feature-pyramid-network 开源项目推荐（36 个）

unsky /FPN

Feature Pyramid Networks for Object Detection

haofengac /MonoDepth-FPN-PyTorch

Single Image Depth Estimation with Feature Pyramid Network

42gas42 /multiclass-semantic-segmentation

Experiments with UNET/FPN models and cityscapes/kitti datasets [Pytorch]

zubair-irshad /NeRF-MAE

[ECCV 2024]我们ECCV'24论文NeRF-MAE：用于神经辐射场自监督3D表示学习的蒙面自编码器中的Pytorch代码

simonmeister /motion-rcnn

Motion R-CNN: Mask R-CNN with support for 3D motion estimation (prototype)

AdeelH /pytorch-fpn

PyTorch implementations of some FPN-based semantic segmentation architectures: vanilla FPN, Panoptic FPN, PANet FPN; with ResNet and EfficientNet backbones.

EmGarr /kerod

DETR - Faster RCNN implementation in tensorflow 2

yuhuan-wu /RDPNet

(IEEE TIP 2021) Regularized Densely-connected Pyramid Network for Salient Instance Segmentation

kbhujbal /LungGuardianAI-pneumonia_detection_from_chest_xrays_with_transfer_learning

State-of-the-Art Pneumonia detection from chest X-rays system using EfficientNetV2 + FPN + Faster R-CNN. Features Focal Loss, Weighted Box Fusion, Mosaic Augmentation & StratifiedGroupKFold. Built for RSNA Pneumonia Detection Challenge. Achieves competitive mAP with mixed-precision training.

stnamjef /feature_pyramid_network

Feature Pyramid Network based on VGG16 and ResNet101

D0352276 /SFPN-Synthetic-FPN-for-Object-Detection

The SFPN is a novel plug-and-play component for the CNN object detector. This project is the official code for the paper "SFPN: Synthetic FPN for Object Detection" in IEEE ICIP 2022.

dyneth02 /MoveNet-Multipose-Detection-OpenCV

A real-time multi-person human pose estimation system using TensorFlow MoveNet Multipose (Lightning). Built with OpenCV for video and webcam inference, it detects and visualizes keypoints and skeletal connections with confidence-based filtering, optimized for speed and multi-person scenarios.

edaaydinea /Low-Grade-Glioma-Segmentation

This is a capstone project on a real dataset related to segmenting low-grade glioma. This capstone project is included in the UpSchool Machine Learning & Deep Learning Program in partnership with Google Developers.

Ziruiwang409 /improved-faster-rcnn

Object Detector for Autonomous Vehicles Based on Improved Faster-RCNN

001honi /video-processing

Digital Video Processing Graduate Course Homeworks

CrazyFroggyFrogDev /ShipSARDetect_mmdetection

Project on the implementation of deep-learning models for ship detection on SAR images.

AI-14 /micar-vl-moe

[IJCNN 2025] [Official code] - MicarVLMoE: A modern gated cross-aligned vision-language mixture of experts model for medical image captioning and report generation

DLforLife /RetinaNet

该项目在 GitHub 上没有填写描述

film-net /film-net.github.io

Website of "FILM: Frame Interpolation for Large Motion", In ECCV 2022.

Detection-Learner /PyTorch-Faster-R-CNN

该项目在 GitHub 上没有填写描述