Bootstrap Your Object Detector via Mixed Training

2021-11-04 · NeurIPS 2021 12 · Mengde Xu, Zheng Zhang, Fangyun Wei, Yutong Lin, Yue Cao, Stephen Lin, Han Hu, Xiang Bai

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. The code and models will be made publicly available at \url{https://github.com/MendelXu/MixTraining}.

📄 PDF Abstract BibTeX arXiv:2111.03056

Code (1)

mendelxu/mixtraining 공식 구현 pytorch

Tasks

Data AugmentationMissing LabelsObjectobject-detection Object Detection

Methods 이 논문이 사용한 방법론

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

RoIPool 설명 없음

Faster R-CNN Faster R-CNN is an object detection model that improves on Fast R-CNN by utilising a region proposal network…

SWA Object Detection

2020-12-23 · Haoyang Zhang, Ying Wang, Feras Dayoub, Niko Sünderhauf

Do you want to improve 1.0 AP for your object detector without any inference cost and any change to your detector? Let us tell you such a recipe. It is surprisingly simple: train your detector for an extra 12 epochs usin…

Instance Segmentation Object object-detection Object Detection+1

You Are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-tailed Data

2025-03-10 · Shanshan Yan, Zexi Li, Chao Wu, Meng Pang 외

Data heterogeneity, stemming from local non-IID data and global long-tailed distributions, is a major challenge in federated learning (FL), leading to significant performance gaps compared to centralized learning. Previo…

Federated Learning Representation Learning

Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images

2019-12-01 · arXiv 2019 12 · Zhaohui Yang, Miaojing Shi, Chao Xu, Vittorio Ferrari 외

Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set. In this work, we study the proble…

object-detection Object Detection Weakly Supervised Object Detection

Bootstrap Your Flow

2021-11-22 · pproximateinference AABI Symposium 2022 2 · Laurence Illing Midgley, Vincent Stimper, Gregor N. C. Simm, José Miguel Hernández-Lobato

Normalizing flows are flexible, parameterized distributions that can be used to approximate expectations from intractable distributions via importance sampling. However, current flow-based approaches are limited on chall…

Normalising Flows

Bootstrap Your Own Variance

2023-12-06 · Polina Turishcheva, Jason Ramapuram, Sinead Williamson, Dan Busbridge 외

Understanding model uncertainty is important for many applications. We propose Bootstrap Your Own Variance (BYOV), combining Bootstrap Your Own Latent (BYOL), a negative-free Self-Supervised Learning (SSL) algorithm, wit…

Self-Supervised Learning