Cynthia I. Ugwu

C. I. Ugwu, S. Casarin, O. Lanz

As a fundamental part of computational healthcare, Computer Tomography (CT) and Magnetic Resonance Imaging (MRI) provide volumetric data, making the development of algorithms for 3D image analysis a necessity. Despite being computationally cheap, 2D Convolutional Neural Networks can only extract spatial information. In contrast, 3D CNNs can extract three-dimensional features, but they have higher computational costs and latency, which is a limitation for clinical practice that requires fast and efficient models. Inspired by the field of video action recognition we propose a new 2D-based model dubbed Slice SHift UNet (SSH-UNet) which encodes three-dimensional features at 2D CNN's complexity. More precisely multi-view features are collaboratively learned by performing 2D convolutions along the three orthogonal planes of a volume and imposing a weights-sharing mechanism. The third dimension, which is neglected by the 2D convolution, is reincorporated by shifting a portion of the feature maps along the slices' axis. The effectiveness of our approach is validated in Multi-Modality Abdominal Multi-Organ Segmentation (AMOS) and Multi-Atlas Labeling Beyond the Cranial Vault (BTCV) datasets, showing that SSH-UNet is more efficient while on par in performance with state-of-the-art architectures.

C. I. Ugwu, S. Casarin, O. Lanz

Anomaly detection is crucial in large-scale industrial manufacturing as it helps detect and localise defective parts. Pre-training feature extractors on large-scale datasets is a popular approach for this task. Stringent data security and privacy regulations and high costs and acquisition time hinder the availability and creation of such large datasets. While recent work in anomaly detection primarily focuses on the development of new methods built on such extractors, the importance of the data used for pre-training has not been studied. Therefore, we evaluated the performance of eight state-of-the-art methods pre-trained using dynamically generated fractal images on the famous benchmark datasets MVTec and VisA. In contrast to existing literature, which predominantly examines the transfer-learning capabilities of fractals, in this study, we compare models pre-trained with fractal images against those pre-trained with ImageNet, without subsequent fine-tuning. Although pre-training with ImageNet remains a clear winner, the results of fractals are promising considering that the anomaly detection task required features capable of discerning even minor visual variations. This opens up the possibility for a new research direction where feature extractors could be trained on synthetically generated abstract datasets reconciling the ever-increasing demand for data in machine learning while circumventing privacy and security concerns.

Sofia Casarin, Cynthia I. Ugwu, Sergio Escalera et al.

The landscape of deep learning research is moving towards innovative strategies to harness the true potential of data. Traditionally, emphasis has been on scaling model architectures, resulting in large and complex neural networks, which can be difficult to train with limited computational resources. However, independently of the model size, data quality (i.e. amount and variability) is still a major factor that affects model generalization. In this work, we propose a novel technique to exploit available data through the use of automatic data augmentation for the tasks of image classification and semantic segmentation. We introduce the first Differentiable Augmentation Search method (DAS) to generate variations of images that can be processed as videos. Compared to previous approaches, DAS is extremely fast and flexible, allowing the search on very large search spaces in less than a GPU day. Our intuition is that the increased receptive field in the temporal dimension provided by DAS could lead to benefits also to the spatial receptive field. More specifically, we leverage DAS to guide the reshaping of the spatial receptive field by selecting task-dependant transformations. As a result, compared to standard augmentation alternatives, we improve in terms of accuracy on ImageNet, Cifar10, Cifar100, Tiny-ImageNet, Pascal-VOC-2012 and CityScapes datasets when plugging-in our DAS over different light-weight video backbones.