wk910930 / diagnosing-object-detectors
This project shows how to analyze the influences of object characteristics on detection performance and the frequency and impact of different types of false positives.
☆40Updated 7 years ago
Related projects ⓘ
Alternatives and complementary repositories for diagnosing-object-detectors
- Data Priming Network for Automatic Check-Out - ACMMM 2019☆26Updated 5 years ago
- A flexible tool for building and sharing deep learning modules.☆44Updated 6 years ago
- Code for calculating the upper bound AP in object detection☆81Updated 4 years ago
- Weakly Supervised Object Detection☆27Updated 4 years ago
- Implementation of NeurIPS2020 paper: Auto-Panoptic: Multi-Component Architecture Search for Panoptic Segmentation☆20Updated 4 years ago
- Data Augmentation for Object Detection via Progressive and Selective Instance-Switching☆77Updated 4 years ago
- Official repository of CVPR 2020 paper "On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location"☆69Updated 3 years ago
- Open MMLab Detection Toolbox and Benchmark☆14Updated 5 years ago
- SaccadeNet : mimic how human locate accurate bounding box☆29Updated 5 years ago
- The code is available at https://github.com/ethvis/qd-track☆46Updated 4 years ago
- ☆47Updated 2 years ago
- Hierarchical Shot Detector (ICCV2019)☆57Updated 3 years ago
- Codes for paper: "IoU-Uniform R-CNN: Breaking Through the Limitations of RPN"☆51Updated 4 years ago
- SOGNet: Scene Overlap Graph Network for Panoptic Segmentation☆56Updated 3 years ago
- Panoptic Feature Pyramid Networks☆59Updated 5 years ago
- Localization Recall Precision Performance Metric toolkit for PASCAL-VOC, COCO datasets with Python and MATLAB implementations.☆63Updated 3 years ago
- Adopting Path Aggregation Network for Monocular Depth Estimation - PyTorch☆26Updated 6 years ago
- Semi-supervised Adaptive Distillation is a model compression method for object detection.☆59Updated 5 years ago
- roi_align_rotate, roi, nms, rotate, pytorch☆19Updated 5 years ago
- 1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking☆80Updated 3 years ago
- Pytorch 1.0 codes(including cuda codes) for Deformable Convolution Version 2☆18Updated 5 years ago
- Implementation of "Anchor Loss: Modulating loss scale based on prediction difficulty"☆53Updated 3 years ago
- You are welcomed to join us!☆50Updated 4 years ago
- ☆26Updated 3 years ago
- ZZNet in Detectron☆20Updated 5 years ago
- ☆63Updated 4 years ago
- YOLACT: Real-time Instance Segmentation on the FCOS detector (without bbox cropping), achives 35.2mAP on coco val☆90Updated 4 years ago
- Rectified Convolution☆45Updated 2 years ago
- Official implementation of our paper "LLA: Loss-aware Label Assignment for Dense Pedestrian Detection" in Pytorch.☆35Updated 3 years ago