paper-with-me

Papers

2nd Place Solution to ECCV 2020 VIPriors Object Detection Challenge

2020-07-17 · Yinzheng Gu, Yihan Pan, Shi-Zhe Chen

In this report, we descibe our approach to the ECCV 2020 VIPriors Object Detection Challenge which took place from March to July in 2020. We show that by using state-of-the-art data augmentation strategies, model designs, and post-processing ensemble methods, it is possible to overcome the difficulty of data shortage and obtain competitive results. Notably, our overall detection system achieves 36.6$\%$ AP on the COCO 2017 validation set using only 10K training images without any pre-training or transfer learning weights ranking us 2nd place in the challenge.

📄 PDF Abstract BibTeX arXiv:2007.08849

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentationobject-detectionObject DetectionTransfer Learning

Similar Papers 제목 키워드 기반

2nd Place Scheme on Action Recognition Track of ECCV 2020 VIPriors Challenges: An Efficient Optical Flow Stream Guided Framework

2020-08-10 · Haoyu Chen, Zitong Yu, Xin Liu, Wei Peng 외

To address the problem of training on small datasets for action recognition tasks, most prior works are either based on a large number of training samples or require pre-trained models transferred from other large datase…

Action RecognitionOptical Flow Estimation

EfficientSeg: An Efficient Semantic Segmentation Network

2020-09-14 · Vahit Bugra Yesilkaynak, Yusuf H. Sahin, Gozde Unal

Deep neural network training without pre-trained weights and few data is shown to need more training iterations. It is also known that, deeper models are more successful than their shallow counterparts for semantic segme…

SegmentationSemantic Segmentation

1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking

2021-01-20 · Fei Du, Bo Xu, Jiasheng Tang, Yuqi Zhang 외

We extend the classical tracking-by-detection paradigm to this tracking-any-object task. Solid detection results are first extracted from TAO dataset. Some state-of-the-art techniques like \textbf{BA}lanced-\textbf{G}rou…

Multi-Object TrackingObject

The 1st-place Solution for ECCV 2022 Multiple People Tracking in Group Dance Challenge

2022-10-27 · Yuang Zhang, Tiancai Wang, Weiyao Lin, Xiangyu Zhang

We present our 1st place solution to the Group Dance Multiple People Tracking Challenge. Based on MOTR: End-to-End Multiple-Object Tracking with Transformer, we explore: 1) detect queries as anchors, 2) tracking as query…

Multi-Object TrackingMultiple Object TrackingMultiple Object Tracking with TransformerMultiple People Tracking

A Competitive Method to VIPriors Object Detection Challenge

2021-04-19 · Fei Shen, Xin He, Mengwan Wei, Yi Xie

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 introdu…

Data AugmentationObjectobject-detectionObject Detection