Use the Detection Transformer as a Data Augmenter

Luping Wang, Bin Liu
4/10/2023
cs.CV

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Learning Data Augmentation Strategies for Object Detection

89% match1 repo5.3k2019

Robust and Accurate Object Detection via Adversarial Learning

87% match1 repo6.5k2021

Contrastive Learning for Multi-Object Tracking with Transformers

84% match1 repo92023

YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary

83% match1 repo72024

Select-Mosaic: Data Augmentation Method for Dense Small Object Scenes

83% match2024

A Simple Semi-Supervised Learning Framework for Object Detection

82% match1 repo4122020

Cite this paper

@article{wang2023detection,
  title  = {Use the Detection Transformer as a Data Augmenter},
  author = {Luping Wang and Bin Liu},
  year   = {2023},
  eprint = {2304.04554},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2304.04554v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2304.04554.svg)](https://codeofpaper.com/paper/2304.04554)

Discussion