If you use this dataset, please cite this paper: Puertas, E.; De-Las-Heras, G.; Sánchez-Soriano, J.; Fernández-Andrés, J. Dataset: Variable Message Signal Annotated Images for Object Detection. Data 2022, 7, 41. https://doi.org/10.3390/data7040041

This dataset consists of Spanish road images taken from inside a vehicle, as well as annotations in XML files in PASCAL VOC format that indicate the location of Variable Message Signals within them. Also, a CSV file is attached with information regarding the geographic position, the folder where the image is located, and the text in Spanish. This can be used to train supervised learning computer vision algorithms, such as convolutional neural networks. Throughout this work, the process followed to obtain the dataset, image acquisition, and labeling, and its specifications are detailed. The dataset is constituted of 1216 instances, 888 positives, and 328 negatives, in 1152 jpg images with a resolution of 1280x720 pixels. These are divided into 576 real images and 576 images created from the data-augmentation technique. The purpose of this dataset is to help in road computer vision research since there is not one specifically for VMSs.

The folder structure of the dataset is as follows:

• vms_dataset/
  • data.csv
  • real_images/
    • imgs/
    • annotations/
  • data-augmentation/
    • imgs/
    • annotations/

In which:

• data.csv: Each row contains the following information separated by commas (,): image_name, x_min, y_min, x_max, y_max, class_name, lat, long, folder, text.
• real_images: Images extracted directly from the videos.
• data-augmentation: Images created using data-augmentation
• imgs: Image files in .jpg format.
• annotations: Annotation files in .xml format.

Comparative results for magnitude domain transformation-based data augmentation methods.

The goal of this work is to generate large statistically representative datasets to train machine learning models for disruption prediction provided by data from few existing discharges. Such a comprehensive training database is important to achieve satisfying and reliable prediction results in artificial neural network classifiers. Here, we aim for a robust augmentation of the training database for multivariate time series data using Student-t process regression. We apply Student-t process regression in a state space formulation via Bayesian filtering to tackle challenges imposed by outliers and noise in the training data set and to reduce the computational complexity. Thus, the method can also be used if the time resolution is high. We use an uncorrelated model for each dimension and impose correlations afterwards via coloring transformations. We demonstrate the efficacy of our approach on plasma diagnostics data of three different disruption classes from the DIII-D tokamak. To evaluate if the distribution of the generated data is similar to the training data, we additionally perform statistical analyses using methods from time series analysis, descriptive statistics, and classic machine learning clustering algorithms.

Object detection in challenging environments, such as low-light, cluttered, or dynamic conditions, remains a critical issue in computer vision. Deep Convolutional Neural Networks (DCNNs) have emerged as powerful tools for addressing these challenges due to their ability to learn hierarchical feature representations. This paper explores the optimization of object detection in such environments by leveraging advanced DCNN architectures, data augmentation techniques, and domain-specific pre-training. We propose an enhanced detection framework that integrates multi-scale feature extraction, transfer learning, and regularization methods to improve robustness against noise, occlusion, and lighting variations. Experimental results demonstrate significant improvements in detection accuracy across various challenging datasets, outperforming traditional methods. This study highlights the potential of DCNNs in real-world applications, such as autonomous driving, surveillance, and robotics, where object detection in difficult conditions is crucial.

This repository contains the data and associated results of all experiments conducted in our work "Phenotype Driven Data Augmentation Methods for Transcriptomic Data". In this work, we introduce two classes of phenotype driven data augmentation approaches – signature-dependent and signature-independent. The signature-dependent methods assume the existence of distinct gene signatures describing some phenotype and are simple, non-parametric, and novel data augmentation methods. The signature-independent methods are a modification of the established Gamma-Poisson and Poisson sampling methods for gene expression data. We benchmark our proposed methods against random oversampling, SMOTE, unmodified versions of Gamma-Poisson and Poisson sampling, and unaugmented data.

This repository contains data used for all our experiments. This includes the original data based off which augmentation was performed, the cross validation split indices as a json file, the training and validation data augmented by the various augmentation methods mentioned in our study, a test set (containing only real samples) and an external test set standardised accordingly with respect to each augmentation method and training data per CV split.

The compressed files 5x5stratified_{x}percent.zip contains data that were augmented on x% of the available real data. brca_public.zip contains data used for the breast cancer experiments. distribution_size_effect.zip contains data used for hyperparameter tuning the reference set size for the modified Poisson and Gamma-Poisson methods.

