The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
01 Oct 2017-pp 5000-5009
TL;DR: The Mapillary Vistas Dataset is a novel, large-scale street-level image dataset containing 25000 high-resolution images annotated into 66 object categories with additional, instance-specific labels for 37 classes, aiming to significantly further the development of state-of-the-art methods for visual road-scene understanding.
Abstract: The Mapillary Vistas Dataset is a novel, large-scale street-level image dataset containing 25000 high-resolution images annotated into 66 object categories with additional, instance-specific labels for 37 classes. Annotation is performed in a dense and fine-grained style by using polygons for delineating individual objects. Our dataset is 5× larger than the total amount of fine annotations for Cityscapes and contains images from all around the world, captured at various conditions regarding weather, season and daytime. Images come from different imaging devices (mobile phones, tablets, action cameras, professional capturing rigs) and differently experienced photographers. In such a way, our dataset has been designed and compiled to cover diversity, richness of detail and geographic extent. As default benchmark tasks, we define semantic image segmentation and instance-specific image segmentation, aiming to significantly further the development of state-of-the-art methods for visual road-scene understanding.
Citations
More filters
18 Jun 2018
TL;DR: PANet as mentioned in this paper enhances the entire feature hierarchy with accurate localization signals in lower layers by bottom-up path augmentation, which shortens the information path between lower layers and topmost feature.
Abstract: The way that information propagates in neural networks is of great importance. In this paper, we propose Path Aggregation Network (PANet) aiming at boosting information flow in proposal-based instance segmentation framework. Specifically, we enhance the entire feature hierarchy with accurate localization signals in lower layers by bottom-up path augmentation, which shortens the information path between lower layers and topmost feature. We present adaptive feature pooling, which links feature grid and all feature levels to make useful information in each level propagate directly to following proposal subnetworks. A complementary branch capturing different views for each proposal is created to further improve mask prediction. These improvements are simple to implement, with subtle extra computational overhead. Yet they are useful and make our PANet reach the 1st place in the COCO 2017 Challenge Instance Segmentation task and the 2nd place in Object Detection task without large-batch training. PANet is also state-of-the-art on MVD and Cityscapes.
3,784 citations
Posted Content•
TL;DR: nuScenes as mentioned in this paper is the first dataset to carry the full autonomous vehicle sensor suite: 6 cameras, 5 radars and 1 lidar, all with full 360 degree field of view.
Abstract: Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment. Most autonomous vehicles, however, carry a combination of cameras and range sensors such as lidar and radar. As machine learning based methods for detection and tracking become more prevalent, there is a need to train and evaluate such methods on datasets containing range sensor data along with images. In this work we present nuTonomy scenes (nuScenes), the first dataset to carry the full autonomous vehicle sensor suite: 6 cameras, 5 radars and 1 lidar, all with full 360 degree field of view. nuScenes comprises 1000 scenes, each 20s long and fully annotated with 3D bounding boxes for 23 classes and 8 attributes. It has 7x as many annotations and 100x as many images as the pioneering KITTI dataset. We define novel 3D detection and tracking metrics. We also provide careful dataset analysis as well as baselines for lidar and image based detection and tracking. Data, development kit and more information are available online.
1,939 citations
Cites background from "The Mapillary Vistas Dataset for Se..."
...Most datasets provide 2D semantic annotations as boxes or masks (class or instance) [8, 19, 33, 85, 55]....
[...]
...Vistas [33] 2017 n/a - 25k 0 0 25k 0 Yes/Yes 0 152 Global...
[...]
...CamVid [8], Cityscapes [19], Mapillary Vistas [33], D-City [11], BDD100k [85] and Apolloscape [41] released ever growing datasets with segmentation masks....
[...]
14 Jun 2020
TL;DR: nuScenes as discussed by the authors is the first dataset to carry the full autonomous vehicle sensor suite: 6 cameras, 5 radars and 1 lidar, all with full 360 degree field of view.
Abstract: Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment. Most autonomous vehicles, however, carry a combination of cameras and range sensors such as lidar and radar. As machine learning based methods for detection and tracking become more prevalent, there is a need to train and evaluate such methods on datasets containing range sensor data along with images. In this work we present nuTonomy scenes (nuScenes), the first dataset to carry the full autonomous vehicle sensor suite: 6 cameras, 5 radars and 1 lidar, all with full 360 degree field of view. nuScenes comprises 1000 scenes, each 20s long and fully annotated with 3D bounding boxes for 23 classes and 8 attributes. It has 7x as many annotations and 100x as many images as the pioneering KITTI dataset. We define novel 3D detection and tracking metrics. We also provide careful dataset analysis as well as baselines for lidar and image based detection and tracking. Data, development kit and more information are available online.
1,378 citations
14 Jun 2020
TL;DR: This work constructs BDD100K, the largest driving video dataset with 100K videos and 10 tasks to evaluate the exciting progress of image recognition algorithms on autonomous driving and shows that special training strategies are needed for existing models to perform such heterogeneous tasks.
