{"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/t-net-parametrizing-fully-convolutional-nets","title":"T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor","arxiv_id":"1904.02698","date":"2019-04-04","proceeding":"CVPR 2019 6","authors":["Jean Kossaifi","Adrian Bulat","Georgios Tzimiropoulos","Maja Pantic"],"abstract":"Recent findings indicate that over-parametrization, while crucial for\nsuccessfully training deep neural networks, also introduces large amounts of\nredundancy. Tensor methods have the potential to efficiently parametrize\nover-complete representations by leveraging this redundancy. In this paper, we\npropose to fully parametrize Convolutional Neural Networks (CNNs) with a single\nhigh-order, low-rank tensor. Previous works on network tensorization have\nfocused on parametrizing individual layers (convolutional or fully connected)\nonly, and perform the tensorization layer-by-layer separately. In contrast, we\npropose to jointly capture the full structure of a neural network by\nparametrizing it with a single high-order tensor, the modes of which represent\neach of the architectural design parameters of the network (e.g. number of\nconvolutional blocks, depth, number of stacks, input features, etc). This\nparametrization allows to regularize the whole network and drastically reduce\nthe number of parameters. Our model is end-to-end trainable and the low-rank\nstructure imposed on the weight tensor acts as an implicit regularization. We\nstudy the case of networks with rich structure, namely Fully Convolutional\nNetworks (FCNs), which we propose to parametrize with a single 8th-order\ntensor. We show that our approach can achieve superior performance with small\ncompression rates, and attain high compression rates with negligible drop in\naccuracy for the challenging task of human pose estimation.","url_abs":"http://arxiv.org/abs/1904.02698v1","url_pdf":"http://arxiv.org/pdf/1904.02698v1.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":[],"tasks":[{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pose-estimation-on-mpii-human-pose","task":"Pose Estimation","dataset":"MPII Human Pose","model":"Tucker T-Net","rank_in_archive_order":35,"of":46,"metrics":{"PCKh-0.5":"87.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.02698","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}