Related papers: Semi-Supervised and Task-Driven Data Augmentation

Deep learning (DL) techniques are highly effective for defect detection from images. Training DL classification models, however, requires vast amounts of labeled data which is often expensive to collect. In many cases, not only the…

With the latest advances in Deep Learning-based generative models, it has not taken long to take advantage of their remarkable performance in the area of time series. Deep neural networks used to work with time series heavily depend on the…

Training accurate intent classifiers requires labeled data, which can be costly to obtain. Data augmentation methods may ameliorate this issue, but the quality of the generated data varies significantly across techniques. We study the…

Data augmentation is often used to enlarge datasets with synthetic samples generated in accordance with the underlying data distribution. To enable a wider range of augmentations, we explore negative data augmentation strategies (NDA)that…

Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly pronounced when adapting to a specific target domain, such…

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we…

Graph neural networks, a powerful deep learning tool to model graph-structured data, have demonstrated remarkable performance on numerous graph learning tasks. To address the data noise and data scarcity issues in deep graph learning, the…

Data augmentation methods enrich datasets with augmented data to improve the performance of neural networks. Recently, automated data augmentation methods have emerged, which automatically design augmentation strategies. Existing work…

Data augmentation using generative models has emerged as a powerful paradigm for enhancing performance in computer vision tasks. However, most existing augmentation approaches primarily focus on optimizing intrinsic data attributes -- such…

Segmentation is essential for medical image analysis tasks such as intervention planning, therapy guidance, diagnosis, treatment decisions. Deep learning is becoming increasingly prominent for segmentation, where the lack of annotations,…

Data diversity and volume are crucial to the success of training deep learning models, while in the medical imaging field, the difficulty and cost of data collection and annotation are especially huge. Specifically in robotic surgery, data…

Data augmentation is a widely used and effective technique to improve the generalization performance of deep neural networks. Yet, despite often facing limited data availability when working with medical images, it is frequently…

3D medical image segmentation is a challenging task with crucial implications for disease diagnosis and treatment planning. Recent advances in deep learning have significantly enhanced fully supervised medical image segmentation. However,…

High-fidelity full-field micro-mechanical modeling of the non-linear path-dependent materials demands a substantial computational effort. Recent trends in the field incorporates data-driven Artificial Neural Networks (ANNs) as surrogate…

One of the biggest issues facing the use of machine learning in medical imaging is the lack of availability of large, labelled datasets. The annotation of medical images is not only expensive and time consuming but also highly dependent on…

Weakly supervised segmentation is an important problem in medical image analysis due to the high cost of pixelwise annotation. Prior methods, while often focusing on weak labels of 2D images, exploit few structural cues of volumetric…

Recent years have witnessed the great progress of deep neural networks on semantic segmentation, particularly in medical imaging. Nevertheless, training high-performing models require large amounts of pixel-level ground truth masks, which…

Reliable perception during fast motion maneuvers or in high dynamic range environments is crucial for robotic systems. Since event cameras are robust to these challenging conditions, they have great potential to increase the reliability of…

Semi-supervised learning has made significant strides in the medical domain since it alleviates the heavy burden of collecting abundant pixel-wise annotated data for semantic segmentation tasks. Existing semi-supervised approaches enhance…

Successive proposals of several self-supervised training schemes continue to emerge, taking one step closer to developing a universal foundation model. In this process, the unsupervised downstream tasks are recognized as one of the…