{"url":"/method/bottom-up-path-augmentation","slug":"bottom-up-path-augmentation","name":"Bottom-up Path Augmentation","full_name":"Bottom-up Path Augmentation","full_name_withheld":false,"description_markdown":"**Bottom-up Path Augmentation** is a feature extraction technique that seeks to shorten the information path and enhance a feature pyramid with accurate localization signals existing in low-levels. This is based on the fact that high response to edges or instance parts is a strong indicator to accurately localize instances. \r\n\r\nEach building block takes a higher resolution feature map $N\\_{i}$ and a coarser map $P\\_{i+1}$ through lateral connection and generates the new feature map $N\\_{i+1}$ Each feature map $N\\_{i}$ first goes through a $3 \\times 3$ convolutional layer with stride $2$ to reduce the spatial size. Then each element of feature map $P\\_{i+1}$ and the down-sampled map are added through lateral connection. The fused feature map is then processed by another $3 \\times 3$ convolutional layer to generate $N\\_{i+1}$ for following sub-networks. This is an iterative process and terminates after approaching $P\\_{5}$. In these building blocks, we consistently use channel 256 of feature maps. The feature grid for each proposal is then pooled from new feature maps, i.e., {$N\\_{2}$, $N\\_{3}$, $N\\_{4}$, $N\\_{5}$}.","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/1803.01534v4","title":"Path Aggregation Network for Instance Segmentation","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/ShuLiu1993/PANet/blob/2644d5ad6ae98c2bf58df45c8792c019b1d7b2b9/lib/modeling/FPN.py#L135","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Feature Extractors","url":"/methods/category/feature-extractors","pwc_aliases":[]}],"n_papers_tagged":123,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/event-based-crossing-dataset-ebcd","title":"Event-Based Crossing Dataset (EBCD)","date":"2025-03-21","arxiv_id":"2503.17499","n_code_links":1,"syntology":null},{"paper":null,"title":"YOLO-LLTS: Real-Time Low-Light Traffic Sign Detection via Prior-Guided Enhancement and Multi-Branch Feature Interaction","date":"2025-03-18","arxiv_id":"2503.13883","n_code_links":0,"syntology":null},{"paper":"/paper/walnutdata-a-uav-remote-sensing-dataset-of","title":"WalnutData: A UAV Remote Sensing Dataset of Green Walnuts and Model Evaluation","date":"2025-02-27","arxiv_id":"2502.20092","n_code_links":1,"syntology":null},{"paper":"/paper/mhaf-yolo-multi-branch-heterogeneous","title":"MHAF-YOLO: Multi-Branch Heterogeneous Auxiliary Fusion YOLO for accurate object detection","date":"2025-02-07","arxiv_id":"2502.04656","n_code_links":1,"syntology":null},{"paper":null,"title":"Vision-Integrated LLMs for Autonomous Driving Assistance : Human Performance Comparison and Trust Evaluation","date":"2025-02-06","arxiv_id":"2502.06843","n_code_links":0,"syntology":null},{"paper":null,"title":"YOLOv4: A Breakthrough in Real-Time Object Detection","date":"2025-02-06","arxiv_id":"2502.04161","n_code_links":0,"syntology":null},{"paper":null,"title":"SPFFNet: Strip Perception and Feature Fusion Spatial Pyramid Pooling for Fabric Defect Detection","date":"2025-02-03","arxiv_id":"2502.01445","n_code_links":0,"syntology":null},{"paper":null,"title":"Efficient Object Detection of Marine Debris using Pruned YOLO Model","date":"2025-01-27","arxiv_id":"2501.16571","n_code_links":0,"syntology":null},{"paper":null,"title":"Object Detection Approaches to Identifying Hand Images with High Forensic Values","date":"2024-12-21","arxiv_id":"2412.16431","n_code_links":0,"syntology":null},{"paper":null,"title":"Exploring Machine Learning Engineering for Object Detection and Tracking by Unmanned Aerial Vehicle (UAV)","date":"2024-12-19","arxiv_id":"2412.15347","n_code_links":0,"syntology":null},{"paper":null,"title":"UICE-MIRNet guided image enhancement for underwater object detection","date":"2024-09-24","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/a-lightweight-insulator-defect-detection","title":"A Lightweight Insulator Defect Detection Model Based on Drone Images","date":"2024-08-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"PANet: A Physics-guided Parametric Augmentation Net for Image Dehazing by Hazing","date":"2024-04-14","arxiv_id":"2404.09269","n_code_links":0,"syntology":null},{"paper":null,"title":"A Parallel Attention Network for Cattle Face Recognition","date":"2024-03-29","arxiv_id":"2403.19980","n_code_links":0,"syntology":null},{"paper":null,"title":"Toward Robust Canine Cardiac Diagnosis: Deep Prototype Alignment Network-Based