{"url":"/method/darknet-19","slug":"darknet-19","name":"Darknet-19","full_name":"Darknet-19","full_name_withheld":false,"description_markdown":"**Darknet-19** is a convolutional neural network that is used as the backbone of [YOLOv2](https://paperswithcode.com/method/yolov2).  Similar to the [VGG](https://paperswithcode.com/method/vgg) models it mostly uses $3 \\times 3$ filters and doubles the number of channels after every pooling step. Following the work on Network in Network (NIN) it uses [global average pooling](https://paperswithcode.com/method/global-average-pooling) to make predictions as well as $1 \\times 1$ filters to compress the feature representation between $3 \\times 3$ convolutions. [Batch Normalization](https://paperswithcode.com/method/batch-normalization) is used to stabilize training, speed up convergence, and regularize the model batch.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1612.08242v1","title":"YOLO9000: Better, Faster, Stronger","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/longcw/yolo2-pytorch/blob/17056ca69f097a07884135d9031c53d4ef217a6a/darknet.py#L140","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Convolutional Neural Networks","url":"/methods/category/convolutional-neural-networks","pwc_aliases":[]}],"n_papers_tagged":52,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"DOEPatch: Dynamically Optimized Ensemble Model for Adversarial Patches Generation","date":"2023-12-28","arxiv_id":"2312.16907","n_code_links":0,"syntology":null},{"paper":null,"title":"Area is all you need: repeatable elements make stronger adversarial attacks","date":"2023-06-13","arxiv_id":"2306.07768","n_code_links":0,"syntology":null},{"paper":null,"title":"Improved Type III solar radio burst detection using congruent deep learning models","date":"2023-05-16","arxiv_id":"2305.09327","n_code_links":0,"syntology":null},{"paper":"/paper/yowo-plus-an-incremental-improvement","title":"YOWO-Plus: An Incremental Improvement","date":"2022-10-20","arxiv_id":"2210.11219","n_code_links":1,"syntology":null},{"paper":null,"title":"People detection and social distancing classification in smart cities for COVID-19 by using thermal images and deep learning algorithms","date":"2022-09-10","arxiv_id":"2209.04704","n_code_links":0,"syntology":null},{"paper":null,"title":"YOLO and Mask R-CNN for Vehicle Number Plate Identification","date":"2022-07-26","arxiv_id":"2207.13165","n_code_links":0,"syntology":null},{"paper":null,"title":"Hybrid Classifiers for Spatio-temporal Real-time Abnormal Behaviors Detection, Tracking, and Recognition in Massive Hajj Crowds","date":"2022-07-25","arxiv_id":"2207.11931","n_code_links":0,"syntology":null},{"paper":null,"title":"Detecting Cloud-Based Phishing Attacks by Combining Deep Learning Models","date":"2022-04-05","arxiv_id":"2204.02446","n_code_links":0,"syntology":null},{"paper":null,"title":"Efficient Placard Discovery for Semantic Mapping During Frontier Exploration","date":"2021-10-27","arxiv_id":"2110.14742","n_code_links":0,"syntology":null},{"paper":null,"title":"PhiNets: a scalable backbone for low-power AI at the edge","date":"2021-10-01","arxiv_id":"2110.00337","n_code_links":0,"syntology":null},{"paper":null,"title":"MAFAT: Memory-Aware Fusing and Tiling of Neural Networks for Accelerated Edge Inference","date":"2021-07-14","arxiv_id":"2107.06960","n_code_links":0,"syntology":null},{"paper":null,"title":"Adversarial YOLO: Defense Human Detection Patch Attacks via Detecting Adversarial Patches","date":"2021-03-16","arxiv_id":"2103.08860","n_code_links":0,"syntology":null},{"paper":null,"title":"RMOPP: Robust Multi-Objective Post-Processing for Effective Object Detection","date":"2021-02-09","arxiv_id":"2102.04582","n_code_links":0,"syntology":null},{"paper":"/paper/deep-dup-an-adversarial-weight-duplication","title":"Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGA","date":"2020-11-05","arxiv_id":"2011.03006","n_code_links":1,"syntology":null},{"paper":null,"title":"Dynamic Adversarial Patch for Evading Object Detection Models","date":"2020-10-25","arxiv_id":"2010.13070","n_code_links":0,"syntology":null},{"paper":null,"title":"Multilanguage Number Plate Detection using Convolutional Neural Networks","date":"2020-08-18","arxiv_id":"2008.08023","n_code_links":0,"syntology":null},{"paper":null,"title":"FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networks","date":"2020-03-27","arxiv_id":"2003.12203","n_code_links":0,"syntology":null},{"paper":null,"title":"ParkingSticker: