{"url":"/method/repvgg","slug":"repvgg","name":"RepVGG","full_name":"RepVGG","full_name_withheld":false,"description_markdown":"**RepVGG** is a [VGG](https://paperswithcode.com/method/vgg)-style convolutional architecture. It has the following advantages:\r\n\r\n- The model has a VGG-like plain (a.k.a. feed-forward) topology 1 without any branches. I.e., every layer takes\r\nthe output of its only preceding layer as input and feeds the output into its only following layer.\r\n- The model’s body uses only 3 × 3 conv and [ReLU](https://paperswithcode.com/method/relu).\r\n- The concrete architecture (including the specific depth and layer widths) is instantiated with no automatic\r\nsearch, manual refinement, compound scaling, nor other heavy designs.","description_state":"present","introduced_year":null,"introduced_by":{"title":"RepVGG: Making VGG-style ConvNets Great Again","paper":"/paper/repvgg-making-vgg-style-convnets-great-again","first_author":"Xiaohan Ding","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/repvgg-making-vgg-style-convnets-great-again"},"source":{"url":"https://arxiv.org/abs/2101.03697v3","title":"RepVGG: Making VGG-style ConvNets Great Again","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Convolutional Neural Networks","url":"/methods/category/convolutional-neural-networks","pwc_aliases":[]}],"n_papers_tagged":13,"archive_num_papers":13,"papers_newest_first":[{"paper":null,"title":"On the Vulnerability of Skip Connections to Model Inversion Attacks","date":"2024-09-03","arxiv_id":"2409.01696","n_code_links":0,"syntology":null},{"paper":null,"title":"Oracle Bone Script Similiar Character Screening Approach Based on Simsiam Contrastive Learning and Supervised Learning","date":"2024-08-13","arxiv_id":"2408.06811","n_code_links":0,"syntology":null},{"paper":"/paper/repvgg-gelan-enhanced-gelan-with-vgg-style","title":"RepVGG-GELAN: Enhanced GELAN with VGG-STYLE ConvNets for Brain Tumour Detection","date":"2024-05-06","arxiv_id":"2405.03541","n_code_links":1,"syntology":null},{"paper":null,"title":"Outlier-Aware Training for Low-Bit Quantization of Structural Re-Parameterized Networks","date":"2024-02-11","arxiv_id":"2402.07200","n_code_links":0,"syntology":null},{"paper":null,"title":"NeRCC: Nested-Regression Coded Computing for Resilient Distributed Prediction Serving Systems","date":"2024-02-06","arxiv_id":"2402.04377","n_code_links":0,"syntology":null},{"paper":null,"title":"Detection of Small Targets in Sea Clutter Based on RepVGG and Continuous Wavelet Transform","date":"2023-11-14","arxiv_id":"2311.07912","n_code_links":0,"syntology":null},{"paper":null,"title":"UNISOUND System for VoxCeleb Speaker Recognition Challenge 2023","date":"2023-08-24","arxiv_id":"2308.12526","n_code_links":0,"syntology":null},{"paper":null,"title":"A region and category confidence-based multi-task network for carotid ultrasound image segmentation and classification","date":"2023-07-02","arxiv_id":"2307.00583","n_code_links":0,"syntology":null},{"paper":"/paper/make-repvgg-greater-again-a-quantization","title":"Make RepVGG Greater Again: A Quantization-aware Approach","date":"2022-12-03","arxiv_id":"2212.01593","n_code_links":2,"syntology":null},{"paper":null,"title":"Artificial Intelligence for Automatic Detection and Classification Disease on the X-Ray Images","date":"2022-11-14","arxiv_id":"2211.08244","n_code_links":0,"syntology":null},{"paper":"/paper/rmnet-equivalently-removing-residual-1","title":"RMNet: Equivalently Removing Residual Connection from Networks","date":"2021-11-01","arxiv_id":"2111.00687","n_code_links":1,"syntology":null},{"paper":null,"title":"Fast query-by-example speech search using separable model","date":"2021-09-18","arxiv_id":"2109.08870","n_code_links":0,"syntology":null},{"paper":"/paper/repvgg-making-vgg-style-convnets-great-again","title":"RepVGG: Making VGG-style ConvNets Great Again","date":"2021-01-11","arxiv_id":"2101.03697","n_code_links":25,"syntology":{"ran":13,"of":16,"unverified":3,"pointer_only":6}}],"papers_shown":13,"tasks":[{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":3},{"task":null,"name":"GPU","papers":2},{"task":"/task/quantization","name":"Quantization","papers":2},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":1},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/diagnostic","name":"Diagnostic","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":1},{"task":"/task/multi-task-learning","name":"Multi-Task Learning","papers":1},{"task":"/task/network-pruning","name":"Network Pruning","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/segmentation","name":"Segmentation","papers":1},{"task":"/task/speaker-recognition","name":"Speaker Recognition","papers":1},{"task":"/task/word-embeddings","name":"Word Embeddings","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1},{"task":"/task/regression-1","name":"regression","papers":1}],"tasks_shown":18,"n_tasks":18,"usage_by_year":[{"year":"2021","papers":3},{"year":"2022","papers":2},{"year":"2023","papers":3},{"year":"2024","papers":5}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/repvgg"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}