• Home
  • Search
  • Image-Level Automatic Data Augmentation for Pedestrian Detection
  • Cite Icon4
  • https://doi.org/10.1109/tim.2023.3336760Copy DOI Icon

Image-Level Automatic Data Augmentation for Pedestrian Detection

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Data augmentation (DA) is a commonly used method to alleviate the problem of detecting occluded pedestrians in crowded scenes. Recently, several dataset-level automatic DA methods have been proposed to search for a set of general DA policies for the entire dataset, which saves a lot of time compared to manually designing DA policies. However, due to the huge differences between each image in pedestrian detection datasets, existing dataset-level augmentation methods cannot automatically adjust DA policies according to the differences between them, which will lead to outlier data and degradation of model performance. Therefore, considering the differences between each image, we propose an image-level automatic DA method that aims to find an optimal DA policy for each image in the dataset according to their respective characteristics. Specifically, we first reformulate the image-level automatic DA method by constructing a search space based on categorical distribution, within which we specify the probability of operations being sampled according to their respective effectiveness so that useful operations can be effectively preserved and useless operations can be suppressed. Subsequently, we design an encoding method to recode the index of images and policies and use the encoded index to closely associate them to achieve a stable matching relationship between images and policies. Finally, a search framework with Bayesian optimization is developed for efficient policy mining. Comprehensive experiments on CrowdHuman and CityPersons datasets show that compared with the commonly used automatic DA method for pedestrian detection, AutoPedestrian, our method takes only 1/14 of the search time, but achieves better detection accuracy. Specifically, we achieve 10.2% MR−2 on the CityPersons reasonable subset and 36.8% MR−2 on the CrowdHuman dataset, outperforming state-of-the-art methods on the CrowdHuman dataset.

Similar Papers
  • PDF
  • Research Article
  • Citations22

Data Augmentation for Building Footprint Segmentation in SAR Images: An Empirical Study

  • Apr 22, 2022
  • Remote Sensing
  • Sandhi Wangiyana +2
  • PDF
  • Conference Article
  • Citations31

Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization

  • Jan 01, 2019
  • Guanlin Li +4
  • Conference Article

A General Multiple Data Augmentation Based Framework for Training Deep Neural Networks

  • Jul 18, 2022
  • Binyan Hu +2
  • Research Article
  • Citations13

Improving classification performance of motor imagery BCI through EEG data augmentation with conditional generative adversarial networks

  • Aug 28, 2024
  • Neural Networks
  • Sanghyun Choo +4
  • Research Article
  • Citations11

A comprehensive survey and comparative analysis of time series data augmentation in medical wearable computing.

  • Mar 18, 2025
  • PloS one
  • Md Abid Hasan +4
  • Conference Article
  • Citations32

Optimizing Data Augmentation for Semantic Segmentation on Small-Scale Dataset

  • Jun 15, 2019
  • Rui Ma +2
  • Research Article
  • Citations99

Data augmentation techniques in natural language processing

  • Nov 19, 2022
  • Applied Soft Computing
  • Lucas Francisco Amaral Orosco Pellicer +2
  • Research Article
  • Citations477

A review of ensemble learning and data augmentation models for class imbalanced problems: Combination, implementation and evaluation

  • Dec 10, 2023
  • Expert Systems with Applications
  • Azal Ahmad Khan +2
  • Research Article
  • Citations66

EEG data augmentation: towards class imbalance problem in sleep staging tasks

  • Oct 01, 2020
  • Journal of Neural Engineering
  • Jiahao Fan +8
  • Research Article
  • Citations15

Identifying stable EEG patterns over time for mental workload recognition using transfer DS-CNN framework

  • Nov 15, 2023
  • Biomedical Signal Processing and Control
  • Lin Jin +4
  • Dissertation
  • Citations1

Data Augmentation methods in natural language processing.

  • Jul 20, 2021
  • Taynan Maier Ferreira
  • Research Article

Evaluating Augmentation Approaches for Deep Learning-based Major Depressive Disorder Diagnosis with Raw Electroencephalogram Data.

  • Jul 15, 2024
  • Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
  • Charles A Ellis +2
  • Research Article
  • Citations39

A comparison of data augmentation methods in voice pathology detection

  • Aug 11, 2023
  • Computer Speech & Language
  • Farhad Javanmardi +2
  • Research Article
  • Citations40

Data augmentation for a Bayesian spatial model involving censored observations

  • Sep 19, 2006
  • Environmetrics
  • Brooke L Fridley +1
  • Research Article
  • Citations70

A review of synthetic and augmented training data for machine learning in ultrasonic non-destructive evaluation

  • May 18, 2023
  • Ultrasonics
  • Sebastian Uhlig +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.