Related papers: Synthetic Examples Improve Generalization for Rare…

The quality and realism of synthetically generated fingerprint images have increased significantly over the past decade fueled by advancements in generative artificial intelligence (GenAI). This has exacerbated the vulnerability of…

Deep learning approaches to object detection have achieved reliable detection of specific object classes in images. However, extending a model's detection capability to new object classes requires large amounts of annotated training data,…

Mixup is a data augmentation technique that relies on training using random convex combinations of data points and their labels. In recent years, Mixup has become a standard primitive used in the training of state-of-the-art image…

Continued improvements in deep learning architectures have steadily advanced the overall performance of 3D object detectors to levels on par with humans for certain tasks and datasets, where the overall performance is mostly driven by…

The human visual system has the remarkably ability to be able to effortlessly learn novel concepts from only a few examples. Mimicking the same behavior on machine learning vision systems is an interesting and very challenging research…

Vision-based object detectors are a crucial basis for robotics applications as they provide valuable information about object localisation in the environment. These need to ensure high reliability in different lighting conditions,…

Despite great success in human parsing, progress for parsing other deformable articulated objects, like animals, is still limited by the lack of labeled data. In this paper, we use synthetic images and ground truth generated from CAD animal…

Supervised training of an automated medical image analysis system often requires a large amount of expert annotations that are hard to collect. Moreover, the proportions of data available across different classes may be highly imbalanced…

We propose a new strategy to improve the accuracy and robustness of image classification. First, we train a baseline CNN model. Then, we identify challenging regions in the feature space by identifying all misclassified samples, and…

Data seems cheap to get, and in many ways it is, but the process of creating a high quality labeled dataset from a mass of data is time-consuming and expensive. With the advent of rich 3D repositories, photo-realistic rendering systems…

In this paper, we explore the use of GAN-based few-shot data augmentation as a method to improve few-shot classification performance. We perform an exploration into how a GAN can be fine-tuned for such a task (one of which is in a…

Scarcity of labeled data, especially for rare events, hinders training effective machine learning models. This paper proposes SYNAPSE-G (Synthetic Augmentation for Positive Sampling via Expansion on Graphs), a novel pipeline leveraging…

Simulation data can be utilized to extend real-world driving data in order to cover edge cases, such as vehicle accidents. The importance of handling edge cases can be observed in the high societal costs in handling car accidents, as well…

The masses of data now available have opened up the prospect of discovering weak signals using machine-learning algorithms, with a view to predictive or interpretation tasks. As this survey of recent results attempts to show, bringing…

Autonomous driving techniques have been flourishing in recent years while thirsting for huge amounts of high-quality data. However, it is difficult for real-world datasets to keep up with the pace of changing requirements due to their…

Few-shot learning (FSL) aims to learn new categories with a few visual samples per class. Few-shot class representations are often biased due to data scarcity. To mitigate this issue, we propose to generate visual samples based on semantic…

Prompt learning is a powerful technique for transferring Vision-Language Models (VLMs) such as CLIP to downstream tasks. However, the prompt-based methods that are fine-tuned solely with base classes may struggle to generalize to novel…

In real-world applications, data do not reflect the ones commonly used for neural networks training, since they are usually few, unlabeled and can be available as a stream. Hence many existing deep learning solutions suffer from a limited…

Several anomaly detection and classification methods rely on large amounts of non-anomalous or "normal" samples under the assump- tion that anomalous data is typically harder to acquire. This hypothesis becomes questionable in Few-Shot…

How should we present training examples to learners to teach them classification rules? This is a natural problem when training workers for crowdsourcing labeling tasks, and is also motivated by challenges in data-driven online education.…