The compressed file results.zip contains all the results from all the experiments. This includes the parameter files used to train the various models, the metrics (balanced accuracy and auc-roc) computed including p-values, as well as the latent space of train, validation and test (for the (N)VAE) for all 25 (5x5) CV splits.

PLEASE NOTE: If any part of this repository is used in any form for your work, please attribute the following, in addition to attributing the original data source - TCGA, CPTAC, GSE20713 and METABRIC, accordingly:

@article{janakarajan2025phenotype,
 title={Phenotype driven data augmentation methods for transcriptomic data},
 author={Janakarajan, Nikita and Graziani, Mara and Rodr{\'\i}guez Mart{\'\i}nez, Mar{\'\i}a},
 journal={Bioinformatics Advances},
 volume={5},
 number={1},
 pages={vbaf124},
 year={2025},
 publisher={Oxford University Press}
}

Comparative results for time domain transformation-based data augmentation methods.

Machine learning‐based behaviour classification using acceleration data is a powerful tool in bio‐logging research. Deep learning architectures such as convolutional neural networks (CNN), long short‐term memory (LSTM) and self‐attention mechanisms as well as related training techniques have been extensively studied in human activity recognition. However, they have rarely been used in wild animal studies. The main challenges of acceleration‐based wild animal behaviour classification include data shortages, class imbalance problems, various types of noise in data due to differences in individual behaviour and where the loggers were attached and complexity in data due to complex animal‐specific behaviours, which may have limited the application of deep learning techniques in this area. To overcome these challenges, we explored the effectiveness of techniques for efficient model training: data augmentation, manifold mixup and pre‐training of deep learning models with unlabelled data, using datasets from two species of wild seabirds and state‐of‐the‐art deep learning model architectures. Data augmentation improved the overall model performance when one of the various techniques (none, scaling, jittering, permutation, time‐warping and rotation) was randomly applied to each data during mini‐batch training. Manifold mixup also improved model performance, but not as much as random data augmentation. Pre‐training with unlabelled data did not improve model performance. The state‐of‐the‐art deep learning models, including a model consisting of four CNN layers, an LSTM layer and a multi‐head attention layer, as well as its modified version with shortcut connection, showed better performance among other comparative models. Using only raw acceleration data as inputs, these models outperformed classic machine learning approaches that used 119 handcrafted features. Our experiments showed that deep learning techniques are promising for acceleration‐based behaviour classification of wild animals and highlighted some challenges (e.g. effective use of unlabelled data). There is scope for greater exploration of deep learning techniques in wild animal studies (e.g. advanced data augmentation, multimodal sensor data use, transfer learning and self‐supervised learning). We hope that this study will stimulate the development of deep learning techniques for wild animal behaviour classification using time‐series sensor data.

This abstract is cited from the original article "Exploring deep learning techniques for wild animal behaviour classification using animal-borne accelerometers" in Methods in Ecology and Evolution (Otsuka et al., 2024).Please see README for the details of the datasets.

This repository contains the Wallhack1.8k dataset for WiFi-based long-range activity recognition in Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS)/Through-Wall scenarios, as proposed in [1,2], as well as the CAD models (of 3D-printable parts) of the WiFi systems proposed in [2].

PyTroch Dataloader

A minimal PyTorch dataloader for the Wallhack1.8k dataset is provided at: https://github.com/StrohmayerJ/wallhack1.8k

Dataset Description

The Wallhack1.8k dataset comprises 1,806 CSI amplitude spectrograms (and raw WiFi packet time series) corresponding to three activity classes: "no presence," "walking," and "walking + arm-waving." WiFi packets were transmitted at a frequency of 100 Hz, and each spectrogram captures a temporal context of approximately 4 seconds (400 WiFi packets).