A Real-World Object Detection Dataset","date":"2020-01-31","arxiv_id":"2001.11639","n_code_links":0,"syntology":null},{"paper":null,"title":"A lightweight target detection algorithm based on Mobilenet Convolution","date":"2020-01-16","arxiv_id":"2002.03729","n_code_links":0,"syntology":null},{"paper":null,"title":"Comparison of object detection methods for crop damage assessment using deep learning","date":"2019-12-31","arxiv_id":"1912.13199","n_code_links":0,"syntology":null},{"paper":null,"title":"Deep SCNN-based Real-time Object Detection for Self-driving Vehicles Using LiDAR Temporal Data","date":"2019-12-17","arxiv_id":"1912.07906","n_code_links":0,"syntology":null},{"paper":"/paper/liteseg-a-novel-lightweight-convnet-for","title":"LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation","date":"2019-12-13","arxiv_id":"1912.06683","n_code_links":2,"syntology":null},{"paper":null,"title":"PhoneBit: Efficient GPU-Accelerated Binary Neural Network Inference Engine for Mobile Phones","date":"2019-12-05","arxiv_id":"1912.04050","n_code_links":0,"syntology":null},{"paper":"/paper/ifq-net-integrated-fixed-point-quantization","title":"IFQ-Net: Integrated Fixed-point Quantization Networks for Embedded Vision","date":"2019-11-19","arxiv_id":"1911.08076","n_code_links":0,"syntology":null},{"paper":null,"title":"Pavement Image Datasets: A New Benchmark Dataset to Classify and Densify Pavement Distresses","date":"2019-10-20","arxiv_id":"1910.11123","n_code_links":0,"syntology":null},{"paper":"/paper/evading-real-time-person-detectors-by","title":"Adversarial T-shirt! Evading Person Detectors in A Physical World","date":"2019-10-18","arxiv_id":"1910.11099","n_code_links":1,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":3}},{"paper":"/paper/yolo-nano-a-highly-compact-you-only-look-once","title":"YOLO Nano: a Highly Compact You Only Look Once Convolutional Neural Network for Object Detection","date":"2019-10-03","arxiv_id":"1910.01271","n_code_links":4,"syntology":null},{"paper":null,"title":"Vision-Based Autonomous Vehicle Control using the Two-Point Visual Driver Control Model","date":"2019-09-29","arxiv_id":"1910.04862","n_code_links":0,"syntology":null},{"paper":null,"title":"Simultaneous Iris and Periocular Region Detection Using Coarse Annotations","date":"2019-07-31","arxiv_id":"1908.00069","n_code_links":0,"syntology":null},{"paper":null,"title":"A Comparison of Super-Resolution and Nearest Neighbors Interpolation Applied to Object Detection on Satellite Data","date":"2019-07-08","arxiv_id":"1907.05283","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":30},{"task":"/task/object-detection-1","name":"object-detection","papers":29},{"task":"/task/object","name":"Object","papers":18},{"task":"/task/deep-learning","name":"Deep Learning","papers":5},{"task":null,"name":"GPU","papers":5},{"task":"/task/real-time-object-detection","name":"Real-Time Object Detection","papers":5},{"task":"/task/3d-object-detection","name":"3D Object Detection","papers":3},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":3},{"task":"/task/classification","name":"General Classification","papers":3},{"task":"/task/image-classification","name":"Image Classification","papers":3},{"task":"/task/quantization","name":"Quantization","papers":3},{"task":"/task/attribute","name":"Attribute","papers":2},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":2},{"task":"/task/human-detection","name":"Human Detection","papers":2},{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/image-classification","name":"image-classification","papers":2},{"task":"/task/action-detection","name":"Action Detection","papers":1},{"task":"/task/active-learning","name":"Active Learning","papers":1},{"task":"/task/activity-recognition","name":"Activity Recognition","papers":1},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":1}],"tasks_shown":20,"n_tasks":54,"usage_by_year":[{"year":"2016","papers":1},{"year":"2017","papers":4},{"year":"2018","papers":12},{"year":"2019","papers":16},{"year":"2020","papers":6},{"year":"2021","papers":5},{"year":"2022","papers":5},{"year":"2023","papers":3}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/darknet-19"},"syntology_read_at":"2026-09-25T09:33:49+00:00"}