Use the Detection Transformer as a Data Augmenter
Not on the map. Why?
Abstract (arXiv)
Detection Transformer (DETR) is a Transformer architecture based object detection model. In this paper, we demonstrate that it can also be used as a data augmenter. We term our approach as DETR assisted CutMix, or DeMix for short. DeMix builds on CutMix, a simple yet highly effective data augmentation technique that has gained popularity in recent years. CutMix improves model performance by cutting and pasting a patch from one image onto another, yielding a new image. The corresponding label for this new example is specified as the weighted average of the original labels, where the weight is proportional to the area of the patch. CutMix selects a random patch to be cut. In contrast, DeMix elaborately selects a semantically rich patch, located by a pre-trained DETR. The label of the new image is specified in the same way as in CutMix. Experimental results on benchmark datasets for image classification demonstrate that DeMix significantly outperforms prior art data augmentation methods including CutMix. Oue code is available at https://github.com/ZJLAB-AMMI/DeMix.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 49 references that are in the map. First posted on arXiv 10 Apr 2023.
Builds on
31 of 49 references.
References · 31
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2020End-to-End Object Detection with Transformerscited by 7,384
- 2016Densely Connected Convolutional Networkscited by 6,691
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
- 2020Shortcut Learning in Deep Neural Networkscited by 1,928
- 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
- 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
- 2017Random Erasing Data Augmentationcited by 1,235
- 2018Image Transformercited by 770
19 more
- 2020A Survey on Visual Transformercited by 653
- 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
- 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
- 2017Universal Style Transfer via Feature Transformscited by 352
- 2017Deep Photo Style Transfercited by 168
- 2020SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularizationcited by 149
- 2019Learning Data Augmentation Strategies for Object Detectioncited by 139
- 2019Data augmentation using learned transformations for one-shot medical image segmentationcited by 138
- 2020Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustnesscited by 121
- 2020SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Datacited by 56
- 2020KeepAugment: A Simple Information-Preserving Data Augmentation Approachcited by 52
- 2018Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimationcited by 44
- 2021HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalizationcited by 31
- 2021Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencodercited by 27
- 2020Semi-supervised Task-driven Data Augmentation for Medical Image Segmentationcited by 24
- 2021Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifierscited by 24
- 2020Automatic Data Augmentation for 3D Medical Image Segmentationcited by 22
- 2018DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classificationcited by 18
- 2021Consistent Relative Confidence and Label-Free Model Selection for Convolutional Neural Networkscited by 1
Built on by
Not cited yet.