To assess cross-scenario and cross-system generalization, WiFi packet sequences were collected in LoS and through-wall (NLoS) scenarios, utilizing two different WiFi systems (BQ: biquad antenna and PIFA: printed inverted-F antenna). The dataset is structured accordingly:

LOS/BQ/ <- WiFi packets collected in the LoS scenario using the BQ system

LOS/PIFA/ <- WiFi packets collected in the LoS scenario using the PIFA system

NLOS/BQ/ <- WiFi packets collected in the NLoS scenario using the BQ system

NLOS/PIFA/ <- WiFi packets collected in the NLoS scenario using the PIFA system

These directories contain the raw WiFi packet time series (see Table 1). Each row represents a single WiFi packet with the complex CSI vector H being stored in the "data" field and the class label being stored in the "class" field. H is of the form [I, R, I, R, ..., I, R], where two consecutive entries represent imaginary and real parts of complex numbers (the Channel Frequency Responses of subcarriers). Taking the absolute value of H (e.g., via numpy.abs(H)) yields the subcarrier amplitudes A.

To extract the 52 L-LTF subcarriers used in [1], the following indices of A are to be selected:

52 L-LTF subcarriers

csi_valid_subcarrier_index = [] csi_valid_subcarrier_index += [i for i in range(6, 32)] csi_valid_subcarrier_index += [i for i in range(33, 59)]

Additional 56 HT-LTF subcarriers can be selected via:

56 HT-LTF subcarriers

csi_valid_subcarrier_index += [i for i in range(66, 94)]
csi_valid_subcarrier_index += [i for i in range(95, 123)]

For more details on subcarrier selection, see ESP-IDF (Section Wi-Fi Channel State Information) and esp-csi.

Extracted amplitude spectrograms with the corresponding label files of the train/validation/test split: "trainLabels.csv," "validationLabels.csv," and "testLabels.csv," can be found in the spectrograms/ directory.

The columns in the label files correspond to the following: [Spectrogram index, Class label, Room label]

Spectrogram index: [0, ..., n]

Class label: [0,1,2], where 0 = "no presence", 1 = "walking", and 2 = "walking + arm-waving."

Room label: [0,1,2,3,4,5], where labels 1-5 correspond to the room number in the NLoS scenario (see Fig. 3 in [1]). The label 0 corresponds to no room and is used for the "no presence" class.

Dataset Overview:

Table 1: Raw WiFi packet sequences.

Scenario System "no presence" / label 0 "walking" / label 1 "walking + arm-waving" / label 2 Total

LoS BQ b1.csv w1.csv, w2.csv, w3.csv, w4.csv and w5.csv ww1.csv, ww2.csv, ww3.csv, ww4.csv and ww5.csv

LoS PIFA b1.csv w1.csv, w2.csv, w3.csv, w4.csv and w5.csv ww1.csv, ww2.csv, ww3.csv, ww4.csv and ww5.csv

NLoS BQ b1.csv w1.csv, w2.csv, w3.csv, w4.csv and w5.csv ww1.csv, ww2.csv, ww3.csv, ww4.csv and ww5.csv

NLoS PIFA b1.csv w1.csv, w2.csv, w3.csv, w4.csv and w5.csv ww1.csv, ww2.csv, ww3.csv, ww4.csv and ww5.csv

4 20 20 44

Table 2: Sample/Spectrogram distribution across activity classes in Wallhack1.8k.

Scenario System

"no presence" / label 0

"walking" / label 1

"walking + arm-waving" / label 2 Total

LoS BQ 149 154 155

LoS PIFA 149 160 152

NLoS BQ 148 150 152

NLoS PIFA 143 147 147

589 611 606 1,806

Download and UseThis data may be used for non-commercial research purposes only. If you publish material based on this data, we request that you include a reference to one of our papers [1,2].

[1] Strohmayer, Julian, and Martin Kampel. (2024). “Data Augmentation Techniques for Cross-Domain WiFi CSI-Based Human Activity Recognition”, In IFIP International Conference on Artificial Intelligence Applications and Innovations (pp. 42-56). Cham: Springer Nature Switzerland, doi: https://doi.org/10.1007/978-3-031-63211-2_4.

[2] Strohmayer, Julian, and Martin Kampel., “Directional Antenna Systems for Long-Range Through-Wall Human Activity Recognition,” 2024 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates, 2024, pp. 3594-3599, doi: https://doi.org/10.1109/ICIP51287.2024.10647666.

