Single-shot Path Integrated Panoptic Segmentation

Hwang, Sukjun; Oh, Seoung Wug; Kim, Seon Joo

doi:10.1109/wacv51458.2022.00200

Cited by 4 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare the performance of Mask-PNet with several representative methods from different architectures, such as Weakly Supervised [ 34 ], Panoptic FPN [ 13 ], AUNet [ 28 ], UPSNet [ 6 ], Seamless [ 35 ], PCV [ 12 ], Mask RCNN [ 4 ], SSAP [ 36 ], AttentionPS [ 37 ], and MaskConver [ 38 ]. Table 1 shows the results of the Cityscapes validation set.…”

Section: Resultsmentioning

confidence: 99%

“…In this sub-section, we compare the performance of our proposed Mask-PNet method with several existing state-of-the-art panoptic segmentation techniques. AUNet [ 28 ], Panoptic FPN [ 13 ], AdaptIS [ 37 ], UPSNet [ 6 ], Seamless [ 35 ], Mask RCNN [ 4 ], SSAP [ 36 ], AttentionPS [ 37 ], and MaskConver [ 38 ] are among the representative methods we compare against. To evaluate the performance of these methods, we utilize the COCO validation dataset and present the results in Table 2 .…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Mask-Pyramid Network: A Novel Panoptic Segmentation Method

Xian,

Po,

Xiong

et al. 2024

Sensors

View full text Add to dashboard Cite

In this paper, we introduce a novel panoptic segmentation method called the Mask-Pyramid Network. Existing Mask RCNN-based methods first generate a large number of box proposals and then filter them at each feature level, which requires a lot of computational resources, while most of the box proposals are suppressed and discarded in the Non-Maximum Suppression process. Additionally, for panoptic segmentation, it is a problem to properly fuse the semantic segmentation results with the Mask RCNN-produced instance segmentation results. To address these issues, we propose a new mask pyramid mechanism to distinguish objects and generate much fewer proposals by referring to existing segmented masks, so as to reduce computing resource consumption. The Mask-Pyramid Network generates object proposals and predicts masks from larger to smaller sizes. It records the pixel area occupied by the larger object masks, and then only generates proposals on the unoccupied areas. Each object mask is represented as a H × W × 1 logit, which fits well in format with the semantic segmentation logits. By applying SoftMax to the concatenated semantic and instance segmentation logits, it is easy and natural to fuse both segmentation results. We empirically demonstrate that the proposed Mask-Pyramid Network achieves comparable accuracy performance on the Cityscapes and COCO datasets. Furthermore, we demonstrate the computational efficiency of the proposed method and obtain competitive results.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Mask-Pyramid Network: A Novel Panoptic Segmentation Method

Xian,

Po,

Xiong

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Using unified feature maps to describe the final panoptic result, Hwang et al. [122] took advantage of the integration of blocks and paths. A unified feature map known as Panoptic Feature was created using the integrated pathway and contained data on both things and things.…”

Section: Review Of Panoptic Segmentationmentioning

confidence: 99%

“…By combining both, a novel building block that could be stacked to create axial-attention models for image classification and the dense prediction was constructed. Using unified feature maps to describe the final panoptic result, Hwang et al [122] took advantage of the integration of blocks and paths. A unified feature map known as Panoptic Feature was created using the integrated pathway and contained data on both things and things.…”

Section: Unified Modelsmentioning

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

“…More recently, there are single-path architectures without using separate branches, which are realized via conditional convolution filters [45], [46], learnable kernels [47], [48], and unified panoptic embeddings [49]. Transformer models have also been introduced into panoptic segmentation due to their capability to model long-range dependencies [17], [50], [51].…”

Section: Related Workmentioning

confidence: 99%

Panoramic Panoptic Segmentation: Towards Complete Surrounding Understanding via Unsupervised Contrastive Learning

Jaus

Yang

Stiefelhagen

2021

2021 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

In this work, we introduce panoramic panoptic segmentation as the most holistic scene understanding both in terms of field of view and image level understanding. A complete surrounding understanding provides a maximum of information to the agent, which is essential for any intelligent vehicle in order to make informed decisions in a safetycritical dynamic environment such as real-world traffic. In order to overcome the lack of annotated panoramic images, we propose a framework which allows model training on standard pinhole images and transfers the learned features to a different domain. Using our proposed method, we manage to achieve significant improvements of over 5% measured in PQ over nonadapted models on our Wild Panoramic Panoptic Segmentation (WildPPS) dataset. We show that our proposed Panoramic Robust Feature (PRF) framework is not only suitable to improve performance on panoramic images but can be beneficial whenever model training and deployment are executed on data taken from different distributions. As an additional contribution, we publish WildPPS: The first panoramic panoptic image dataset to foster progress in surrounding perception.

show abstract

Single-shot Path Integrated Panoptic Segmentation

Cited by 4 publications

References 31 publications

Mask-Pyramid Network: A Novel Panoptic Segmentation Method

Mask-Pyramid Network: A Novel Panoptic Segmentation Method

Deep learning‐based panoptic segmentation: Recent advances and perspectives

Panoramic Panoptic Segmentation: Towards Complete Surrounding Understanding via Unsupervised Contrastive Learning

Contact Info

Product

Resources

About