Related papers: AugLy: Data Augmentations for Robustness
Transfer learning across domains with distribution shift remains a fundamental challenge in building robust and adaptable machine learning systems. While adversarial perturbations are traditionally viewed as threats that expose model…
Deep learning algorithms have shown promising results in visual question answering (VQA) tasks, but a more careful look reveals that they often do not understand the rich signal they are being fed with. To understand and better measure the…
Modern deep neural networks can achieve high accuracy when the training distribution and test distribution are identically distributed, but this assumption is frequently violated in practice. When the train and test distributions are…
Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection. Noting that most state-of-the-art object detectors benefit from fine-tuning a…
With the capabilities of understanding and executing natural language instructions, Large language models (LLMs) can potentially act as a powerful tool for textual data augmentation. However, the quality of augmented data depends heavily on…
Data augmentation is used extensively to improve model generalisation. However, reliance on external libraries to implement augmentation methods introduces a vulnerability into the machine learning pipeline. It is well known that backdoors…
Diverse data augmentation strategies are a natural approach to improving robustness in computer vision models against unforeseen shifts in data distribution. However, the ability to tailor such strategies to inoculate a model against…
Ultra-low-field (ULF) MRI promises broader accessibility but suffers from low signal-to-noise ratio (SNR), reduced spatial resolution, and contrasts that deviate from high-field standards. Image-to-image translation can map ULF images to a…
Data augmentation (DA) has gained widespread popularity in deep speaker models due to its ease of implementation and significant effectiveness. It enriches training data by simulating real-life acoustic variations, enabling deep neural…
The quality and size of training set have great impact on the results of deep learning-based face related tasks. However, collecting and labeling adequate samples with high quality and balanced distributions still remains a laborious and…
The spread of fake news harms individuals and presents a critical social challenge that must be addressed. Although numerous algorithmic and insightful features have been developed to detect fake news, many of these features can be…
Users who come to recommendation platforms are heterogeneous in activity levels. There usually exists a group of core users who visit the platform regularly and consume a large body of content upon each visit, while others are casual users…
While great progress has been made at making neural networks effective across a wide range of visual tasks, most models are surprisingly vulnerable. This frailness takes the form of small, carefully chosen perturbations of their input,…
Data augmentation is a key tool for improving the performance of deep networks, particularly when there is limited labeled data. In some fields, such as computer vision, augmentation methods have been extensively studied; however, for…
Data augmentation is a major component of many machine learning methods with state-of-the-art performance. Common augmentation strategies work by drawing random samples from a space of transformations. Unfortunately, such sampling…
Gradient leakage attacks pose a significant threat to the privacy guarantees of federated learning. While distortion-based protection mechanisms are commonly employed to mitigate this issue, they often lead to notable performance…
The large volumes of structured data currently available, from Web tables to open-data portals and enterprise data, open up new opportunities for progress in answering many important scientific, societal, and business questions. However,…
Recent works have shown that self-supervised learning can achieve remarkable robustness when integrated with adversarial training (AT). However, the robustness gap between supervised AT (sup-AT) and self-supervised AT (self-AT) remains…
Accurately interpreting cardiac auscultation signals plays a crucial role in diagnosing and managing cardiovascular diseases. However, the paucity of labelled data inhibits classification models' training. Researchers have turned to…
Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we…