Related papers: DANCE: DAta-Network Co-optimization for Efficient …
Dataset condensation addresses the problem of data burden by learning a small synthetic training set that preserves essential knowledge from the larger real training set. To date, the state-of-the-art (SOTA) results are often yielded by…
To cope with the ever-increasing computational demand of the DNN execution, recent neural architecture search (NAS) algorithms consider hardware cost metrics into account, such as GPU latency. To further pursue a fast, efficient execution,…
Neural Architecture Search (NAS) has emerged as a powerful approach for automating neural network design. However, existing NAS methods face critical limitations in real-world deployments: architectures lack adaptability across scenarios,…
The analysis of large-scale complex networks is a major challenge in the Big Data domain. Given the large-scale of the complex networks researchers commonly deal with nowadays, the use of localized information (i.e. restricted to a limited…
This dissertation addresses visual scene understanding and enhances segmentation performance and generalization, training efficiency of networks, and holistic understanding. First, we investigate semantic segmentation in the context of…
Driven by rapid advances in large-scale generative models, synthetic data has emerged as a promising solution for visual understanding. While modern diffusion models achieve remarkable photorealistic image synthesis, their potential in…
Comprehensive semantic segmentation is one of the key components for robust scene understanding and a requirement to enable autonomous driving. Driven by large scale datasets, convolutional neural networks show impressive results on this…
Accurate segmentation of the pelvic CTs is crucial for the clinical diagnosis of pelvic bone diseases and for planning patient-specific hip surgeries. With the emergence and advancements of deep learning for digital healthcare, several…
Modern convolutional neural networks (CNNs) are workhorses for video and image processing, but fail to adapt to the computational complexity of input samples in a dynamic manner to minimize energy consumption. In this research, we propose…
Accurate semantic segmentation models typically require significant computational resources, inhibiting their use in practical applications. Recent works rely on well-crafted lightweight models to achieve fast inference. However, these…
This paper presents an effective and general data augmentation framework for medical image segmentation. We adopt a computationally efficient and data-efficient gradient-based meta-learning scheme to explicitly align the distribution of…
Deep learning will play a crucial role in enabling cognitive automation for the mobile networks of the future. Deep clustering, a subset of deep learning, could be a valuable tool for many network automation use-cases. Unfortunately, most…
One of the key criticisms of deep learning is that large amounts of expensive and difficult-to-acquire training data are required in order to train models with high performance and good generalization capabilities. Focusing on the task of…
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…
Deep learning-based medical image segmentation is increasingly used to support clinical diagnosis and develop new treatment strategies. However, model performance remains limited by the scarcity of high-quality annotated data and…
We propose a network architecture to perform efficient scene understanding. This work presents three main novelties: the first is an Improved Guided Upsampling Module that can replace in toto the decoder part in common semantic segmentation…
As research interests in medical image analysis become increasingly fine-grained, the cost for extensive annotation also rises. One feasible way to reduce the cost is to annotate with coarse-grained superclass labels while using limited…
Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…
Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards. Here, we address three of its most prominent hurdles, namely, i) the adaptation of a single…
Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget. Common solutions uniformly downsample the input images to…