Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

This is an experiment adapting the project https://github.com/hubert10/fasterrcnn_resnet50_fpn_v2_new_dataset to detect wrist fractures using a selection of wrist fracture images obtained from https://universe.roboflow.com/landy-aw2jb/fracture-ov5p1/dataset/1 as a custom dataset. Given the positive results, it is uploaded to GitHub.

End-to-end FCOS object detector from scratch in PyTorch, including FPN, centerness, and NMS inference.

Small-scale, reproducible study of Feature Pyramid Networks for object detection on PASCAL VOC, analyzing multi-scale performance under limited compute budgets.

Drone detection with a simple program obtained by asking a simple question in the address bar of bings (copilot search)

An implementation of Feature Pyramid Network (FPN) and Yolo purely in rust - and a little sprinkle of python

Implement Panoptic FPN to Tackle Down Panoptic Segmentation for Cityscapes Dataset

Multi-task perception system

Scalable Instance Segmentation using PyTorch & PyTorch Lightning.

Using Faster R-CNN with ResNet50 and FPN to detect abnormalities in mammograms

Yolov3 with multi backbone

Image Segmentation using Oxford Pets Dataset with the goal to improve animal tranquilizer aiming system.

Distinguishing Urban Roads from Non-Road Regions in the Indian Driving Dataset(IDD) Using Binary Deep Learning Segmentation 🛣️

YOLOv3: An Incremental Improvement

This projects uses video feeds from endoscopic procedures to identify polyps in the gastrointestinal tract and draw masks around them to aid doctors in identifying precursors of colorectal cancer.

Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

Predicting cats feature points using a feature pyramid network

1D and 2D Segmentation Models with options such as Deep Supervision, Guided Attention, BiConvLSTM, Autoencoder, etc.

Efficient model for semantic segmentation on edge devices, specifically targeting the analysis of disaster scenes from images captured by unmanned aerial vehicles (UAVs).

A c++ trainable semantic segmentation library based on libtorch (pytorch c++). Backbone: VGG, ResNet, ResNext. Architecture: FPN, U-Net, PAN, LinkNet, PSPNet, DeepLab-V3, DeepLab-V3+ by now.