相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Kai Han et al.
Summary: Transformer, a deep neural network with a self-attention mechanism, has been initially used in natural language processing and is now gaining attention in computer vision tasks. Transformer-based models perform as well as or even better than convolutional and recurrent neural networks in various visual benchmarks. This paper reviews vision transformer models, categorizes them based on different tasks, and analyzes their advantages and disadvantages. The discussed categories include backbone network, high/mid-level vision, low-level vision, and video processing. Efficient methods for applying transformer in real device-based applications are also explored. The challenges and further research directions for vision transformers are discussed as well.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Guozeng Xian et al.
Summary: This paper investigates the distribution issue of LiDAR-based 3D point cloud panoptic segmentation in autonomous driving. A new method is proposed to project the 3D point clouds into a 2D image using bird's eye view (BEV) representation, and extract local features for panoptic segmentation. The effectiveness of the proposed method is validated on the validation and test sets of the SemanticKITTI dataset, outperforming other state-of-the-art methods based on 2D projection in terms of higher panoptic quality scores.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2023)
Article
Computer Science, Artificial Intelligence
Daniel Bolya et al.
Summary: This paper presents a simple fully-convolutional model for real-time instance segmentation. By breaking instance segmentation into two parallel subtasks and linearly combining prototypes with mask coefficients, the model achieves competitive results with significantly faster speed. The authors also propose a faster replacement for standard non-maximum suppression and apply deformable convolutions to improve performance and efficiency.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Tao Chu et al.
Summary: Panoptic segmentation is a joint task of semantic and instance segmentation, and conflicting feature discriminability may arise due to different requirements. To address this issue, a Dual-FPN framework and a Region Refinement Module are proposed, achieving state-of-the-art performance on Cityscapes and Mapillary Vistas datasets.
PATTERN RECOGNITION
(2022)
Article
Environmental Sciences
Osmar Luiz Ferreira de Carvalho et al.
Summary: Panoptic segmentation has great potential in remotely sensed data as it combines instance and semantic predictions to detect countable objects and different backgrounds simultaneously. However, challenges such as labeling large images, generating DL samples in the panoptic segmentation format, handling large remote sensing images, and software compatibility issues have hindered the growth of this task. This study addresses these challenges by providing a pipeline for generating panoptic segmentation datasets, software for creating deep learning samples in the COCO annotation format, a novel dataset, compatibility with remote sensing data using Detectron2 software, and evaluation on the urban setting.
Review
Computer Science, Artificial Intelligence
Wenchao Gu et al.
Summary: This article introduces 2D instance segmentation methods based on deep neural networks. It summarizes different supervised approaches and methods with different numbers of stages. It also introduces evaluation datasets and metrics, and reviews the latest instance segmentation techniques and applications. The future research directions and potential applications are discussed as well.
IMAGE AND VISION COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Qi Wang et al.
Summary: Panoptic segmentation is a challenging task where researchers have proposed a single shot panoptic segmentation network (SSPSNet) to handle it more accurately.
NEURAL COMPUTING & APPLICATIONS
(2022)
Proceedings Paper
Acoustics
Minxiang Ye et al.
Summary: Panoptic segmentation is a challenging task that combines semantic segmentation and instance segmentation, assigning both semantic labels and instance ids to each pixel. This work proposes a box-free strategy and utilizes a graph-based clustering method to merge repetitive kernel weights for object instances, providing an efficient alternative for instance-aware label prediction in both training and inference stages.
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Rohit Mohan et al.
Summary: The article introduces the way humans perceive the world through modal perception and proposes a new task, namely amodal panoptic segmentation. To facilitate research on this task, the article extends two existing datasets and proposes a new segmentation network. The experimental results demonstrate that this method achieves state-of-the-art performance on the benchmarks.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Oliver Zendel et al.
Summary: This paper improves panoptic segmentation for real-world applications by unifying label policies, introducing new datasets and benchmark services, adding hazard-aware and negative testing, and proposing a novel technique for visualizing segmentation errors.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Qihang Yu et al.
Summary: This paper presents a transformer-based framework for panoptic segmentation, called Clustering Mask Transformer (CMT-DeepLab), which utilizes a CMT layer to compute pixel clustering based on feature affinity and generate denser and more consistent cross-attention for the final segmentation task. Experimental results show that this method significantly improves performance compared to prior art.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Jianyuan Guo et al.
Summary: This paper introduces a novel hybrid network based on transformers and CNNs, called CMTs, which performs well in image recognition tasks and achieves a better trade-off between accuracy and computational efficiency.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhiqi Li et al.
Summary: Panoptic SegFormer is a general framework for panoptic segmentation using transformers, incorporating innovative components and strategies to enhance performance and reduce training epochs, resulting in higher accuracy than baseline models. This approach outperforms existing methods in various aspects.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Shubhankar Borse et al.
Summary: This paper presents a novel framework for integrating semantic and instance contexts for panoptic segmentation. By introducing a panoptic relational attention module, the framework is able to capture relations between semantic classes and instances as well as relations between these categories and spatial features. Evaluation on multiple panoptic segmentation benchmarks demonstrates considerable improvements achieved by this framework.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Sukjun Hwang et al.
Summary: This paper proposes a method for single-shot panoptic segmentation by integrating execution flows, generating a unified feature map called Panoptic-Feature, and clustering pixels and classifying objects through auxiliary problems to achieve single-shot panoptic segmentation.
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022)
(2022)
Review
Computer Science, Artificial Intelligence
Yifei Zhang et al.
Summary: Recent advances in deep learning have shown excellent performance in scene understanding tasks, but in complex environments, multimodal fusion is necessary. Deep multimodal fusion significantly improves semantic image segmentation, with different fusion strategies such as early fusion, late fusion, and hybrid fusion.
