High-autonomy vehicle functions rely on machine learning (ML) algorithms to understand the environment. Despite displaying remarkable performance in fair weather scenarios, perception algorithms are heavily affected by adverse weather and lighting conditions. To overcome these difficulties, ML engineers mainly rely on comprehensive real-world datasets. However, the difficulties in real-world data collection for critical areas of the operational design domain (ODD) often means synthetic data is required for perception training and safety validation. Thus, we present A-BDD, a large set of over 60,000 synthetically augmented images based on BDD100K that are equipped with semantic segmentation and bounding box annotations (inherited from the BDD100K dataset). The dataset contains augmented data for rain, fog, overcast and sunglare/shadow with varying intensity levels. We further introduce novel strategies utilizing feature-based image quality metrics like FID and CMMD, which help identify useful augmented and real-world data for ML training and testing. By conducting experiments on A-BDD, we provide evidence that data augmentations can play a pivotal role in closing performance gaps in adverse weather and lighting conditions.

Data augmentation is a key technique for addressing the challenge of limited datasets, which have become a major component in the training procedures of image processing. Techniques such as geometric transformations and color space adjustments have been thoroughly tested for their ability to artificially expand training datasets and generate semi-realistic data for training purposes. Data augmentation is the most important key to addressing the challenge of limited datasets, which have become a major component of image processing training procedures. Data augmentation techniques, such as geometric transformations and color space adjustments, are thoroughly tested for their ability to artificially expand training datasets and generate semi-realistic data for training purposes. Polygons play a crucial role in instance segmentation and have seen a surge in use across advanced models, such as YOLOv8. Despite their growing popularity, the lack of specialized libraries hampers the polygon-augmentation process. This paper introduces a novel solution to this challenge, embodied in the newly developed AugmenTory library. Notably, AugmenTory offers reduced computational demands in both time and space compared to existing methods. Additionally, the library includes a postprocessing thresholding feature. The AugmenTory package is publicly available on GitHub, where interested users can access the source code: https://github.com/Smartory/AugmenTory

I need to admit that it is unclear how image search will work with other domains. At the moment, everything is designed to work on natural images. To be applied to medical or satellite, I will need new models, and I do not have them in front of me. If there is interest, we can explore this option. I have a request -- if you have an idea how your product may benefit from an image search, do me a favor, and write in the comments or message on LinkedIn.

If you want to train your models with Tensorflow in the most efficient way you probably should use TFRecords and the Tensorflow data module to build your pipelines, but depending on the requirements and constraints of your applications, using them might be necessary not and an option, the good news is that Tensorflow has made both of them pretty clean and easy to use. In this article, we will go through a simple yet efficient way of building pipelines with complex combinations of data augmentation using the Tensorflow data module. One of the options I mentioned that could improve your models' training, is to use TFRecords, TFRecord is a simple format provided by Tensorflow for storing data, I am not going into too many details about TFRecords because it is not the focus of this article but if you want to learn more check out this tutorial from Tensorflow. The information provided here can be applied to train models with Tensorflow in any hardware, I am going to use TPU as the target hardware because if you are using TPUs, probably you are already trying to make the most of your resources, and you would need to use the Tensorflow data module anyway. First, we will begin by taking a look at how data augmentation is done at the official data augmentation tutorial by Tensorflow.

We introduce AugLy, a data augmentation library with a focus on adversarial robustness. AugLy provides a wide array of augmentations for multiple modalities (audio, image, text, & video). These augmentations were inspired by those that real users perform on social media platforms, some of which were not already supported by existing data augmentation libraries. AugLy can be used for any purpose where data augmentations are useful, but it is particularly well-suited for evaluating robustness and systematically generating adversarial attacks. In this paper we present how AugLy works, benchmark it compared against existing libraries, and use it to evaluate the robustness of various state-of-the-art models to showcase AugLy's utility. The AugLy repository can be found at https://github.com/facebookresearch/AugLy.

If you are new to the field of deep learning, at some point in time you may have heard of the topic of image augmentation. This article will discuss what image augmentation is and implement it in three different python libraries i.e Keras, PyTorch, and augmentation (specifically for image augmentation). So the first question arises what is image augmentation or in general data augmentation. Augmentation is the action or process of making or becoming greater in size or amount. In deep learning, deep networks require a large amount of training data to generalize well and achieve good accuracy. But in some cases, image data is not large enough.

I wanted an easy way to get a state-of-the-art image augmentation pipeline with no manual iteration, no separate models to train and no thinking. To provide that, I created MuarAugment (Model Uncertainty- And Randomness-based Augmentation), a GPU-supported Python package built on Pytorch, Albumentations and Kornia. There are a few resources you can use to master MuarAugment. There are Colab tutorials demonstrating MuarAugment. Most of the material in this article comes from those.

In machine learning (ML), if the situation when the model does not generalize well from the training data to unseen data is called overfitting. As you might know, it is one of the trickiest obstacles in applied machine learning. The first step in tackling this problem is to actually know that your model is overfitting. That is where proper cross-validation comes in. After identifying the problem you can prevent it from happening by applying regularization or training with more data. Still, sometimes you might not have additional data to add to your initial dataset. Acquiring and labeling additional data points may also be the wrong path. Of course, in many cases, it will deliver better results, but in terms of work, it is time-consuming and expensive a lot of the time.

The performance of a deep learning model is influenced by large datasets and diversity of the dataset. But, there might be situations where the dataset is simply not large enough or diverse enough. In such cases, data augmentation is used. Data augmentation is a technique that enables you to significantly increase the diversity of data available for training models, without actually collecting new data. Although deep learning models come with inbuilt methods to augment the data, these can be inefficient or lacking some required functionality.

I am one of the authors of the image augmentation library Albumentations. Image augmentations is an interpretable regularization technique. You transform the existing data to generate a new one. You can use the library with PyTorch, Keras, Tensorflow, or any other framework that can treat an image as a numpy array. Multi-target is the situation when every sample consists of a set of different objects.