Published on Mon Apr 19 2021

A Competitive Method to VIPriors Object Detection Challenge

Fei Shen, Xin He, Mengwan Wei, Yi Xie
0
0
0
Abstract

In this report, we introduce the technical details of our submission to the VIPriors object detection challenge. Our solution is based on mmdetction of a strong baseline open-source detection toolbox. Firstly, we introduce an effective data augmentation method to address the lack of data problem, which contains bbox-jitter, grid-mask, and mix-up. Secondly, we present a robust region of interest (ROI) extraction method to learn more significant ROI features via embedding global context features. Thirdly, we propose a multi-model integration strategy to refinement the prediction box, which weighted boxes fusion (WBF). Experimental results demonstrate that our approach can significantly improve the average precision (AP) of object detection on the subset of the COCO2017 dataset.

Thu Jul 16 2020
Computer Vision
VIPriors Object Detection Challenge
0
0
0
Mon Sep 22 2014
Computer Vision
1-HKUST: Object Detection in ILSVRC 2014
The Imagenet Large Scale Visual Recognition Challenge (ILSVRC) is one of the most important big data challenges to date. We participated in the object detection track of ILSVRC 2014 and received the fourth place among the 38teams.
0
0
0
Tue Dec 08 2015
Computer Vision
SSD: Single Shot MultiBox Detector
We present a method for detecting objects in images using a single deep neurological network. Our approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios. At prediction time, the network generates scores for the presence of each object category in each default box.
1
0
1
Mon Aug 31 2020
Computer Vision
VarifocalNet: An IoU-aware Dense Object Detector
Dense object detectors can achieve a more accurate ranking of candidates based on the IACS. VFNet consistently surpasses the strong baseline by $2.0 AP with different backbones. Our best model VF net achieves a single-model single-scale AP of 55.1.
0
0
0
Mon Jun 17 2019
Machine Learning
MMDetection: Open MMLab Detection Toolbox and Benchmark
MMDetection contains a rich set of object detection and instance segmentation methods. It includes training and inference codes, but also provides provides weights for more than 200 network models.
0
0
0
Fri Nov 16 2018
Computer Vision
DeRPN: Taking a further step toward more general object detection
Most current detection methods have adopted anchor boxes as regression tests. A proper setting of anchor boxes may vary significantly across different datasets. To improve the adaptivity of the detectors, in this paper, we present a novel dimension-decomposition region proposal network (DeRPN)
0
0
0