Related papers: Resource Constrained Semantic Segmentation for Was…

The goal of incremental Few-shot Semantic Segmentation (iFSS) is to extend pre-trained segmentation models to new classes via few annotated images without access to old training data. During incrementally learning novel classes, the data…

Regenerating codes allow distributed storage systems to recover from the loss of a storage node while transmitting the minimum possible amount of data across the network. We present a systematic computer search for optimal systematic…

Semantic communications offer the potential to alleviate communication loads by exchanging meaningful information. However, semantic extraction (SE) is computationally intensive, posing challenges for resource-constrained Internet of Things…

Assigning a label to each pixel in an image, namely semantic segmentation, has been an important task in computer vision, and has applications in autonomous driving, robotic navigation, localization, and scene understanding. Fully…

While nowadays deep neural networks achieve impressive performances on semantic segmentation tasks, they are usually trained by optimizing pixel-wise losses such as cross-entropy. As a result, the predictions outputted by such networks…

In many classification settings, the class of primary interest is underrepresented, leading to imbalanced data problems that arise in applications such as rare disease detection and fraud identification. In these contexts, identifying a…

As digital technologies advance, communication networks face challenges in handling the vast data generated by intelligent devices. Autonomous vehicles, smart sensors, and IoT systems necessitate new paradigms. This thesis addresses these…

Semantic segmentation benefits robotics related applications especially autonomous driving. Most of the research on semantic segmentation is only on increasing the accuracy of segmentation models with little attention to computationally…

Resource-constrained classification tasks are common in real-world applications such as allocating tests for disease diagnosis, hiring decisions when filling a limited number of positions, and defect detection in manufacturing settings…

We deal with the problem of semantic classification of challenging and highly-cluttered dataset. We present a novel, and yet a very simple classification technique by leveraging the ease of classifiability of any existing well separable…

In this work we investigate the problem of road scene semantic segmentation using Deconvolutional Networks (DNs). Several constraints limit the practical performance of DNs in this context: firstly, the paucity of existing pixel-wise…

Convolutional neural networks model the transformation of the input sensory data at the bottom of a network hierarchy to the semantic information at the top of the visual hierarchy. Feedforward processing is sufficient for some object…

Semantic segmentation is a computer vision task that associates a label with each pixel in an image. Modern approaches tend to introduce class embeddings into semantic segmentation for deeply utilizing category semantics, and regard…

Deep convolutional neural networks (CNN) have proven to be remarkably effective in semantic segmentation tasks. Most popular loss functions were introduced targeting improved volumetric scores, such as the Dice coefficient (DSC). By design,…

In this paper we investigate image classification with computational resource limits at test time. Two such settings are: 1. anytime classification, where the network's prediction for a test example is progressively updated, facilitating…

One of the key drawbacks of 3D convolutional neural networks for segmentation is their memory footprint, which necessitates compromises in the network architecture in order to fit into a given memory budget. Motivated by the RevNet for…

Training and inference on edge devices often requires an efficient setup due to computational limitations. While pre-computing data representations and caching them on a server can mitigate extensive edge device computation, this leads to…

Most recent semantic segmentation methods train deep convolutional neural networks with fully annotated masks requiring pixel-accuracy for good quality training. Common weakly-supervised approaches generate full masks from partial input…

Classification tasks require a balanced distribution of data to ensure the learner to be trained to generalize over all classes. In real-world datasets, however, the number of instances vary substantially among classes. This typically leads…

The performance of deep learning based semantic segmentation models heavily depends on sufficient data with careful annotations. However, even the largest public datasets only provide samples with pixel-level annotations for rather limited…