KernelWarehouse: Rethinking the Design of Dynamic Convolution
Dynamic convolution learns a linear mixture of n static kernels weighted with their input-dependent attentions, demonstrating superior performance than normal convolution. However, it increases the number of convolutional parameters by n times, and thus is not parameter efficient. This leads to no r...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Li, Chao Yao, Anbang |
| description | Dynamic convolution learns a linear mixture of n static kernels weighted with
their input-dependent attentions, demonstrating superior performance than
normal convolution. However, it increases the number of convolutional
parameters by n times, and thus is not parameter efficient. This leads to no
research progress that can allow researchers to explore the setting n>100 (an
order of magnitude larger than the typical setting n |
| doi_str_mv | 10.48550/arxiv.2406.07879 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2406_07879</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2406_07879</sourcerecordid><originalsourceid>FETCH-LOGICAL-a679-7c31f4efa5afb78803b3e5d04d009ef6a8bd97ae5f754b838d0bf008daea63233</originalsourceid><addsrcrecordid>eNotj8FKAzEUAHPxINUP8GR-YNfXJtlkhR5kq1YsCFLwuLw0L93QbSLZbbF_L7ae5jbMMHY3hVIapeAB8084ljMJVQna6Pqazd8pR-q_MFOXDgM98k8auxB3IW752BFf0BC2kSfPF6eI-7DhTYrH1B_GkOINu_LYD3T7zwlbvzyvm2Wx-nh9a55WBVa6LvRGTL0kjwq91caAsIKUA-kAavIVGutqjaS8VtIaYRxYD2AcElZiJsSE3V-05_72O4c95lP799GeP8Qvdf1Dlg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>KernelWarehouse: Rethinking the Design of Dynamic Convolution</title><source>arXiv.org</source><creator>Li, Chao ; Yao, Anbang</creator><creatorcontrib>Li, Chao ; Yao, Anbang</creatorcontrib><description>Dynamic convolution learns a linear mixture of n static kernels weighted with
their input-dependent attentions, demonstrating superior performance than
normal convolution. However, it increases the number of convolutional
parameters by n times, and thus is not parameter efficient. This leads to no
research progress that can allow researchers to explore the setting n>100 (an
order of magnitude larger than the typical setting n<10) for pushing forward
the performance boundary of dynamic convolution while enjoying parameter
efficiency. To fill this gap, in this paper, we propose KernelWarehouse, a more
general form of dynamic convolution, which redefines the basic concepts of
``kernels", ``assembling kernels" and ``attention function" through the lens of
exploiting convolutional parameter dependencies within the same layer and
across neighboring layers of a ConvNet. We testify the effectiveness of
KernelWarehouse on ImageNet and MS-COCO datasets using various ConvNet
architectures. Intriguingly, KernelWarehouse is also applicable to Vision
Transformers, and it can even reduce the model size of a backbone while
improving the model accuracy. For instance, KernelWarehouse (n=4) achieves
5.61%|3.90%|4.38% absolute top-1 accuracy gain on the
ResNet18|MobileNetV2|DeiT-Tiny backbone, and KernelWarehouse (n=1/4) with
65.10% model size reduction still achieves 2.29% gain on the ResNet18 backbone.
The code and models are available at https://github.com/OSVAI/KernelWarehouse.</description><identifier>DOI: 10.48550/arxiv.2406.07879</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning</subject><creationdate>2024-06</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2406.07879$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2406.07879$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Li, Chao</creatorcontrib><creatorcontrib>Yao, Anbang</creatorcontrib><title>KernelWarehouse: Rethinking the Design of Dynamic Convolution</title><description>Dynamic convolution learns a linear mixture of n static kernels weighted with
their input-dependent attentions, demonstrating superior performance than
normal convolution. However, it increases the number of convolutional
parameters by n times, and thus is not parameter efficient. This leads to no
research progress that can allow researchers to explore the setting n>100 (an
order of magnitude larger than the typical setting n<10) for pushing forward
the performance boundary of dynamic convolution while enjoying parameter
efficiency. To fill this gap, in this paper, we propose KernelWarehouse, a more
general form of dynamic convolution, which redefines the basic concepts of
``kernels", ``assembling kernels" and ``attention function" through the lens of
exploiting convolutional parameter dependencies within the same layer and
across neighboring layers of a ConvNet. We testify the effectiveness of
KernelWarehouse on ImageNet and MS-COCO datasets using various ConvNet
architectures. Intriguingly, KernelWarehouse is also applicable to Vision
Transformers, and it can even reduce the model size of a backbone while
improving the model accuracy. For instance, KernelWarehouse (n=4) achieves
5.61%|3.90%|4.38% absolute top-1 accuracy gain on the
ResNet18|MobileNetV2|DeiT-Tiny backbone, and KernelWarehouse (n=1/4) with
65.10% model size reduction still achieves 2.29% gain on the ResNet18 backbone.
