Related papers: Hyperbolic Active Learning for Semantic Segmentati…

Active Learning (AL) has emerged as a powerful approach for minimizing labeling costs by selectively sampling the most informative data for neural network model development. Effective AL for large-scale vision-language models necessitates…

Unsupervised active learning has attracted increasing attention in recent years, where its goal is to select representative samples in an unsupervised setting for human annotating. Most existing works are based on shallow linear models by…

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,…

Robust generalization beyond training distributions remains a critical challenge for deep neural networks. This is especially pronounced in medical image analysis, where data is often scarce and covariate shifts arise from different…

Deep learning models have achieved remarkable success across various domains, yet their learned representations and decision-making processes remain largely opaque and hard to interpret. This work introduces HOLE (Homological Observation of…

Appearance-based gaze estimation, aiming to predict accurate 3D gaze direction from a single facial image, has made promising progress in recent years. However, most methods suffer significant performance degradation in cross-domain…

We consider active learning for binary classification in the agnostic pool-based setting. The vast majority of works in active learning in the agnostic setting are inspired by the CAL algorithm where each query is uniformly sampled from the…

Recent advances in representation learning have shown that hyperbolic geometry can offer a more expressive alternative to the Euclidean embeddings used in CLIP models, capturing hierarchical structures and leading to better-organized…

Domain Adaptation aiming to learn a transferable feature between different but related domains has been well investigated and has shown excellent empirical performances. Previous works mainly focused on matching the marginal feature…

Learning semantic segmentation requires pixel-wise annotations, which can be time-consuming and expensive. To reduce the annotation cost, we propose a superpixel-based active learning (AL) framework, which collects a dominant label per…

Training a deep neural model for semantic segmentation requires collecting a large amount of pixel-level labeled data. To alleviate the data scarcity problem presented in the real world, one could utilize synthetic data whose label is easy…

Learning good image representations that are beneficial to downstream tasks is a challenging task in computer vision. As such, a wide variety of self-supervised learning approaches have been proposed. Among them, contrastive learning has…

We present a novel region based active learning method for semantic image segmentation, called MetaBox+. For acquisition, we train a meta regression model to estimate the segment-wise Intersection over Union (IoU) of each predicted segment…

Hyperbolic geometry has been successfully applied in modeling brain cortical and subcortical surfaces with general topological structures. However such approaches, similar to other surface based brain morphology analysis methods, usually…

Generalizing deep neural networks to new target domains is critical to their real-world utility. In practice, it may be feasible to get some target data labeled, but to be cost-effective it is desirable to select a maximally-informative…

This paper introduces a novel approach that combines unsupervised active contour models with deep learning for robust and adaptive image segmentation. Indeed, traditional active contours, provide a flexible framework for contour evolution…

Domain adaptive semantic segmentation aims to train a model performing satisfactory pixel-level predictions on the target with only out-of-domain (source) annotations. The conventional solution to this task is to minimize the discrepancy…

Deep learning for medical imaging suffers from temporal and privacy-related restrictions on data availability. To still obtain viable models, continual learning aims to train in sequential order, as and when data is available. The main…

Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…

This paper studies active learning (AL) on graphs, whose purpose is to discover the most informative nodes to maximize the performance of graph neural networks (GNNs). Previously, most graph AL methods focus on learning node representations…