IMAGE AND VISION COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Zhaowei Cai et al.
Summary: In object detection, the commonly used IoU threshold of 0.5 can lead to noisy detections, and performance may degrade for larger thresholds. The Cascade R-CNN architecture addresses this issue by training detectors sequentially with increasing IoU thresholds and eliminating quality mismatches at inference, resulting in state-of-the-art performance and significant improvement in high-quality detection across various datasets. The model is also generalized to instance segmentation, achieving nontrivial improvements over existing methods.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Engineering, Electrical & Electronic
Qiang Chen et al.
Summary: In this article, the importance of object location in panoptic segmentation is discussed, with the proposal of spatial information flows to effectively integrate object locations in the segmentation process. By utilizing four parallel sub-networks, a framework called SpatialFlow is introduced for achieving state-of-the-art results in panoptic segmentation benchmarks.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Lian Xu et al.
Summary: The proposed AuxSegNet framework leverages saliency detection and multi-label image classification as auxiliary tasks to improve the primary task of semantic segmentation. By learning a cross-task global pixel-level affinity map, the method effectively enhances saliency predictions and provides improved pseudo labels for segmentation tasks.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yi Li et al.
Summary: This study proposes new designs to address issues related to pseudo-mask quality and noisy pseudo-mask supervision in weakly supervised semantic segmentation, achieving new state-of-the-art results on two challenging datasets.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Automation & Control Systems
Sumanth Chennupati et al.
Summary: Panoptic Segmentation aims to combine semantic segmentation and instance segmentation into a unified scene understanding task, deriving instance segmentation through learning instance contours and semantic segmentation, and merging the results for panoptic segmentation.
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Lorenzo Porzi et al.
Summary: Crop-based training strategies allow for the use of large-capacity panoptic segmentation networks on multi-megapixel images, but may introduce a bias towards truncating or missing large objects. A novel crop-aware bounding box regression loss is proposed to address this issue, along with a new data sampling and augmentation strategy to improve generalization.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jaedong Hwang et al.
Summary: Researchers extend panoptic segmentation to the open-world scenario and introduce the task of open-set panoptic segmentation. They propose a novel exemplar-based open-set panoptic segmentation network (EOPSN) that identifies new classes based on exemplars.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Weixiang Hong et al.
Summary: Panoptic segmentation aims to segment objects at instance level and background contents at semantic level. Existing methods mostly use a two-stage detection network for instance segmentation and a fully convolutional network for semantic segmentation, but require post-processing or additional modules to handle conflicts between the outputs.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Tommi Kerola et al.
Summary: Panoptic segmentation combines instance and semantic segmentation tasks, using complex models to learn instance-specific and category-specific representations simultaneously.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Software Engineering
Hongwei Chen et al.
Summary: This paper proposes a panoptic segmentation algorithm for UAV platforms, which improves network feature extraction and foreground target mask quality by introducing deformable convolution and MaskIoU module.
TWELFTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2020)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Xiaolong Liu et al.
Summary: The CASNet is an one-stage instance segmentation network that predicts and clusters common attributes for instance segmentation and can be easily extended to panoptic segmentation. Experimental results demonstrate that CASNet achieves outstanding performance on the Cityscapes validation dataset.
2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)
(2021)
Article
Computer Science, Artificial Intelligence
Naiyu Gao et al.
Summary: This paper proposes a novel panoptic segmentation method that simplifies the pipeline by predicting category- and instance-aware pixel embedding through an extra module. By assigning each pixel to a detected instance or class based on learned embedding, the method achieves fast inference speed and comparable performance to two-stage methods on challenging benchmarks like COCO.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Dongnan Liu et al.
Summary: Instance segmentation in biomedical and biological image analysis is challenging due to complex backgrounds, variable object appearances, overlapping objects, and ambiguous boundaries. Proposed Panoptic Feature Fusion Net (PFFNet) unifies semantic and instance features to address the issue of information loss in proposal-free and proposal-based methods. PFFNet incorporates a residual attention feature fusion mechanism and mask quality sub-branch to improve semantic contextual information learning and align object confidence scores with mask quality prediction, leading to robust learning in both semantic and instance branches. Extensive experiments show PFFNet outperforms state-of-the-art methods on biomedical and biological datasets.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Asifullah Khan et al.
ARTIFICIAL INTELLIGENCE REVIEW
(2020)
Article
Computer Science, Artificial Intelligence
Abdul Mueed Hafiz et al.
INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL
(2020)
Article
Robotics
Daan de Geus et al.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2020)
Review
Computer Science, Interdisciplinary Applications
Siddharth Singh Chouhan et al.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2019)
Article
Computer Science, Artificial Intelligence
Fahad Lateef et al.
Article
Computer Science, Software Engineering
L. Yao et al.
COMPUTER GRAPHICS FORUM
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Henghui Ding et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Hang Zhang et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Article
Computer Science, Artificial Intelligence
Liang-Chieh Chen et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2018)
Article
Computer Science, Information Systems
Siddharth Singh Chouhan et al.
MULTIMEDIA TOOLS AND APPLICATIONS
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Xiang Wang et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Garrick Brazil et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Gao Huang et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Kaiming He et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Francois Chollet
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Article
Engineering, Biomedical
Xiaofeng Zhu et al.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2016)
Proceedings Paper
Computer Science, Artificial Intelligence
Ross Girshick
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2015)
Proceedings Paper
Computer Science, Artificial Intelligence
Pablo Arbelaez et al.
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2014)
Article
Computer Science, Artificial Intelligence
Feng Han et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2008)