BibTeX citations:

@inproceedings{strohmayer2024data, title={Data Augmentation Techniques for Cross-Domain WiFi CSI-Based Human Activity Recognition}, author={Strohmayer, Julian and Kampel, Martin}, booktitle={IFIP International Conference on Artificial Intelligence Applications and Innovations}, pages={42--56}, year={2024}, organization={Springer}}@INPROCEEDINGS{10647666, author={Strohmayer, Julian and Kampel, Martin}, booktitle={2024 IEEE International Conference on Image Processing (ICIP)}, title={Directional Antenna Systems for Long-Range Through-Wall Human Activity Recognition}, year={2024}, volume={}, number={}, pages={3594-3599}, keywords={Visualization;Accuracy;System performance;Directional antennas;Directive antennas;Reflector antennas;Sensors;Human Activity Recognition;WiFi;Channel State Information;Through-Wall Sensing;ESP32}, doi={10.1109/ICIP51287.2024.10647666}}

Comparative results for pattern mixing-based data augmentation methods.

Over the last ten years, social media has become a crucial data source for businesses and researchers, providing a space where people can express their opinions and emotions. To analyze this data and classify emotions and their polarity in texts, natural language processing (NLP) techniques such as emotion analysis (EA) and sentiment analysis (SA) are employed. However, the effectiveness of these tasks using machine learning (ML) and deep learning (DL) methods depends on large labeled datasets, which are scarce in languages like Spanish. To address this challenge, researchers use data augmentation (DA) techniques to artificially expand small datasets. This study aims to investigate whether DA techniques can improve classification results using ML and DL algorithms for sentiment and emotion analysis of Spanish texts. Various text manipulation techniques were applied, including transformations, paraphrasing (back-translation), and text generation using generative adversarial networks, to small datasets such as song lyrics, social media comments, headlines from national newspapers in Chile, and survey responses from higher education students. The findings show that the Convolutional Neural Network (CNN) classifier achieved the most significant improvement, with an 18% increase using the Generative Adversarial Networks for Sentiment Text (SentiGan) on the Aggressiveness (Seriousness) dataset. Additionally, the same classifier model showed an 11% improvement using the Easy Data Augmentation (EDA) on the Gender-Based Violence dataset. The performance of the Bidirectional Encoder Representations from Transformers (BETO) also improved by 10% on the back-translation augmented version of the October 18 dataset, and by 4% on the EDA augmented version of the Teaching survey dataset. These results suggest that data augmentation techniques enhance performance by transforming text and adapting it to the specific characteristics of the dataset. Through experimentation with various augmentation techniques, this research provides valuable insights into the analysis of subjectivity in Spanish texts and offers guidance for selecting algorithms and techniques based on dataset features.

Traditional differential expression genes (DEGs) identification models have limitations in small sample size datasets because they require meeting distribution assumptions, otherwise resulting high false positive/negative rates due to sample variation. In contrast, tabular data model based on deep learning (DL) frameworks do not need to consider the data distribution types and sample variation. However, applying DL to RNA-Seq data is still a challenge due to the lack of proper labeling and the small sample size compared to the number of genes. Data augmentation (DA) extracts data features using different methods and procedures, which can significantly increase complementary pseudo-values from limited data without significant additional cost. Based on this, we combine DA and DL framework-based tabular data model, propose a model TabDEG, to predict DEGs and their up-regulation/down-regulation directions from gene expression data obtained from the Cancer Genome Atlas database. Compared to five counterpart methods, TabDEG has high sensitivity and low misclassification rates. Experiment shows that TabDEG is robust and effective in enhancing data features to facilitate classification of high-dimensional small sample size datasets and validates that TabDEG-predicted DEGs are mapped to important gene ontology terms and pathways associated with cancer.

K. Scott Mader created the original dataset of 204 hand-drawn images for Parkinson’s disease diagnosis, consisting of two classes: Healthy and Parkinson. The dataset includes spiral and wave drawings. For my thesis, the original 204 images were expanded to 3,264 across the same two classes. This increase was achieved through data augmentation techniques, including rotations of 90°, 180°, and 270°, vertical flipping at 180°, and conversion to color images. The augmented data gives the model more opportunities to generalize, enhancing training and testing processes.

PDBscreen with multiple data augmentation strategies suitable for training protein-ligand interaction prediction methods.

PDBscreen is the training dataset for EquiScore.

There are four datasets:

1.Dataset_structure indicates the structure of the datasets, such as column name, type, and value.

2. Spanish_promise_exp_nfr_train and Spanish_promise_exp_nfr_test are the non-functional requirements of the Promise_exp[1] dataset translated into the Spanish language.

