Related papers: When Labels Are Scarce: A Systematic Mapping of La…

In this paper, we study the problem of learning from weakly labeled data, where labels of the training examples are incomplete. This includes, for example, (i) semi-supervised learning where labels are partially known; (ii) multi-instance…

Labeling data (e.g., labeling the people, objects, actions and scene in images) comprehensively and efficiently is a widely needed but challenging task. Numerous models were proposed to label various data and many approaches were designed…

The rapid development of deep learning has made a great progress in image segmentation, one of the fundamental tasks of computer vision. However, the current segmentation algorithms mostly rely on the availability of pixel-level…

Competitive methods for multi-label classification typically invest in learning labels together. To do so in a beneficial way, analysis of label dependence is often seen as a fundamental step, separate and prior to constructing a…

Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks. The success of existing approaches is attributed to deep network design and large amount of labelled training data, where the…

Compared with multi-class classification, multi-label classification that contains more than one class is more suitable in real life scenarios. Obtaining fully labeled high-quality datasets for multi-label classification problems, however,…

Large unlabeled datasets demand efficient and scalable data labeling solutions, in particular when the number of instances and classes is large. This leads to significant visual scalability challenges and imposes a high cognitive load on…

Machine learning algorithms are increasingly being applied in security-related tasks such as spam and malware detection, although their security properties against deliberate attacks have not yet been widely understood. Intelligent and…

High-quality labels are expensive to obtain for many machine learning tasks, such as medical image classification tasks. Therefore, probabilistic (weak) labels produced by weak supervision tools are used to seed a process in which…

Labeling data correctly is an expensive and challenging task in machine learning, especially for on-line data streams. Deep learning models especially require a large number of clean labeled data that is very difficult to acquire in…

Hierarchical text classification has many real-world applications. However, labeling a large number of documents is costly. In practice, we can use semi-supervised learning or weakly supervised learning (e.g., dataless classification) to…

Data-driven software engineering processes, such as vulnerability prediction heavily rely on the quality of the data used. In this paper, we observe that it is infeasible to obtain a noise-free security defect dataset in practice. Despite…

In many real-world settings, machine learning models need to identify user inputs that are out-of-domain (OOD) so as to avoid performing wrong actions. This work focuses on a challenging case of OOD detection, where no labels for in-domain…

We introduce a novel method for training machine learning models in the presence of noisy labels, which are prevalent in domains such as medical diagnosis and autonomous driving and have the potential to degrade a model's generalization…

This manuscript presents a series of my selected contributions to the topic of label-efficient learning in computer vision and remote sensing. The central focus of this research is to develop and adapt methods that can learn effectively…

Vision-Language Models (VLMs), with their powerful content generation capabilities, have been successfully applied to data annotation processes. However, the VLM-generated labels exhibit dual limitations: low quality (i.e., label noise) and…

Though many deep learning-based models have made great progress in vulnerability detection, we have no good understanding of these models, which limits the further advancement of model capability, understanding of the mechanism of model…

Laboratories are prone to severe injuries from minor unsafe actions, yet continuous safety monitoring -- beyond mandatory pre-lab safety training -- is limited by human availability. Vision language models (VLMs) offer promise for…

Labeling training data has become one of the major roadblocks to using machine learning. Among various weak supervision paradigms, programmatic weak supervision (PWS) has achieved remarkable success in easing the manual labeling bottleneck…

Vulnerability datasets used for ML testing implicitly contain retrospective information. When tested on the field, one can only use the labels available at the time of training and testing (e.g. seen and assumed negatives). As…