The code and models are available at https://github.com/OSVAI/KernelWarehouse.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8FKAzEUAHPxINUP8GR-YNfXJtlkhR5kq1YsCFLwuLw0L93QbSLZbbF_L7ae5jbMMHY3hVIapeAB8084ljMJVQna6Pqazd8pR-q_MFOXDgM98k8auxB3IW752BFf0BC2kSfPF6eI-7DhTYrH1B_GkOINu_LYD3T7zwlbvzyvm2Wx-nh9a55WBVa6LvRGTL0kjwq91caAsIKUA-kAavIVGutqjaS8VtIaYRxYD2AcElZiJsSE3V-05_72O4c95lP799GeP8Qvdf1Dlg</recordid><startdate>20240612</startdate><enddate>20240612</enddate><creator>Li, Chao</creator><creator>Yao, Anbang</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240612</creationdate><title>KernelWarehouse: Rethinking the Design of Dynamic Convolution</title><author>Li, Chao ; Yao, Anbang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a679-7c31f4efa5afb78803b3e5d04d009ef6a8bd97ae5f754b838d0bf008daea63233</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Li, Chao</creatorcontrib><creatorcontrib>Yao, Anbang</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Li, Chao</au><au>Yao, Anbang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>KernelWarehouse: Rethinking the Design of Dynamic Convolution</atitle><date>2024-06-12</date><risdate>2024</risdate><abstract>Dynamic convolution learns a linear mixture of n static kernels weighted with
their input-dependent attentions, demonstrating superior performance than
normal convolution. However, it increases the number of convolutional
parameters by n times, and thus is not parameter efficient. This leads to no
research progress that can allow researchers to explore the setting n>100 (an
order of magnitude larger than the typical setting n<10) for pushing forward
the performance boundary of dynamic convolution while enjoying parameter
efficiency. To fill this gap, in this paper, we propose KernelWarehouse, a more
general form of dynamic convolution, which redefines the basic concepts of
``kernels", ``assembling kernels" and ``attention function" through the lens of
exploiting convolutional parameter dependencies within the same layer and
across neighboring layers of a ConvNet. We testify the effectiveness of
KernelWarehouse on ImageNet and MS-COCO datasets using various ConvNet
architectures. Intriguingly, KernelWarehouse is also applicable to Vision
Transformers, and it can even reduce the model size of a backbone while
improving the model accuracy. For instance, KernelWarehouse (n=4) achieves
5.61%|3.90%|4.38% absolute top-1 accuracy gain on the
ResNet18|MobileNetV2|DeiT-Tiny backbone, and KernelWarehouse (n=1/4) with
65.10% model size reduction still achieves 2.29% gain on the ResNet18 backbone.
The code and models are available at https://github.com/OSVAI/KernelWarehouse.</abstract><doi>10.48550/arxiv.2406.07879</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2406.07879 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2406_07879 |
| source | arXiv.org |
| subjects | Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning |
| title | KernelWarehouse: Rethinking the Design of Dynamic Convolution |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T19%3A49%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=KernelWarehouse:%20Rethinking%20the%20Design%20of%20Dynamic%20Convolution&rft.au=Li,%20Chao&rft.date=2024-06-12&rft_id=info:doi/10.48550/arxiv.2406.07879&rft_dat=%3Carxiv_GOX%3E2406_07879%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |