{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/matrixnets-a-new-scale-and-aspect-ratio-aware","title":"MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection","arxiv_id":"2001.03194","date":"2020-01-09","proceeding":null,"authors":["Abdullah Rashwan","Rishav Agarwal","Agastya Kalra","Pascal Poupart"],"abstract":"We present MatrixNets (xNets), a new deep architecture for object detection. xNets map objects with similar sizes and aspect ratios into many specialized layers, allowing xNets to provide a scale and aspect ratio aware architecture. We leverage xNets to enhance single-stage object detection frameworks. First, we apply xNets on anchor-based object detection, for which we predict object centers and regress the top-left and bottom-right corners. Second, we use MatrixNets for corner-based object detection by predicting top-left and bottom-right corners. Each corner predicts the center location of the object. We also enhance corner-based detection by replacing the embedding layer with center regression. Our final architecture achieves mAP of 47.8 on MS COCO, which is higher than its CornerNet counterpart by +5.6 mAP while also closing the gap between single-stage and two-stage detectors. The code is available at https://github.com/arashwan/matrixnet.","url_abs":"https://arxiv.org/abs/2001.03194v1","url_pdf":"https://arxiv.org/pdf/2001.03194v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"matrixnets-a-new-scale-and-aspect-ratio-aware","repo_url":"https://github.com/arashwan/matrixnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"corner-pooling","method_name":"Corner Pooling"},{"method_slug":"cornernet","method_name":"CornerNet"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"hourglass-module","method_name":"Hourglass Module"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"matrixnet","method_name":"MatrixNet"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"random-scaling","method_name":"Random Scaling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"soft-nms","method_name":"Soft-NMS"},{"method_slug":"stacked-hourglass-network","method_name":"Stacked Hourglass Network"},{"method_slug":"step-decay","method_name":"Step Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}