Learning the Superpixel in a Non-iterative and Lifelong Manner

Zhu, Lei; She, Qi; Zhang, Bin; Lu, Yanye; Lu, Zhilin; Li, Duo; Hu, Jie

doi:10.1109/cvpr46437.2021.00128

Cited by 25 publications

(17 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We adopt AP, AP 50 , AP 75 , AP S , AP M , and AP L . (Achanta et al, 2012) by a large margin, and also surpasses recent three deep learning based competitors, i.e., SSFCN (Yang et al, 2020) and LNS (Zhu et al, 2021b). In addition, CLUSTSEG gains high CO score.…”

Section: Experiments On Panoptic Segmentationmentioning

confidence: 80%

“…Superpixel segmentation is an active research area in the pre-deep learning era; see (Stutz et al, 2018) for a thorough survey. Recently, some approaches are developed to harness neural networks to facilitate superpixel segmentation (Jampani et al, 2018;Yang et al, 2020;Zhu et al, 2021b). For instance, Tu et al (2018) make use of deep learning techniques to learn a superpixelfriendly embedding space; Yang et al (2020) adopt a FCN to directly predict association scores between pixels and regular grid cells for grid-based superpixel creation.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Robust Graph-Based Multi-View Clustering

Liang

Liu

Zhou

et al. 2022

AAAI

View full text Add to dashboard Cite

Graph-based multi-view clustering (G-MVC) constructs a graphical representation of each view and then fuses them to a unified graph for clustering. Though demonstrating promising clustering performance in various applications, we observe that their formulations are usually non-convex, leading to a local optimum. In this paper, we propose a novel MVC algorithm termed robust graph-based multi-view clustering (RG-MVC) to address this issue. In particular, we define a min-max formulation for robust learning and then rewrite it as a convex and differentiable objective function whose convexity and differentiability are carefully proved. Thus, we can efficiently solve the resultant problem using a reduced gradient descent algorithm, and the corresponding solution is guaranteed to be globally optimal. As a consequence, although our algorithm is free of hyper-parameters, it has shown good robustness against noisy views. Extensive experiments on benchmark datasets verify the superiority of the proposed method against the compared state-of-the-art algorithms. Our codes and appendix are available at https://github.com/wx-liang/RG-MVC.

show abstract

Section: Experiments On Panoptic Segmentationmentioning

confidence: 80%

Section: Related Workmentioning

confidence: 99%

Robust Graph-Based Multi-View Clustering

Liang

Liu

Zhou

et al. 2022

AAAI

View full text Add to dashboard Cite

show abstract

“…It will be meaningful to present an adaptive sampling method based on the self-attention mechanism for the hierarchical Transformer. Additionally, inspired by the superpixel [138] in the 2D field, we argue that it is feasible to utilize the attention map in 3D Transformers to obtain the "superpoint" [139] for point cloud oversegmentation, converting point-level 3D data into districtlevel data. In this way, this adaptive clustering technique can be used to replace the query ball grouping method.…”

Section: A Discussionmentioning

confidence: 99%

Transformers in 3D Point Clouds: A Survey

Lu¹,

Quan²,

Wei³

et al. 2022

Preprint

View full text Add to dashboard Cite

In recent years, Transformer models have been proven to have the remarkable ability of long-range dependencies modeling. They have achieved satisfactory results both in Natural Language Processing (NLP) and image processing. This significant achievement sparks great interest among researchers in 3D point cloud processing to apply them to various 3D tasks. Due to the inherent permutation invariance and strong global feature learning ability, 3D Transformers are well suited for point cloud processing and analysis. They have achieved competitive or even better performance compared to the state-of-the-art non-Transformer algorithms. This survey aims to provide a comprehensive overview of 3D Transformers designed for various tasks (e.g. point cloud classification, segmentation, object detection, and so on). We start by introducing the fundamental components of the general Transformer and providing a brief description of its application in 2D and 3D fields. Then, we present three different taxonomies (i.e., Transformer implementation-based taxonomy, data representation-based taxonomy, and task-based taxonomy) for method classification, which allows us to analyze involved methods from multiple perspectives. Furthermore, we also conduct an investigation of 3D self-attention mechanism variants designed for performance improvement. To demonstrate the superiority of 3D Transformers, we compare the performance of Transformer-based algorithms in terms of point cloud classification, segmentation, and object detection. Finally, we point out three potential future research directions, expecting to provide some benefit references for the development of 3D Transformers.

show abstract

“…Superpixels are over-segmentation of images, which are generated by simply utilizing low-level image features to group pixels into perceptually meaningful regions [43], [44]. By combining the advantages of perceptual uniformity [45] and contour adherence [46], superpixels offer a more natural representation than individual image pixels [47]. The merits of superpixels have been extensively explored in diverse vision tasks, such as object detection [48], object tracking [49], optical flow estimation [50], and 3D reconstruction [51].…”

Section: B Superpixel-enhanced Semantic Segmentationmentioning

confidence: 99%

Semantic-Aware Region Loss for Land-Cover Classification

Zheng

Huan

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Integrating superpixel segmentation into convolutional neural networks is known to be effective in enhancing the accuracy of land-cover classification. However, most of existing methods accomplish such integration by focusing on the development of new network architectures, which suffer from several flaws: 1) conflicts between general superpixels and semantic labels introduce noise into the training, especially at object boundaries; 2) absence of training guidance for superpixels leads to ineffective regional feature learning; 3) unnecessary superpixel segmentation in the testing stage not only increases the computational burden but also incurs jagged edges. In this study, we propose a novel semantic-aware region (SARI) loss to guide the effective learning of regional features with superpixels for accurate land-cover classification. The key idea of the proposed method is to reduce the feature variance inside and between homogeneous superpixels while enlarging feature discrepancy between heterogeneous ones. The SARI loss is thus designed with three sub-parts, including superpixel variance loss, intra-class similarity loss and interclass distance loss. We also develop semantic superpixels to assist in the network training with SARI loss while overcoming the limitations of general superpixels. Extensive experiments on two challenging datasets demonstrate that the SARI loss can facilitate regional feature learning, achieving state-of-the-art performance with mIoU scores of around 97.11% and 73.99%

show abstract

Learning the Superpixel in a Non-iterative and Lifelong Manner

Cited by 25 publications

References 24 publications

Robust Graph-Based Multi-View Clustering

Robust Graph-Based Multi-View Clustering

Transformers in 3D Point Clouds: A Survey

Semantic-Aware Region Loss for Land-Cover Classification

Contact Info

Product

Resources

About