SpatialFlow: Bridging All Tasks for Panoptic Segmentation

Chen, Qiang; Cheng, Anda; He, Xiaoliang; Wang, Peisong; Cheng, Jian

doi:10.1109/tcsvt.2020.3020257

Cited by 17 publications

(7 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many products requiring vast amounts of information can benefit from panoptic segmentation. A selfdriving vehicle, for instance, must be able to capture and understand its surroundings quickly and accurately [82]. A panoptic segmentation algorithm can be used to segment a live stream of images [83].…”

Section: Panoptic Segmentationmentioning

confidence: 99%

Object-based Classification of Natural Scenes Using Machine Learning Methods

Jasim¹,

Younis²

2023

Technium

View full text Add to dashboard Cite

The replication of human intellectual processes by machines, particularly computer systems, is known as artificial intelligence (AI). AI is an intelligent tool that is utilized across sectors to improve decision making, increase productivity, and eliminate repetitive tasks. Machine learning (ML) is a key component of AI since it includes understanding and developing ways that can learn or improve performance on tasks. For the last decade, ML has been applied in computer vision (CV) applications. In computer vision, systems and computers extract meaningful data from digital videos, photos, and other visual sources and use that information to conduct actions or make suggestions. In this work, we have solved the image segmentation problem for the natural images to segment out water, land, and sky. Instead of applying image segmentation directly to the images, images are pre-processed, and statistical and textural features are then passed through a neural network for the pixel-wise semantic segmentation of the images. We chose the 5X5 window over the pixel-by-pixel technique since it requires less resources and time for training and testing.

show abstract

Section: Panoptic Segmentationmentioning

confidence: 99%

Object-based Classification of Natural Scenes Using Machine Learning Methods

Jasim¹,

Younis²

2023

Technium

View full text Add to dashboard Cite

show abstract

“…Trying to incorporate object position in both thing and stuff segmentation, Chen et al. [113] designed spatial information flows. By passing the object's spatial context from the box regression job to others, the flows could connect all panoptic segmentation subtasks.…”

Section: Review Of Panoptic Segmentationmentioning

confidence: 99%

Deep learning‐based panoptic segmentation: Recent advances and perspectives

Chuang

Zhang

Zhao

2023

IET Image Processing

View full text Add to dashboard Cite

In recent years, panoptic segmentation has drawn increasing amounts of attention, leading to the rapid emergence of numerous related algorithms. A variety of deep neural networks have been used more frequently for panoptic segmentation, which is motivated by the significant success of deep learning methods in other tasks. This article presents a comprehensive exploration of panoptic segmentation, focusing on the analysis and understanding of RGB image data. Initially, the authors introduce the background of panoptic segmentation, including deep learning models and image segmentation. Then, the authors thoroughly cover a variety of panoptic segmentation‐related topics, such as datasets connected to the field, evaluation metrics, panoptic segmentation models, and derived subfields based on panoptic segmentation. Finally, the authors examine the difficulties and possibilities in this area and identify its future paths.

show abstract

“…CSRNet [60] (2018) VGG-16 Axial-DeepLab [136] DeepLab SPN [61] (2019) VGG-16 BANet [137] ResNet-50 DENet [63] VGG-16 VSPNet [138] ResNet-50 CANNet [64] VGG-16 BGRNet [139] ResNet50 SCAR [65] VGG-16 SpatialFlow [140] ResNet50 ADNet [69] VGG-16 Weber et al [141] ResNet50 ADSCNet [69] VGG-16 AUNet [142] ResNet50 ASNet [70] VGG-16 OANet [143] ResNet50 SCNet [68] VGG-16 SPINet [144] ResNet50 BL [66] VGG-19 Son et al [145] ResNet-50 MobileCount [62] MobileNet-V2 SOGNet [146] ResNet101 SFCN [67] ResNet-101 DR1Mask [147] ResNet101…”

Section: Crowd Countingmentioning

confidence: 99%

“…A holistic understanding of an image in the panoptic segmentation task can be achieved by modeling the correlation between object and background. For this purpose, a bidirectional graph reasoning network for panoptic segmentation (BGR-Net) is proposed in [139] Using ResNet-50 as well as the architecture in [140] and [141]. Using the same backbone in [142], the foreground things and background stuff have been dealt together in attention guided unified network (AUNet).…”

Section: Panoptic Segmentationmentioning

confidence: 99%

Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches

Elharrouss¹,

Akbari²,

Almaadeed³

et al. 2022

Preprint

View full text Add to dashboard Cite

To understand the real world using various types of data, Artificial Intelligence (AI) is the most used technique nowadays. While finding the pattern within the analyzed data represents the main task. This is performed by extracting representative features step, which is proceeded using the statistical algorithms or using some specific filters. However, the selection of useful features from large-scale data represented a crucial challenge. Now, with the development of convolution neural networks (CNNs), the feature extraction operation has become more automatic and easier. CNNs allow to work on large-scale size of data, as well as cover different scenarios for a specific task. For computer vision tasks, convolutional networks are used to extract features also for the other parts of a deep learning model. The selection of a suitable network for feature extraction or the other parts of a DL model is not random work. So, the implementation of such a model can be related to the target task as well as the computational complexity of it. Many networks have been proposed and become the famous networks used for any DL models in any AI task. These networks are exploited for feature extraction or at the beginning of any DL model which is named backbones. A backbone is a known network trained in many other tasks before and demonstrates its effectiveness. In this paper, an overview of the existing backbones, e.g. VGGs, ResNets, DenseNet, etc, is given with a detailed description. Also, a couple of computer vision tasks are discussed by providing a review of each task regarding the backbones used. In addition, a comparison in terms of performance is also provided, based on the backbone used for each task.

show abstract

SpatialFlow: Bridging All Tasks for Panoptic Segmentation

Cited by 17 publications

References 52 publications

Object-based Classification of Natural Scenes Using Machine Learning Methods

Object-based Classification of Natural Scenes Using Machine Learning Methods

Deep learning‐based panoptic segmentation: Recent advances and perspectives

Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches

Contact Info

Product

Resources

About