File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-030-58607-2_35
- Scopus: eid_2-s2.0-85097431150
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: CN: Channel Normalization for Point Cloud Recognition
Title | CN: Channel Normalization for Point Cloud Recognition |
---|---|
Authors | |
Keywords | 3D recognition Point cloud Object detection Classification |
Issue Date | 2020 |
Publisher | Springer. The Proceedings' web site is located at https://link.springer.com/conference/eccv |
Citation | Proceedings of the 16th European Conference on Computer Vision (ECCV), Online, Glasgow, UK, 23-28 August 2020, pt X, p. 600-616 How to Cite? |
Abstract | In 3D recognition, to fuse multi-scale structure information, existing methods apply hierarchical frameworks stacked by multiple fusion layers for integrating current relative locations with structure information from the previous level. In this paper, we deeply analyze these point recognition frameworks and present a factor, called difference ratio, to measure the influence of structure information among different levels on the final representation. We discover that structure information in deeper layers is overwhelmed by information in shallower layers in generating the final features, which prevents the model from understanding the point cloud in a global view. Inspired by this observation, we propose a novel channel normalization scheme to balance structure information among different layers and avoid excessive accumulation of shallow information, which benefits the model in exploiting and integrating multilayer structure information. We evaluate our channel normalization in several core 3D recognition tasks including classification, segmentation and detection. Experimental results show that our channel normalization further boosts the performance of state-of-the-art methods effectively. |
Persistent Identifier | http://hdl.handle.net/10722/294235 |
ISBN | |
Series/Report no. | Lecture Notes in Computer Science ; vol. 12355 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yang, Z | - |
dc.contributor.author | Sun, Y | - |
dc.contributor.author | Liu, S | - |
dc.contributor.author | Qi, X | - |
dc.contributor.author | Jia, J | - |
dc.date.accessioned | 2020-11-23T08:28:22Z | - |
dc.date.available | 2020-11-23T08:28:22Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | Proceedings of the 16th European Conference on Computer Vision (ECCV), Online, Glasgow, UK, 23-28 August 2020, pt X, p. 600-616 | - |
dc.identifier.isbn | 9783030586065 | - |
dc.identifier.uri | http://hdl.handle.net/10722/294235 | - |
dc.description.abstract | In 3D recognition, to fuse multi-scale structure information, existing methods apply hierarchical frameworks stacked by multiple fusion layers for integrating current relative locations with structure information from the previous level. In this paper, we deeply analyze these point recognition frameworks and present a factor, called difference ratio, to measure the influence of structure information among different levels on the final representation. We discover that structure information in deeper layers is overwhelmed by information in shallower layers in generating the final features, which prevents the model from understanding the point cloud in a global view. Inspired by this observation, we propose a novel channel normalization scheme to balance structure information among different layers and avoid excessive accumulation of shallow information, which benefits the model in exploiting and integrating multilayer structure information. We evaluate our channel normalization in several core 3D recognition tasks including classification, segmentation and detection. Experimental results show that our channel normalization further boosts the performance of state-of-the-art methods effectively. | - |
dc.language | eng | - |
dc.publisher | Springer. The Proceedings' web site is located at https://link.springer.com/conference/eccv | - |
dc.relation.ispartof | European Conference on Computer Vision (ECCV) | - |
dc.relation.ispartofseries | Lecture Notes in Computer Science ; vol. 12355 | - |
dc.subject | 3D recognition | - |
dc.subject | Point cloud | - |
dc.subject | Object detection | - |
dc.subject | Classification | - |
dc.title | CN: Channel Normalization for Point Cloud Recognition | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Qi, X: xjqi@eee.hku.hk | - |
dc.identifier.authority | Qi, X=rp02666 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1007/978-3-030-58607-2_35 | - |
dc.identifier.scopus | eid_2-s2.0-85097431150 | - |
dc.identifier.hkuros | 320010 | - |
dc.identifier.volume | pt X | - |
dc.identifier.spage | 600 | - |
dc.identifier.epage | 616 | - |
dc.publisher.place | Cham | - |