An Implementation of Faster RCNN with Study for Region Sampling
arXiv:1702.02138
Abstract
We adapted the join-training scheme of Faster RCNN framework from Caffe to TensorFlow as a baseline implementation for object detection. Our code is made publicly available. This report documents the simplifications made to the original pipeline, with justifications from ablation analysis on both PASCAL VOC 2007 and COCO 2014. We further investigated the role of non-maximal suppression (NMS) in selecting regions-of-interest (RoIs) for region classification, and found that a biased sampling toward small regions helps performance and can achieve on-par mAP to NMS-based sampling when converged sufficiently.
arXiv commentTechnical Report, 3 pages
References in corpus (3)
Cited by in corpus (27)
- Monitoring COVID-19 social distancing with person detection and tracking via fine-tuned YOLO v3 and Deepsort techniques
- Automatic Colon Polyp Detection using Region based Deep CNN and Post Learning Approaches
- Adversarial Examples that Fool Detectors
- PixelNet: Representation of the pixels, by the pixels, and for the pixels
- MAttNet: Modular Attention Network for Referring Expression Comprehension
- Robust Adversarial Perturbation on Deep Proposal-based Models
- Face Detection Using Improved Faster RCNN
- RMPE: Regional Multi-person Pose Estimation
- Bounding Box Regression with Uncertainty for Accurate Object Detection
- Lifelong Object Detection
- ChainerCV: a Library for Deep Learning in Computer Vision
- Interact as You Intend: Intention-Driven Human-Object Interaction Detection
- Deep Mangoes: from fruit detection to cultivar identification in colour images of mango trees
- Fast Vehicle Detection in Aerial Imagery
- OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge
- OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation
- Video Object Segmentation using Tracked Object Proposals
- Intention Recognition of Pedestrians and Cyclists by 2D Pose Estimation
- Spatial Memory for Context Reasoning in Object Detection
- Slot Based Image Augmentation System for Object Detection
- Visual Diver Recognition for Underwater Human-Robot Collaboration
- Characters Detection on Namecard with faster RCNN
- Learning Instance-Aware Object Detection Using Determinantal Point Processes
- Image Captioning with Integrated Bottom-Up and Multi-level Residual Top-Down Attention for Game Scene Understanding
- Efficient Pipelines for Vision-Based Context Sensing
- Analysing object detectors from the perspective of co-occurring object categories
- CPARR: Category-based Proposal Analysis for Referring Relationships