Abstract: Datasets drive vision progress, yet existing driving datasets are impoverished in terms of visual content and supported tasks to study multitask learning for autonomous driving. Researchers are usually constrained to study a small set of problems on one dataset, while real-world computer vision applications require performing tasks of various complexities. We construct BDD100K, the largest driving video dataset with 100K videos and 10 tasks to evaluate the exciting progress of image recognition algorithms on autonomous driving. The dataset possesses geographic, environmental, and weather diversity, which is useful for training models that are less likely to be surprised by new conditions. Based on this diverse dataset, we build a benchmark for heterogeneous multitask learning and study how to solve the tasks together. Our experiments show that special training strategies are needed for existing models to perform such heterogeneous tasks. BDD100K opens the door for future studies in this important venue.
1,163 citations
Cites background from "The Mapillary Vistas Dataset for Se..."
...Existing datasets for autonomous driving [15, 7, 24] are limited in one or more significant aspects, including the scene variation, the richness of annotations, and the geographic distribution....
[...]
...Like Vistas, our data is crowdsourced, however, our dataset is collected solely from drivers, with each annotated image corresponding to a video sequence, which enables interesting applications for modeling temporal dynamics....
[...]
...Mapillary Vistas [24] provides fine-grained annotations for user uploaded data, which is much more diverse with respect to location....
[...]
...Especially with the advent of deep learning methods, large scale visual datasets, such as [8, 36, 40, 24], are essential for learning high-level image representations....
[...]
01 Jun 2019
TL;DR: A novel panoptic quality (PQ) metric is proposed that captures performance for all classes (stuff and things) in an interpretable and unified manner and is performed a rigorous study of both human and machine performance for PS on three existing datasets, revealing interesting insights about the task.
Abstract: We propose and study a task we name panoptic segmentation (PS). Panoptic segmentation unifies the typically distinct tasks of semantic segmentation (assign a class label to each pixel) and instance segmentation (detect and segment each object instance). The proposed task requires generating a coherent scene segmentation that is rich and complete, an important step toward real-world vision systems. While early work in computer vision addressed related image/scene parsing tasks, these are not currently popular, possibly due to lack of appropriate metrics or associated recognition challenges. To address this, we propose a novel panoptic quality (PQ) metric that captures performance for all classes (stuff and things) in an interpretable and unified manner. Using the proposed metric, we perform a rigorous study of both human and machine performance for PS on three existing datasets, revealing interesting insights about the task. The aim of our work is to revive the interest of the community in a more unified view of image segmentation. For more analysis and up-to-date results, please check the arXiv version of the paper: {\small\url{https://arxiv.org/abs/1801.00868}}.
980 citations
Cites background or methods or result from "The Mapillary Vistas Dataset for Se..."
...This includes the Cityscapes [6], ADE20k [54], and Mapillary Vistas [35] datasets....
[...]
...Both COCO [25] and Mapillary Vistas [35] featured the panoptic segmentation task as one of the tracks in their recognition challenges at ECCV 2018....
[...]
...As expected, humans are not perfect at this task, which is consistent with studies of annotation quality from [6, 54, 35]....
[...]
...Finally we note that the panoptic segmentation task was featured as a challenge track by both the COCO [25] and Mapillary Vistas [35] recognition challenges and that the proposed task has already begun to gain traction in the community (e....
[...]
...Recently the field has seen numerous new segmentation datasets including Cityscapes [6], ADE20k [54], and Mapillary Vistas [35]....
[...]
References
More filters
27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
123,388 citations
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
Posted Content•
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers.
The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
44,703 citations
"The Mapillary Vistas Dataset for Se..." refers methods in this paper
...A line of successful approaches have been inspired by the Fully Convolutional Network (FCN) [37], which has shown that effective semantic segmentation networks can be obtained from state-of-the-art architectures for image classification such as VGG [52], GoogleNet [53], ResNet [18], Wider ResNet [58], etc., pre-trained on ImageNet [48] and/or Places2 [63], by turning fully-connected layers into convolutional layers....
[...]
...The ResNet 50 models are used due to preference of larger image inputs (max. image size 1900) over deeper feature extractors....
[...]
...The winning team PSPNET [60] built upon [61], extending the basic ResNet 101 (pretrained on ImageNet and Cityscapes, though Cityscapes contribution was negligible) architecture with the following features: i) Modifying the res4b module according to the hybrid dilation convolution (HDC) approach intro- duced in [54]....
[...]
...A line of successful approaches have been inspired by the Fully Convolutional Network (FCN) [37], which has shown that effective semantic segmentation networks can be obtained from state-of-the-art architectures for image classification such as VGG [52], GoogleNet [53], ResNet [18], Wider ResNet [58], etc....
[...]
...2 we present baseline results using a Wider Network (ResNet38) [55] architecture with cross-entropy loss as well as imbalance correction via loss max-pooling and/or alternative minibatch compilation strategies as described in [47]....
[...]
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