Timezone: »
We introduce MixTraining, a new training paradigm for object detection that can improve the performance of existing detectors for free. MixTraining enhances data augmentation by utilizing augmentations of different strengths while excluding the strong augmentations of certain training samples that may be detrimental to training. In addition, it addresses localization noise and missing labels in human annotations by incorporating pseudo boxes that can compensate for these errors. Both of these MixTraining capabilities are made possible through bootstrapping on the detector, which can be used to predict the difficulty of training on a strong augmentation, as well as to generate reliable pseudo boxes thanks to the robustness of neural networks to labeling error. MixTraining is found to bring consistent improvements across various detectors on the COCO dataset. In particular, the performance of Faster R-CNN~\cite{ren2015faster} with a ResNet-50~\cite{he2016deep} backbone is improved from 41.7 mAP to 44.0 mAP, and the accuracy of Cascade-RCNN~\cite{cai2018cascade} with a Swin-Small~\cite{liu2021swin} backbone is raised from 50.9 mAP to 52.8 mAP.
Author Information
Mengde Xu (Huazhong University of Science and Technology)
Zheng Zhang (MSRA)
Fangyun Wei (Microsoft Research Asia)
Yutong Lin (Xi'an Jiaotong University)
Yue Cao (Microsoft Research)
Stephen Lin (Microsoft Research)
Han Hu (Microsoft Research Asia)
Xiang Bai (Huazhong University of Science and Technology)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 Poster: Bootstrap Your Object Detector via Mixed Training »
Tue Dec 7th 04:30 -- 06:00 PM Room None
More from the Same Authors
-
2020 : Paper 62: Instance-wise Depth and Motion Learning from Monocular Videos »
Seokju Lee · Sunghoon Im · Stephen Lin · In So Kweon -
2021 Spotlight: Aligning Pretraining for Detection via Object-Level Contrastive Learning »
Fangyun Wei · Yue Gao · Zhirong Wu · Han Hu · Stephen Lin -
2021 Spotlight: Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning »
Hanzhe Hu · Fangyun Wei · Han Hu · Qiwei Ye · Jinshi Cui · Liwei Wang -
2021 : Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge »
Jiyang Qi · Yan Gao · Yao Hu · Xinggang Wang · Xiaoyu Liu · Xiang Bai · Serge Belongie · Alan Yuille · Philip Torr · Song Bai -
2021 Poster: The Emergence of Objectness: Learning Zero-shot Segmentation from Videos »
Runtao Liu · Zhirong Wu · Stella Yu · Stephen Lin -
2021 Poster: Aligning Pretraining for Detection via Object-Level Contrastive Learning »
Fangyun Wei · Yue Gao · Zhirong Wu · Han Hu · Stephen Lin -
2021 Poster: Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning »
Hanzhe Hu · Fangyun Wei · Han Hu · Qiwei Ye · Jinshi Cui · Liwei Wang -
2020 Poster: RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder »
Cheng Chi · Fangyun Wei · Han Hu -
2020 Spotlight: RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder »
Cheng Chi · Fangyun Wei · Han Hu -
2020 Poster: RepPoints v2: Verification Meets Regression for Object Detection »
Yihong Chen · Zheng Zhang · Yue Cao · Liwei Wang · Stephen Lin · Han Hu -
2020 Poster: Parametric Instance Classification for Unsupervised Visual Feature learning »
Yue Cao · Zhenda Xie · Bin Liu · Yutong Lin · Zheng Zhang · Han Hu -
2020 Poster: Restoring Negative Information in Few-Shot Object Detection »
Yukuan Yang · Fangyun Wei · Miaojing Shi · Guoqi Li -
2018 Poster: Recurrent Transformer Networks for Semantic Correspondence »
Seungryong Kim · Stephen Lin · Sangryul Jeon · Dongbo Min · Kwanghoon Sohn -
2018 Spotlight: Recurrent Transformer Networks for Semantic Correspondence »
Seungryong Kim · Stephen Lin · Sangryul Jeon · Dongbo Min · Kwanghoon Sohn -
2012 Poster: Fusion with Diffusion for Robust Visual Tracking »
Yu Zhou · Xiang Bai · Wenyu Liu · Longin Jan J Latecki -
2011 Poster: Maximal Cliques that Satisfy Hard Constraints with Application to Deformable Object Model Learning »
Xinggang Wang · Xiang Bai · Xingwei Yang · Wenyu Liu · Longin Jan J Latecki -
2008 Poster: Multiscale Random Fields with Application to Contour Grouping »
Longin Jan J Latecki · ChengEn Lu · Marc J Sobel · Xiang Bai