Related papers: Calibrating Histopathology Image Classifiers using…

Prior work has explored directly regularizing the output distributions of probabilistic models to alleviate peaky (i.e. over-confident) predictions, a common sign of overfitting. This class of techniques, of which label smoothing is one,…

The colorectal polyps classification is a critical clinical examination. To improve the classification accuracy, most computer-aided diagnosis algorithms recognize colorectal polyps by adopting Narrow-Band Imaging (NBI). However, the NBI…

Manual annotation of medical images is a labor-intensive and time-consuming process, posing a significant bottleneck in the development and deployment of robust medical imaging AI systems. This paper introduces a novel hands-free Human-AI…

In this paper, we study the problem of learning image classification models with label noise. Existing approaches depending on human supervision are generally not scalable as manually identifying correct or incorrect labels is…

In medical imaging, inter-observer variability among radiologists often introduces label uncertainty, particularly in modalities where visual interpretation is subjective. Lung ultrasound (LUS) is a prime example-it frequently presents a…

Differentiation of colorectal polyps is an important clinical examination. A computer-aided diagnosis system is required to assist accurate diagnosis from colonoscopy images. Most previous studies at-tempt to develop models for polyp…

Few-shot learning is an established topic in natural images for years, but few work is attended to histology images, which is of high clinical value since well-labeled datasets and rare abnormal samples are expensive to collect. Here, we…

Recently, there has been a growing interest in research concerning document image analysis and recognition in photographic scenarios. However, the lack of labeled datasets for this emerging challenge poses a significant obstacle, as manual…

A ubiquitous challenge in machine learning is the problem of domain generalisation. This can exacerbate bias against groups or labels that are underrepresented in the datasets used for model development. Model bias can lead to unintended…

We motivate weakly supervised learning as an effective learning paradigm for problems where curating perfectly annotated datasets is expensive and may require domain expertise such as fine-grained classification. We focus on Partial Label…

Deep neural networks (DNNs) have been widely applied in medical image classification and achieve remarkable classification performance. These achievements heavily depend on large-scale accurately annotated training data. However, label…

The success of deep learning methods relies on the availability of well-labeled large-scale datasets. However, for medical images, annotating such abundant training data often requires experienced radiologists and consumes their limited…

Consider a multi-class labelling problem, where the labels can take values in $[k]$, and a predictor predicts a distribution over the labels. In this work, we study the following foundational question: Are there notions of multi-class…

Data augmentation has been pivotal in successfully training deep learning models on classification tasks over the past decade. An important subclass of data augmentation techniques - which includes both label smoothing and Mixup - involves…

Safe artificial intelligence for perception tasks remains a major challenge, partly due to the lack of data with high-quality labels. Annotations themselves are subject to aleatoric and epistemic uncertainty, which is typically ignored…

The label noise transition matrix, denoting the transition probabilities from clean labels to noisy labels, is crucial for designing statistically robust solutions. Existing estimators for noise transition matrices, e.g., using either…

Weakly supervised image segmentation with image-level labels has drawn attention due to the high cost of pixel-level annotations. Traditional methods using Class Activation Maps (CAMs) often highlight only the most discriminative regions,…

Variability in medical image segmentation, arising from annotator preferences, expertise, and their choice of tools, has been well documented. While the majority of multi-annotator segmentation approaches focus on modeling…

Model calibration seeks to ensure that models produce confidence scores that accurately reflect the true likelihood of their predictions being correct. However, existing calibration approaches are fundamentally tied to datasets of one-hot…

Semi-supervised learning has been employed to alleviate the need for extensive labeled data for histopathology image segmentation, but existing methods struggle with noisy pseudo-labels due to ambiguous gland boundaries and morphological…