Few-Shot Segmentation in Veterinary Medicine","date":"2024-03-11","arxiv_id":"2403.06471","n_code_links":0,"syntology":null},{"paper":null,"title":"More than the Sum of Its Parts: Ensembling Backbone Networks for Few-Shot Segmentation","date":"2024-02-09","arxiv_id":"2402.06581","n_code_links":0,"syntology":null},{"paper":"/paper/yolo-former-yolo-shakes-hand-with-vit","title":"YOLO-Former: YOLO Shakes Hand With ViT","date":"2024-01-11","arxiv_id":"2401.06244","n_code_links":0,"syntology":null},{"paper":null,"title":"HyperSense: Hyperdimensional Intelligent Sensing for Energy-Efficient Sparse Data Processing","date":"2024-01-04","arxiv_id":"2401.10267","n_code_links":0,"syntology":null},{"paper":null,"title":"Global Feature Pyramid Network","date":"2023-12-18","arxiv_id":"2312.11231","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-synthetic-and-real-worlds-for-pre","title":"Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors","date":"2023-12-08","arxiv_id":"2312.05286","n_code_links":1,"syntology":null},{"paper":"/paper/toward-improving-robustness-of-object","title":"Toward Improving Robustness of Object Detectors Against Domain Shift","date":"2023-12-02","arxiv_id":"2403.12049","n_code_links":1,"syntology":null},{"paper":null,"title":"YOLOv5s-BC: An improved YOLOv5s-based method for real-time apple detection","date":"2023-11-10","arxiv_id":"2311.05811","n_code_links":0,"syntology":null},{"paper":null,"title":"Feature Aggregation in Joint Sound Classification and Localization Neural Networks","date":"2023-10-29","arxiv_id":"2310.19063","n_code_links":0,"syntology":null},{"paper":null,"title":"Application of deep learning for livestock behaviour recognition: A systematic literature review","date":"2023-10-20","arxiv_id":"2310.13483","n_code_links":0,"syntology":null},{"paper":null,"title":"Parking Spot Classification based on surround view camera system","date":"2023-10-05","arxiv_id":"2310.12997","n_code_links":0,"syntology":null},{"paper":null,"title":"Randomize to Generalize: Domain Randomization for Runway FOD Detection","date":"2023-09-23","arxiv_id":"2309.13264","n_code_links":0,"syntology":null},{"paper":null,"title":"Automatic Signboard Recognition in Low Quality Night Images","date":"2023-08-17","arxiv_id":"2308.08941","n_code_links":0,"syntology":null},{"paper":null,"title":"YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems","date":"2023-07-26","arxiv_id":"2307.13901","n_code_links":0,"syntology":null},{"paper":"/paper/panet-lidar-panoptic-segmentation-with-sparse","title":"PANet: LiDAR Panoptic Segmentation with Sparse Instance Proposal and Aggregation","date":"2023-06-27","arxiv_id":"2306.15348","n_code_links":1,"syntology":null},{"paper":"/paper/group-channel-pruning-and-spatial-attention","title":"Group channel pruning and spatial attention distilling for object detection","date":"2023-06-02","arxiv_id":"2306.01526","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":69},{"task":"/task/object-detection-1","name":"object-detection","papers":63},{"task":"/task/object","name":"Object","papers":33},{"task":"/task/segmentation","name":"Segmentation","papers":13},{"task":"/task/real-time-object-detection","name":"Real-Time Object Detection","papers":12},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":12},{"task":null,"name":"GPU","papers":8},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":7},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":7},{"task":"/task/deep-learning","name":"Deep Learning","papers":7},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":7},{"task":"/task/2d-object-detection","name":"2D Object Detection","papers":5},{"task":"/task/image-classification","name":"Image Classification","papers":5},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":5},{"task":"/task/small-object-detection","name":"Small Object Detection","papers":4},{"task":"/task/traffic-sign-detection","name":"Traffic Sign Detection","papers":4},{"task":"/task/image-classification","name":"image-classification","papers":4},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":3},{"task":"/task/object-tracking","name":"Object Tracking","papers":3},{"task":null,"name":"Position","papers":3}],"tasks_shown":20,"n_tasks":144,"usage_by_year":[{"year":"2018","papers":1},{"year":"2019","papers":4},{"year":"2020","papers":18},{"year":"2021","papers":28},{"year":"2022","papers":33},{"year":"2023","papers":21},{"year":"2024","papers":10},{"year":"2025","papers":8}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/bottom-up-path-augmentation"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}