Related papers: ARM: A Confidence-Based Adversarial Reweighting Mo…
Sharpness-Aware Minimization (SAM) was introduced to improve generalization by seeking flat minima, yet it also exhibits robustness to label noise, a phenomenon that remains only partially understood. Prior work has mainly attributed this…
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…
Active Learning (AL) promises to reduce annotation cost by prioritizing informative samples, yet its reliability is undermined when labels are noisy or when the data distribution shifts. In practice, annotators make mistakes, rare…
The escalating threat of weapon-related violence necessitates automated detection systems capable of pixel-level precision for accurate threat assessment in real-time security applications. Traditional weapon detection approaches rely on…
Recently, methods based on Convolutional Neural Networks (CNN) achieved impressive success in semantic segmentation tasks. However, challenges such as the class imbalance and the uncertainty in the pixel-labeling process are not completely…
Reliable classification and detection of certain medical conditions, in images, with state-of-the-art semantic segmentation networks, require vast amounts of pixel-wise annotation. However, the public availability of such datasets is…
Deep neural networks (DNNs) have achieved great success in a wide variety of medical image analysis tasks. However, these achievements indispensably rely on the accurately-annotated datasets. If with the noisy-labeled images, the training…
Noisy partial label learning (noisy PLL) is an important branch of weakly supervised learning. Unlike PLL where the ground-truth label must conceal in the candidate label set, noisy PLL relaxes this constraint and allows the ground-truth…
Semi-supervised learning has attracted much attention due to its less dependence on acquiring abundant annotations from experts compared to fully supervised methods, which is especially important for medical image segmentation which…
Obtaining large-scale medical data, annotated or unannotated, is challenging due to stringent privacy regulations and data protection policies. In addition, annotating medical images requires that domain experts manually delineate…
Incremental learning of semantic segmentation has emerged as a promising strategy for visual scene interpretation in the open- world setting. However, it remains challenging to acquire novel classes in an online fashion for the segmentation…
The advancement of artificial intelligence generated content (AIGC) has created a pressing need for robust image watermarking that can withstand both conventional signal processing and novel semantic editing attacks. Current deep…
Adaptive Mesh Refinement (AMR) enhances the Finite Element Method, an important technique for simulating complex problems in engineering, by dynamically refining mesh regions, enabling a favorable trade-off between computational speed and…
Deep learning models for semantic segmentation rely on expensive, large-scale, manually annotated datasets. Labelling is a tedious process that can take hours per image. Automatically annotating video sequences by propagating sparsely…
Post-hoc saliency methods are widely used to interpret deep neural networks, but their faithfulness is difficult to evaluate reliably. Existing evaluations mask features according to saliency-induced feature ordering and measure performance…
Training neural networks using limited annotations is an important problem in the medical domain. Deep Neural Networks (DNNs) typically require large, annotated datasets to achieve acceptable performance which, in the medical domain, are…
Pixel-level crack segmentation is widely studied due to its high impact on building and road inspections. While recent studies have made significant improvements in accuracy, they typically heavily depend on pixel-level crack annotations,…
The extraction of multi-attribute objects from the deep web is the bridge between the unstructured web and structured data. Existing approaches either induce wrappers from a set of human-annotated pages or leverage repeated structures on…
Semantic segmentation requires large amounts of pixel-wise annotations to learn accurate models. In this paper, we present a video prediction-based methodology to scale up training sets by synthesizing new training samples in order to…
Stream-based active learning (AL) is an efficient training data collection method, and it is used to reduce human annotation cost required in machine learning. However, it is difficult to say that the human cost is low enough because most…