paper-with-me

Papers

Large Batch Optimization for Object Detection: Training COCO in 12 Minutes

2020-08-01 · ECCV 2020 8 · Tong Wang, Yousong Zhu, Chaoyang Zhao, Wei Zeng, Yao-Wei Wang, Jinqiao Wang, Ming Tang

Most of existing object detectors usually adopt a small training batch size ( ~16), which severely hinders the whole community from exploring large-scale datasets due to the extremely long training procedure. In this paper, we propose a versatile large batch optimization framework for object detection, named LargeDet, which successfully scales the batch size to larger than 1K for the first time. Specifically, we present a novel Periodical Moments Decay LAMB (PMD-LAMB) algorithm to effectively reduce the negative effects of the lagging historical gradients. Additionally, the Synchronized Batch Normalization (SyncBN) is utilized to help fast convergence. With LargeDet, we can not only prominently shorten the training period, but also significantly improve the detection accuracy of sparsely annotated large-scale datasets. For instance, we can finish the training of ResNet50 FPN detector on COCO within 12 minutes. Moreover, we achieve 12.2% mAP@0.5 absolute improvement for ResNet50 FPN on Open Images by training with batch size 640.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

object-detectionObject Detection

Similar Papers 제목 키워드 기반

Large-batch Optimization for Dense Visual Predictions

2022-10-20 · Zeyue Xue, Jianming Liang, Guanglu Song, Zhuofan Zong 외

Training a large-scale deep neural network in a large-scale dataset is challenging and time-consuming. The recent breakthrough of large-batch optimization is a promising way to tackle this challenge. However, although th…

Instance Segmentationobject-detectionObject DetectionPanoptic Segmentation+2

MegDet: A Large Mini-Batch Object Detector

2017-11-20 · CVPR 2018 6 · Chao Peng, Tete Xiao, Zeming Li, Yuning Jiang 외

The improvements in recent CNN-based object detection works, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from new network, new framework, or novel loss design. Bu…

GPUObjectobject-detectionObject Detection

Stochastic Nonconvex Optimization with Large Minibatches

2017-09-25 · Weiran Wang, Nathan Srebro

We study stochastic optimization of nonconvex loss functions, which are typical objectives for training neural networks. We propose stochastic approximation algorithms which optimize a series of regularized, nonlinearize…

Stochastic Optimization

A Batched Scalable Multi-Objective Bayesian Optimization Algorithm

2018-11-04 · Xi Lin, Hui-Ling Zhen, Zhenhua Li, Qingfu Zhang 외

The surrogate-assisted optimization algorithm is a promising approach for solving expensive multi-objective optimization problems. However, most existing surrogate-assisted multi-objective optimization algorithms have th…

Bayesian Optimization

Domain Adaptation in 3D Object Detection with Gradual Batch Alternation Training

2022-10-18 · Mrigank Rochan, Xingxin Chen, Alaap Grandhi, Eduardo R. Corral-Soto 외

We consider the problem of domain adaptation in LiDAR-based 3D object detection. Towards this, we propose a simple yet effective training strategy called Gradual Batch Alternation that can adapt from a large labeled sour…

3D Object DetectionAutonomous DrivingDomain AdaptationObject+2