-quality, time-synchronized off-road monocular visual-inertial data sequences to further the development of related research, and the accuracy and repeatability of Kalibr's IMU-camera extrinsics calibration tool is measured to be +/- 1 degrees for orientation and +/- 1mm at best (left-right and +/- 10mm (depth) at worse for position estimation in the camera frame.
Abstract: The development and implementation of visual-inertial odometry (VIO) has focused on structured environments, but interest in localization in off-road environments is growing. In this paper, we present the ROOAD which provides high-quality, time-synchronized off-road monocular visual-inertial data sequences to further the development of related research. We exhibit the 2-30x worse performance of two established VIO implementations, OpenVINS and VINS-Fusion, when stable, and the former is less prone to estimation divergences on our data sequences. The accuracy and repeatability of Kalibr's IMU-camera extrinsics calibration tool is measured to be +/-1 degrees for orientation and +/-1mm at best (left-right) and +/-10mm (depth) at worse for position estimation in the camera frame. This novel dataset provides a new set of scenarios for researchers to design and test their localization algorithms on, as well as critical insights in the current performance of VIO off-road.
ROOAD Dataset: github.com/unmannedlab/ROOAD
1 citations
17 Oct 2021
TL;DR: Sidewalk Gallery as discussed by the authors is an interactive, filterable gallery of over 500,000 crowdsourced sidewalk accessibility images across seven cities in two countries (US and Mexico) allowing users to explore and interactively filter sidewalk images.
Abstract: What do sidewalk accessibility problems look like? How might these problems differ across cities? In this poster paper, we introduce Sidewalk Gallery, an interactive, filterable gallery of over 500,000 crowdsourced sidewalk accessibility images across seven cities in two countries (US and Mexico). Gallery allows users to explore and interactively filter sidewalk images based on five primary accessibility problem types, 35 tag categories, and a 5-point severity scale. When browsing images, users can also provide feedback about data correctness. We envision Gallery as a tool for teaching in urban design and accessibility and as a visualization aid for disability advocacy.
1 citations
TL;DR: Wang et al. as discussed by the authors proposed a simple yet effective architecture that introduces auxiliary branches to Mask2former during training to capture dense local features on the encoder side, which help improve the performance of learning local information and segmenting small objects.
Abstract: Transformer-based semantic segmentation methods have achieved excellent performance in recent years. Mask2Former is one of the well-known transformer-based methods which unifies common image segmentation into a universal model. However, it performs relatively poorly in obtaining local features and segmenting small objects due to relying heavily on transformers. To this end, we propose a simple yet effective architecture that introduces auxiliary branches to Mask2Former during training to capture dense local features on the encoder side. The obtained features help improve the performance of learning local information and segmenting small objects. Since the proposed auxiliary convolution layers are required only for training and can be removed during inference, the performance gain can be obtained without additional computation at inference. Experimental results show that our model can achieve state-of-the-art performance (57.6% mIoU) on the ADE20K and (84.8% mIoU) on the Cityscapes datasets.
1 citations
1 citations
1 citations
References
More filters
Proceedings Article•
03 Dec 2012TL;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.
Abstract: We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, 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. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
73,978 citations
Proceedings Article•
04 Sep 2014TL;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.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) 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. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
55,235 citations
"The Cityscapes Dataset for Semantic..." refers methods in this paper
...We adopted VGG16 [68] and utilize the PASCAL-context setup [41] with a modified learning rate to match our image resolution under an unnormalized loss....
[...]
Proceedings Article•
01 Jan 2015TL;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.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) 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. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
49,914 citations
[...]
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.
Abstract: Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.
46,982 citations
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.
Abstract: The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions. This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotation, highlight key breakthroughs in categorical object recognition, provide a detailed analysis of the current state of the field of large-scale image classification and object detection, and compare the state-of-the-art computer vision accuracy with human accuracy. We conclude with lessons learned in the 5 years of the challenge, and propose future directions and improvements.
30,811 citations