Bootstrap Your Object Detector via Mixed Training
- URL: http://arxiv.org/abs/2111.03056v1
- Date: Thu, 4 Nov 2021 17:58:26 GMT
- Title: Bootstrap Your Object Detector via Mixed Training
- Authors: Mengde Xu, Zheng Zhang, Fangyun Wei, Yutong Lin, Yue Cao, Stephen Lin,
Han Hu, Xiang Bai
- Abstract summary: MixTraining is a new training paradigm for object detection that can improve the performance of existing detectors for free.
It enhances data augmentation by utilizing augmentations of different strengths while excluding the strong augmentations of certain training samples that may be detrimental to training.
MixTraining is found to bring consistent improvements across various detectors on the COCO dataset.
- Score: 82.98619147880397
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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}.
Related papers
- KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training [2.8804804517897935]
We propose a method for hiding the least-important samples during the training of deep neural networks.
We adaptively find samples to exclude in a given epoch based on their contribution to the overall learning process.
Our method can reduce total training time by up to 22% impacting accuracy only by 0.4% compared to the baseline.
arXiv Detail & Related papers (2023-10-16T06:19:29Z) - DE-CROP: Data-efficient Certified Robustness for Pretrained Classifiers [21.741026088202126]
We propose a novel way to certify the robustness of pretrained models using only a few training samples.
Our proposed approach generates class-boundary and interpolated samples corresponding to each training sample.
We obtain significant improvements over the baseline on multiple benchmark datasets and also report similar performance under the challenging black box setup.
arXiv Detail & Related papers (2022-10-17T10:41:18Z) - Learning from Data with Noisy Labels Using Temporal Self-Ensemble [11.245833546360386]
Deep neural networks (DNNs) have an enormous capacity to memorize noisy labels.
Current state-of-the-art methods present a co-training scheme that trains dual networks using samples associated with small losses.
We propose a simple yet effective robust training scheme that operates by training only a single network.
arXiv Detail & Related papers (2022-07-21T08:16:31Z) - Training Your Sparse Neural Network Better with Any Mask [106.134361318518]
Pruning large neural networks to create high-quality, independently trainable sparse masks is desirable.
In this paper we demonstrate an alternative opportunity: one can customize the sparse training techniques to deviate from the default dense network training protocols.
Our new sparse training recipe is generally applicable to improving training from scratch with various sparse masks.
arXiv Detail & Related papers (2022-06-26T00:37:33Z) - Distributed Adversarial Training to Robustify Deep Neural Networks at
Scale [100.19539096465101]
Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification.
To defend against such attacks, an effective approach, known as adversarial training (AT), has been shown to mitigate robust training.
We propose a large-batch adversarial training framework implemented over multiple machines.
arXiv Detail & Related papers (2022-06-13T15:39:43Z) - RecursiveMix: Mixed Learning with History [21.865332756486314]
"RecursiveMix" (RM) is a mixed-sample learning paradigm that leverages the historical input-prediction-label triplets.
Based on ResNet-50, RM largely improves classification accuracy by $sim$3.2% on CIFAR100 and $sim$2.8% on ImageNet with negligible extra computation/storage costs.
arXiv Detail & Related papers (2022-03-14T03:59:47Z) - BatchFormer: Learning to Explore Sample Relationships for Robust
Representation Learning [93.38239238988719]
We propose to enable deep neural networks with the ability to learn the sample relationships from each mini-batch.
BatchFormer is applied into the batch dimension of each mini-batch to implicitly explore sample relationships during training.
We perform extensive experiments on over ten datasets and the proposed method achieves significant improvements on different data scarcity applications.
arXiv Detail & Related papers (2022-03-03T05:31:33Z) - End-to-End Semi-Supervised Object Detection with Soft Teacher [63.26266730447914]
This paper presents an end-to-end semi-supervised object detection approach, in contrast to previous more complex multi-stage methods.
The proposed approach outperforms previous methods by a large margin under various labeling ratios.
On the state-of-the-art Swin Transformer-based object detector, it can still significantly improve the detection accuracy by +1.5 mAP.
arXiv Detail & Related papers (2021-06-16T17:59:30Z) - PatchUp: A Regularization Technique for Convolutional Neural Networks [19.59198017238128]
We propose PatchUp, a hidden state block-level regularization technique for Convolutional Neural Networks (CNNs)
Our approach improves the robustness of CNN models against the manifold intrusion problem that may occur in other state-of-the-art mixing approaches like Mixup and CutMix.
We also show that PatchUp can provide better generalization to affine transformations of samples and is more robust against adversarial attacks.
arXiv Detail & Related papers (2020-06-14T04:28:11Z) - Dynamic R-CNN: Towards High Quality Object Detection via Dynamic
Training [70.2914594796002]
We propose Dynamic R-CNN to adjust the label assignment criteria and the shape of regression loss function.
Our method improves upon ResNet-50-FPN baseline with 1.9% AP and 5.5% AP$_90$ on the MS dataset with no extra overhead.
arXiv Detail & Related papers (2020-04-13T15:20:25Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.