Related papers: Active Expansion Sampling for Learning Feasible Do…

It is now practically the norm for data to be very high dimensional in areas such as genetics, machine vision, image analysis and many others. When analyzing such data, parametric models are often too inflexible while nonparametric…

Distributed multi-party learning provides an effective approach for training a joint model with scattered data under legal and practical constraints. However, due to the quagmire of a skewed distribution of data labels across participants…

This paper proposes a novel active boundary loss for semantic segmentation. It can progressively encourage the alignment between predicted boundaries and ground-truth boundaries during end-to-end training, which is not explicitly enforced…

Bayesian optimization is normally performed within fixed variable bounds. In cases like hyperparameter tuning for machine learning algorithms, setting the variable bounds is not trivial. It is hard to guarantee that any fixed bounds will…

We investigate active learning in the context of deep neural network models for change detection and map updating. Active learning is a natural choice for a number of remote sensing tasks, including the detection of local surface changes:…

This paper presents methods for improving automated essay scoring with techniques that address the computational trade-offs of self-attention and document length. To make Automated Essay Scoring (AES) more useful to practitioners,…

Accurate segmentation of tissue in histopathological images can be very beneficial for defining regions of interest (ROI) for streamline of diagnostic and prognostic tasks. Still, adapting to different domains is essential for…

Face anti-spoofing (FAS) is an indispensable and widely used module in face recognition systems. Although high accuracy has been achieved, a FAS system will never be perfect due to the non-stationary applied environments and the potential…

Segmentation is essential for medical image analysis tasks such as intervention planning, therapy guidance, diagnosis, treatment decisions. Deep learning is becoming increasingly prominent for segmentation, where the lack of annotations,…

Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. These predictions can then be deferred to humans for further evaluation. As an everlasting challenge for machine learning, in many…

Dense random sampling and surfacing of shapes encoded via implicit occupancy functions (OFs) are critical elements of many applications. Existing methods largely provide either one or the other of random sampling or mesh surfaces: ray…

Active learning aims to develop label-efficient algorithms by sampling the most representative queries to be labeled by an oracle. We describe a pool-based semi-supervised active learning algorithm that implicitly learns this sampling…

How should we gather information to make effective decisions? We address Bayesian active learning and experimental design problems, where we sequentially select tests to reduce uncertainty about a set of hypotheses. Instead of minimizing…

Data subsampling has become widely recognized as a tool to overcome computational and economic bottlenecks in analyzing massive datasets. We contribute to the development of adaptive design for estimation of finite population…

Active learning (AL) has found wide applications in medical image segmentation, aiming to alleviate the annotation workload and enhance performance. Conventional uncertainty-based AL methods, such as entropy and Bayesian, often rely on an…

Deep learning models in medical imaging often encounter challenges when adapting to new clinical settings unseen during training. Test-time adaptation offers a promising approach to optimize models for these unseen domains, yet its…

The objective of Continual Test-time Domain Adaptation (CTDA) is to gradually adapt a pre-trained model to a sequence of target domains without accessing the source data. This paper proposes a Dynamic Sample Selection (DSS) method for CTDA.…

We propose associative domain adaptation, a novel technique for end-to-end domain adaptation with neural networks, the task of inferring class labels for an unlabeled target domain based on the statistical properties of a labeled source…

We present a general-purpose active learning scheme for data in metric spaces. The algorithm maintains a collection of neighborhoods of different sizes and uses label queries to identify those that have a strong bias towards one particular…

In this work, we consider the problem of identifying an unknown linear dynamical system given a finite hypothesis class. In particular, we analyze the effect of the excitation input on the sample complexity of identifying the true system…