Related papers: Adaptive Deep Learning for Entity Resolution by Ri…

Task engagement is defined as loadings on energetic arousal (affect), task motivation, and concentration (cognition). It is usually challenging and expensive to label cognitive state data, and traditional computational models trained with…

Label-efficient segmentation aims to perform effective segmentation on input data using only sparse and limited ground-truth labels for training. This topic is widely studied in 3D point cloud segmentation due to the difficulty of…

Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. Most current methods, however, require…

Large-scale labeled training datasets have enabled deep neural networks to excel on a wide range of benchmark vision tasks. However, in many applications it is prohibitively expensive or time-consuming to obtain large quantities of labeled…

In multi-label classification, each training instance is associated with multiple class labels simultaneously. Unfortunately, collecting the fully precise class labels for each training instance is time- and labor-consuming for real-world…

Quantifying the data uncertainty in learning tasks is often done by learning a prediction interval or prediction set of the label given the input. Two commonly desired properties for learned prediction sets are \emph{valid coverage} and…

Deep learning models are known to solve classification and regression problems by employing a number of epoch and training samples on a large dataset with optimal accuracy. However, that doesn't mean they are attack-proof or unexposed to…

Early Risk Detection (ERD) on the Web aims to identify promptly users facing social and health issues. Users are analyzed post-by-post, and it is necessary to guarantee correct and quick answers, which is particularly challenging in…

The study of model bias and variance with respect to decision boundaries is critically important in supervised classification. There is generally a tradeoff between the two, as fine-tuning of the decision boundary of a classification model…

Proper learning refers to the setting in which learners must emit predictors in the underlying hypothesis class $H$, and often leads to learners with simple algorithmic forms (e.g. empirical risk minimization (ERM), structural risk…

Deep learning has emerged as a technique of choice for rapid feature extraction across imaging disciplines, allowing rapid conversion of the data streams to spatial or spatiotemporal arrays of features of interest. However, applications of…

Most existing sensor-based monitoring frameworks presume that a large available labeled dataset is processed to train accurate detection models. However, in settings where personalization is necessary at deployment time to fine-tune the…

Deep learning models are often deployed in downstream tasks that the training procedure may not be aware of. For example, models solely trained to achieve accurate predictions may struggle to perform well on downstream tasks because…

While deep learning models often achieve high predictive accuracy, their predictions typically do not come with any provable guarantees on risk or reliability, which are critical for deployment in high-stakes applications. The framework of…

Given a limited labeling budget, active learning (AL) aims to sample the most informative instances from an unlabeled pool to acquire labels for subsequent model training. To achieve this, AL typically measures the informativeness of…

Empirical risk minimization often performs poorly when the distribution of the target domain differs from those of source domains. To address such potential distribution shifts, we develop an unsupervised domain adaptation approach that…

The remarkable performance of deep neural networks depends on the availability of massive labeled data. To alleviate the load of data annotation, active deep learning aims to select a minimal set of training points to be labelled which…

We study adapting trained object detectors to unseen domains manifesting significant variations of object appearance, viewpoints and backgrounds. Most current methods align domains by either using image or instance-level feature alignment…

In this paper, we explore bounds on the expected risk when using deep neural networks for supervised classification from an information theoretic perspective. Firstly, we introduce model risk and fitting error, which are derived from…

Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy. Most prior DA approaches leverage complicated and powerful deep neural…