3. Blanced_promise_exp_nfr_train is the new balanced dataset of Spanish_promise_exp_nfr_train, in which the Data Augmentation technique with chatGPT was applied to increase the requirements with little data and random undersampling was used to eliminate requirements.

Abstract: The integration of neural-network-based systems into clinical practice is limited by challenges related to domain generalization and robustness. The computer vision community established benchmarks such as ImageNet-C as a fundamental prerequisite to measure progress towards those challenges. Similar datasets are largely absent in the medical imaging community which lacks a comprehensive benchmark that spans across imaging modalities and applications. To address this gap, we create and open-source MedMNIST-C, a benchmark dataset based on the MedMNIST+ collection, covering 12 datasets and 9 imaging modalities. We simulate task and modality-specific image corruptions of varying severity to comprehensively evaluate the robustness of established algorithms against real-world artifacts and distribution shifts. We further provide quantitative evidence that our simple-to-use artificial corruptions allow for highly performant, lightweight data augmentation to enhance model robustness. Unlike traditional, generic augmentation strategies, our approach leverages domain knowledge, exhibiting significantly higher robustness when compared to widely adopted methods. By introducing MedMNIST-C and open-sourcing the corresponding library allowing for targeted data augmentations, we contribute to the development of increasingly robust methods tailored to the challenges of medical imaging. The code is available at github.com/francescodisalvo05/medmnistc-api.

This work has been accepted at the Workshop on Advancing Data Solutions in Medical Imaging AI @ MICCAI 2024 [preprint].

Note: Due to space constraints, we have uploaded all datasets except TissueMNIST-C. However, it can be reproduced via our APIs.

Usage: We recommend using the demo code and tutorials available on our GitHub repository.

Citation: If you find this work useful, please consider citing us:

@article{disalvo2024medmnist,
 title={MedMNIST-C: Comprehensive benchmark and improved classifier robustness by simulating realistic image corruptions},
 author={Di Salvo, Francesco and Doerrich, Sebastian and Ledig, Christian},
 journal={arXiv preprint arXiv:2406.17536},
 year={2024}
}

Disclaimer: This repository is inspired by MedMNIST APIs and the ImageNet-C repository. Thus, please also consider citing MedMNIST, the respective source datasets (described here), and ImageNet-C.

Diversification rates vary across species as a response to various factors, including environmental conditions and species-specific features. Phylogenetic models that allow accounting for and quantifying this heterogeneity in diversification rates have proven particularly useful for understanding clades diversification. Recently, we introduced the cladogenetic diversification rate shift model (ClaDS), which allows inferring subtle rate variations across lineages. Here we present a new inference technique for this model that considerably reduces computation time through the use of data augmentation and provide an implementation of this method in Julia. In addition to drastically reducing computation time, this new inference approach provides a posterior distribution of the augmented data, that is the tree with extinct and unsampled lineages as well as associated diversification rates. In particular, this allows extracting the distribution through time of both the mean rate and the number of lineages. We assess the statistical performances of our approach using simulations and illustrate its application on the entire bird radiation. Methods These additionnal data contains supplementary figures supporting the paper, as well as a tutorial for the use of the Julia package.

The .jld2 file is the result of the run of ClaDS on the complete bird phylogeny computed with molecular data from Jetz (2012) with the Hackett backbone, containing 6670 species. We use TreeAnnotator from the software Beast with the Common Ancestor option for node height (Bouckaert 2019) to obtain a Maximum Clade Credibility (MCC) tree computed from a sample of 1000 trees from the posterior distribution. We fix the sampling fractions for each of the subtrees of the tree from Jetz (2012) as the ratio between the number of species in the molecular phylogeny over that in the phylogeny including all bird species. We attach the results of this analysis as a supplementary material to this paper.

Bouckaert, R., T. G. Vaughan, J. Barido-Sottani, S. Duchêne, M. Fourment, A. Gavryushkina, J. Heled, G. Jones, D. Kühnert, N. De Maio, et al. 2019. Beast 2.5: An advanced software platform for bayesian evolutionary analysis. PLoS computational biology 15:e1006650.

Jetz, W., G. Thomas, J. Joy, K. Hartmann, and A. Mooers. 2012. The global diversity of birds in space and time. Nature 491:444.

