[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81979-en":3,"doc-seo-81979-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},81979,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware","Scaling down input image resolution can substantially reduce convolutional neural network (CNN) computation, which is attractive for edge AI. Yet uniform resizing wastes spatial redundancy while discarding critical foreground details, causing accuracy loss. Smart Scissor introduces dynamic, instance-aware cropping using a lightweight foreground predictor, enabling correct recognition at small resolutions. It further applies a compound CNN shrinking strategy over depth, width, and resolution, and combines both into one unified compression framework, validated on ImageNet-1K.","Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware  \nHao Kong1,2 , Di Liu2 , Shuo Huai1,2 , Xiangzhong Luo1 , Weichen Liu1 ,  \nRavi Subramaniam3 , Christian Makaya3 , and Qian Lin3  \n1School of Computer Science and Engineering, Nanyang Technological University, Singapore  \n2HP-NTU Digital Manufacturing Corporate Lab, Nanyang Technological University, Singapore  \n3HP Inc., Palo Alto, California, USA  \narXiv :2607 .069 15v 1 [ cs .CV] 8 Jul 2026  \nABSTRACT  \nScaling down the resolution of input images can greatly reduce the computational overhead of convolutional neural networks (CNNs), which is promising for edge AI. However, as an image usually contains much spatial redundancy, e.g., background pixels, directly shrinking the whole image will lose important features of the foreground object and lead to severe accuracy degradation. In this paper, we propose a dynamic image cropping framework to reduce the spatial redundancy by accurately cropping the foreground object from images. To achieve the instance-aware fine cropping, we introduce a lightweight foreground predictor to efficiently localize and crop the foreground of an image. The finely cropped images can be correctly recognized even at a small resolution. Meanwhile, computational redundancy also exists in CNN architectures. To pursue higher execution efficiency on resource-constrained embedded devices, we also propose a compound shrinking strategy to coordinately compress the three dimensions (depth, width, resolution) of CNNs. Eventually, we seamlessly combine the proposed dynamic image cropping and compound shrinking into a unified compression framework, Smart Scissor, which is expected to significantly reduce the computational overhead of CNNs while still maintaining high accuracy. Experiments on ImageNet-1K demonstrate that our method reduces the computational cost of ResNet50 by 41.5% while improving the top-1 accuracy by 0.3% . Moreover, compared to HRank, the state-of-theart CNN compression framework, our method achieves 4.1% higher top-1 accuracy at the same computational cost. The codes and data are available at [https://github.com/ntuliuteam/smart-scissor](https://github.com/ntuliuteam/smart-scissor)  \n1 INTRODUCTION  \nModern convolutional neural networks (CNNs) continue to break previous accuracy records with the advances in large-scale datasets [3, 4, 21, 28] and network architecture innovation [22, 24, 34, 39] . Naturally, the accuracy improvement comes at the cost of higher computational overhead [2, 7, 34] . Recently, there is a trend deploying CNNs in edge environments [31] to mitigate the latency and privacy concerns. However, the prohibitive computational  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions [from permissions@acm.org](from permissions@acm.org).  \nICCAD’22, October 30-November 3, 2022, San Diego, CA, USA © 2022 Association for Computing Machinery.  \nACM ISBN 978-1-4503-9217-4/22/10. . . $15.00 [https://doi.org/10.1145/3508352.3549397](https://doi.org/10.1145/3508352.3549397)  \nindigo bird Easy sample  \nFigure 1: The prediction results of our pretrained ResNet- 50 model. For easy samples, the network can still generate correct predictions at a smaller resolution (e.g. 112 × 112 for ImageNet). For hard samples, simply resizing the images to a smaller resolution can lead to misclassification, while the dynamic cropping strategy can correctly classify hard samples at a smaller resolution.  \ncost impedes the dep","cbCaigclkQvoSXQ1","https://ap.wps.com/l/cbCaigclkQvoSXQ1","pdf",1454036,3,1,9,"English","en",105,"# Abstract\n# Introduction\n## Motivation: Cost from Architecture and Resolution\n## Dynamic Image Cropping vs Static Cropping","[{\"question\":\"What problem does Smart Scissor address for edge AI deployment?\",\"answer\":\"Smart Scissor targets the high computational cost of CNNs on resource-constrained edge devices, where both network architecture and high-resolution inputs increase Multiply-Accumulate Operations (MACs).\"},{\"question\":\"How does Smart Scissor reduce spatial redundancy without hurting accuracy?\",\"answer\":\"It uses a dynamic image cropping framework that accurately crops the foreground object, driven by a lightweight foreground predictor, so low-resolution inference preserves essential details.\"},{\"question\":\"What is the compound shrinking strategy, and how is it combined with cropping?\",\"answer\":\"Smart Scissor coordinates compression across three CNN dimensions—depth, width, and resolution—then seamlessly unifies this compound shrinking with dynamic image cropping into a single compression framework.\"}]",1784177390,23,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"smart-scissor-coupling-spatial-redundancy-reduction-and-cnn-compression-for-embedded-hardware","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/smart-scissor-coupling-spatial-redundancy-reduction-and-cnn-compression-for-embedded-hardware/81979/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-29","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does Smart Scissor address for edge AI deployment?","Question",{"text":75,"@type":76},"Smart Scissor targets the high computational cost of CNNs on resource-constrained edge devices, where both network architecture and high-resolution inputs increase Multiply-Accumulate Operations (MACs).","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does Smart Scissor reduce spatial redundancy without hurting accuracy?",{"text":80,"@type":76},"It uses a dynamic image cropping framework that accurately crops the foreground object, driven by a lightweight foreground predictor, so low-resolution inference preserves essential details.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the compound shrinking strategy, and how is it combined with cropping?",{"text":84,"@type":76},"Smart Scissor coordinates compression across three CNN dimensions—depth, width, and resolution—then seamlessly unifies this compound shrinking with dynamic image cropping into a single compression framework.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]