File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1609/aaai.v34i07.6720
- Scopus: eid_2-s2.0-85093258076
- WOS: WOS:000668126803041
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Channel pruning guided by classification loss and feature importance
Title | Channel pruning guided by classification loss and feature importance |
---|---|
Authors | |
Issue Date | 2020 |
Citation | AAAI 2020 - 34th AAAI Conference on Artificial Intelligence, 2020, p. 10885-10892 How to Cite? |
Abstract | In this work, we propose a new layer-by-layer channel pruning method called Channel Pruning guided by classification Loss and feature Importance (CPLI). In contrast to the existing layer-by-layer channel pruning approaches that only consider how to reconstruct the features from the next layer, our approach additionally take the classification loss into account in the channel pruning process. We also observe that some reconstructed features will be removed at the next pruning stage. So it is unnecessary to reconstruct these features. To this end, we propose a new strategy to suppress the influence of unimportant features (i.e., the features will be removed at the next pruning stage). Our comprehensive experiments on three benchmark datasets, i.e., CIFAR-10, ImageNet, and UCF-101, demonstrate the effectiveness of our CPLI method. |
Persistent Identifier | http://hdl.handle.net/10722/321903 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Guo, Jinyang | - |
dc.contributor.author | Ouyang, Wanli | - |
dc.contributor.author | Xu, Dong | - |
dc.date.accessioned | 2022-11-03T02:22:14Z | - |
dc.date.available | 2022-11-03T02:22:14Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | AAAI 2020 - 34th AAAI Conference on Artificial Intelligence, 2020, p. 10885-10892 | - |
dc.identifier.uri | http://hdl.handle.net/10722/321903 | - |
dc.description.abstract | In this work, we propose a new layer-by-layer channel pruning method called Channel Pruning guided by classification Loss and feature Importance (CPLI). In contrast to the existing layer-by-layer channel pruning approaches that only consider how to reconstruct the features from the next layer, our approach additionally take the classification loss into account in the channel pruning process. We also observe that some reconstructed features will be removed at the next pruning stage. So it is unnecessary to reconstruct these features. To this end, we propose a new strategy to suppress the influence of unimportant features (i.e., the features will be removed at the next pruning stage). Our comprehensive experiments on three benchmark datasets, i.e., CIFAR-10, ImageNet, and UCF-101, demonstrate the effectiveness of our CPLI method. | - |
dc.language | eng | - |
dc.relation.ispartof | AAAI 2020 - 34th AAAI Conference on Artificial Intelligence | - |
dc.title | Channel pruning guided by classification loss and feature importance | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1609/aaai.v34i07.6720 | - |
dc.identifier.scopus | eid_2-s2.0-85093258076 | - |
dc.identifier.spage | 10885 | - |
dc.identifier.epage | 10892 | - |
dc.identifier.isi | WOS:000668126803041 | - |