The original dataset can be found in the following link (https://www.kaggle.com/datasets/hamdallak/the-iqothnccd-lung-cancer-dataset/data)

The goal for this dataset is to enhance the usability of the original dataset by augmenting the data to generate more CT images. The augmented dataset has more than 10 times the number of images compared to the original. Data, and specifically, image augmentation is a popular technique used in Data Engineering to enlarge the existing dataset in order to make the model more robust and more precise. Medical images are very hard to come by, so sometimes Data Augmentation is a necessity when it comes to these kinds of datasets.

For the purpose of augmenting the existing images, I created a notebook which can be found in the following link (https://www.kaggle.com/code/aleksandarcvetanov/elastic-transformation-of-ct-images). The notebook uses the OpenCV library and its methods to achieve elastic transformation of the images. Elastic transformation (deformation) is a well-known technique in image augmentation, cited in numerous science papers and articles. Elastic transformation of images is the base technique used in the original development of the U-Net, a popular neural network developed for the purposes of classifying and segmenting medical images using Convolutional Neural Networks.

More information about the original dataset can be found in the text file attached with this dataset.

This repository contains the data and associated results of all experiments conducted in our work "Signature Informed Sampling for Transcriptomic Data". In this work we propose a simple, novel, non-parametric method for augmenting data inspired by the concept of chromosomal crossover. We benchmark our proposed methods against random oversampling, SMOTE, modified versions of gamma-Poisson and Poisson sapling, and the unbalanced data.

The compressed file data_5x5stratified.zip contains all the data used for our experiments. This includes the original count data based off of which augmentation was performed, the cross validation split indices as a json file, the training and validation data (TCGA) augmented by the various augmentation methods mentioned in our study, a test set (containing only real samples from TCGA) and an external test set (CPTAC) standardised accordingly with respect to each augmentation method and training data per cv split.

The compressed file 5x5_Results.zip contains all the results from all the experiments. This includes the parameter files used to train the various models, the metrics computed, the latent space of train, validation and test (if the model is a VAE), and the trained model itself for all 25 (5x5) splits.

Terrestrial ecosystems have emerged as critical carbon sinks, holding a crucial role in the carbon cycle. Net ecosystem productivity (NEP) is a highly significant parameter in terrestrial ecosystems, representing the net ecosystem exchange (NEE) between ecosystems and the atmosphere, without considering other carbon fluxes from disturbances. In this NEP product, we harmonized various sets of tower-based NEP from flux sites as target variable, remote sensing product and meteorological data as traning variables. We further optimizied these smaple sets to address the problems in spatial distribution, culminating in a global NEP product spanning the years 2001-2022, achieved through the application of the random forest method. This dataset contains NEP data for global terrestrial ecosystems for the period 2001-2022 in MgC with a temporal resolution of 1 year. The spatial resolution of the product is 250m and the data format is TIFF.

For detailed instructions on how to use the dataset, see User Guides.doc!

Dataset Description:

This dataset contains a collection of images featuring individual Lao characters, specifically designed for image classification tasks. The dataset is organized into folders, where each folder is named directly with the Lao character it represents (e.g., a folder named "ກ", a folder named "ຂ", and so on) and contains 100 images of that character.

Content:

The dataset comprises images of 44 distinct Lao characters, including consonants, vowels, and tone marks.

• Image Characteristics: - Resolution: 128x128 pixels - Format: JPEG (.jpg) - Appearance: Each image features a white drawn line representing the Lao character against a black background.

Structure:

- The dataset is divided into 44 folders.
- Each folder is named with the actual Lao character it contains.
- Each folder contains 100 images of the corresponding Lao character.
- This results in a total of 4400 images in the dataset.

Potential Use Cases:

- Training and evaluating image classification models for Lao character recognition.
- Developing Optical Character Recognition (OCR) systems for the Lao language.
- Research in computer vision and pattern recognition for Southeast Asian scripts.

Usage Notes / Data Augmentation:

The nature of these images (white characters on a black background) lends itself well to various data augmentation techniques to improve model robustness and performance. Consider applying augmentations such as:

- Geometric Transformations:
  - Zoom (in/out)
  - Height and width shifts
  - Rotation
  - Perspective transforms
- Blurring Effects:
  - Standard blur
  - Motion blur
- Noise Injection:
  - Gaussian noise

Applying these augmentations can help create a more diverse training set and potentially lead to better generalization on unseen data.