SHREC’22 track: Open-Set 3D Object Retrieval

Feng, Yifan; Gao, Yue; Zhao, Xibin; Guo, Yandong; Bagewadi, Nihar; Bui, Nhat-Tan; Dao, Hieu Trong; Gangisetty, Shankar; Guan, Ripeng; Xie, Haiyang; Huang, Cong; Hunakunti, Chidambar; Yu, Junsheng; Jiao, Shichao; Ke, Yuqi; Kuang, Liqun; Liu, An-An; Nguyen, Dinh-Huan; Nguyen, Hai-Dang; Nie, Weizhi; Pham, Bang-Dang; Raikar, Karthik; Tang, Qingmei; Tran, Minh-Triet; Wan, Jialong; Yan, Chenggang; You, Haoxuan; Zhu, Difei

doi:10.1016/j.cag.2022.07.020

Cited by 7 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to evaluate the retrieval performance of our method, we choose some state-of-the-art methods [13] as a comparison. All the competing methods take the same experimental settings as the proposed method, and we choose the best results for comparison.…”

Section: Comparison With the State-of-art Methodsmentioning

confidence: 99%

“…Mutil-view Pointcloud Mesh Voxel TT VODKA [13] CU MM [13] MM AI SoCSE KLETech [13] NUC AICV [13] Ome Candy [13] HCMUS [13] Ours For the OS-MN40-Miss, we replace the missing modality features with zero vectors, which is also done by other methods using either zeros or random numbers. Overall, our method outperforms other methods on all four evaluation metrics.…”

Section: Methodsmentioning

confidence: 99%

“…To substantiate our approach, we utilized 3D model data encompassing four modalities: multiview representation, point cloud, mesh, and voxel. Our method's performance was assessed on OS-MN40 [13] and OS-MN40-Miss [13] datasets, yielding results that surpass the established baseline. Furthermore, we conducted a comprehensive ablation study to validate the effectiveness of each module in our method.…”

Section: Motivationmentioning

confidence: 98%

“…We used multi-modal data from 3D models to demonstrate the effectiveness of the proposed method on retrieval and classification tasks. Our experiments were performed on the OS-MN40 [13] and OS-MN40-Miss [13] datasets. Furthermore, to validate the crossdomain generalization of the framework proposed by our method, we conducted a transfer experiment on the well-established NCD benchmark following the methodology of [53] based on Cifar10 [14].…”

Section: Datasetmentioning

confidence: 99%

See 3 more Smart Citations

Information Fusion Based on Multi-View and Multi-Feature Learning

Li¹,

Zhang²,

Zhang³

2022

Information Fusion

View full text Add to dashboard Cite

With the development of deep learning techniques, supervised learning has achieved performances surpassing those of humans. Researchers have designed numerous corresponding models for different data modalities, achieving excellent results in supervised tasks. However, with the exponential increase of data in multiple fields, the recognition and classification of unlabeled data have gradually become a hot topic. In this paper, we employed a Reinforcement Learning framework to simulate the cognitive processes of humans for effectively addressing novel class discovery in the Open-set domain. We deployed a Member-to-Leader Multi-Agent framework to extract and fuse features from multi-modal information, aiming to acquire a more comprehensive understanding of the feature space. Furthermore, this approach facilitated the incorporation of self-supervised learning to enhance model training. We employed a clustering method with varying constraint conditions, ranging from strict to loose, allowing for the generation of dependable labels for a subset of unlabeled data during the training phase. This iterative process is similar to human exploratory learning of unknown data. These mechanisms collectively update the network parameters based on rewards received from environmental feedback. This process enables effective control over the extent of exploration learning, ensuring the accuracy of learning in unknown data categories. We demonstrate the performance of our approach in both the 3D and 2D domains by employing the OS-MN40, OS-MN40-Miss, and Cifar10 datasets. Our approach achieves competitive competitive results. The source code can be found here: https://github.com/AveryFallson/RMFFN

show abstract

Section: Comparison With the State-of-art Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Motivationmentioning

confidence: 98%

Section: Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Information Fusion Based on Multi-View and Multi-Feature Learning

Li¹,

Zhang²,

Zhang³

2022

Information Fusion

View full text Add to dashboard Cite

show abstract

On efficient 3D object retrieval

Liu,

Wong

2024

The VLDB Journal

View full text Add to dashboard Cite

Due to the growth of the 3D technology, digital 3D models represented in the form of point clouds have attracted a lot of attention from both industry and academia. In this paper, due to a variety of applications, we study a fundamental problem called the 3D object retrieval, which is to find a set of 3D point clouds stored in a database that are similar to a given query 3D point cloud. To the best of our knowledge, solving the problem of 3D object retrieval efficiently remains unexplored in the research community. In this paper, we propose a framework called C$$_2$$ 2 O to find the answer efficiently with the help of an index built on the database. In most of our experiments, C$$_2$$ 2 O performs up to 2 orders of magnitude faster than all adapted algorithms in the literature. In particular, when the database size scales up to 100 million points, C$$_2$$ 2 O answers the 3D object retrieval within 10 s but all adapted exact algorithms need more than 1000 s.

show abstract