Related papers: Learning with Weak Supervision for Email Intent De…
Scribble-based weakly supervised semantic segmentation leverages only a few annotated pixels as labels to train a segmentation model, presenting significant potential for reducing the human labor involved in the annotation process. This…
Machine learning has become successful in solving wireless interference management problems. Different kinds of deep neural networks (DNNs) have been trained to accomplish key tasks such as power control, beamforming and admission control.…
Many success stories involving deep neural networks are instances of supervised learning, where available labels power gradient-based learning methods. Creating such labels, however, can be expensive and thus there is increasing interest in…
We address a weakly-supervised low-shot instance segmentation, an annotation-efficient training method to deal with novel classes effectively. Since it is an under-explored problem, we first investigate the difficulty of the problem and…
Email spam detection is a critical task in modern communication systems, essential for maintaining productivity, security, and user experience. Traditional machine learning and deep learning approaches, while effective in static settings,…
Audio content analysis in terms of sound events is an important research problem for a variety of applications. Recently, the development of weak labeling approaches for audio or sound event detection (AED) and availability of large scale…
When one wants to train a neural network to perform semantic segmentation, creating pixel-level annotations for each of the images in the database is a tedious task. If he works with aerial or satellite images, which are usually very large,…
With the popularity and development of the wearable devices such as smartphones, human activity recognition (HAR) based on sensors has become as a key research area in human computer interaction and ubiquitous computing. The emergence of…
Web search is among the most frequent online activities. Whereas traditional information retrieval techniques focus on the information need behind a user query, previous work has shown that user behaviour and interaction can provide…
Automatic fact-checking systems detect misinformation, such as fake news, by (i) selecting check-worthy sentences for fact-checking, (ii) gathering related information to the sentences, and (iii) inferring the factuality of the sentences.…
Training object detection models usually requires instance-level annotations, such as the positions and labels of all objects present in each image. Such supervision is unfortunately not always available and, more often, only image-level…
We propose a novel algorithm for weakly supervised semantic segmentation based on image-level class labels only. In weakly supervised setting, it is commonly observed that trained model overly focuses on discriminative parts rather than the…
Research in the supervised learning algorithms field implicitly assumes that training data is labeled by domain experts or at least semi-professional labelers accessible through crowdsourcing services like Amazon Mechanical Turk. With the…
At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specifically active learning…
Task-oriented dialog(TOD) aims to assist users in achieving specific goals through multi-turn conversation. Recently, good results have been obtained based on large pre-trained models. However, the labeled-data scarcity hinders the…
Multiple instance learning (MIL) problem is currently solved from either bag-classification or instance-classification perspective, both of which ignore important information contained in some instances and result in limited performance.…
Voice-controlled dialog systems have become immensely popular due to their ability to perform a wide range of actions in response to diverse user queries. These agents possess a predefined set of skills or intents to fulfill specific user…
Collecting large-scale medical datasets with fine-grained annotations is time-consuming and requires experts. For this reason, weakly supervised learning aims at optimising machine learning models using weaker forms of annotations, such as…
The performance of deep neural networks improves with more annotated data. The problem is that the budget for annotation is limited. One solution to this is active learning, where a model asks human to annotate data that it perceived as…
Intent classification is an important component of a functional Information Retrieval ecosystem. Many current approaches to intent classification, typically framed as a classification problem, can be problematic as intents are often hard to…