Related papers: Robust Multi-instance Learning with Stable Instanc…
Deep neural networks, including transformers and convolutional neural networks, have significantly improved multivariate time series classification (MTSC). However, these methods often rely on supervised learning, which does not fully…
Multiple instance learning (MIL) is the standard approach for whole-slide image (WSI) classification and survival prediction, where attention-based models ag gregate patch features into slide-level predictions. These models treat attention…
Machine learning models have become integral to many fields, but their reliability, defined as producing dependable, trustworthy, and domain-consistent predictions, remains a critical concern. Multiple Instance Learning (MIL) models…
The presence of label noise often misleads the training of deep neural networks. Departing from the recent literature which largely assumes the label noise rate is only determined by the true label class, the errors in human-annotated…
The quantity and the quality of the training labels are central problems in high-resolution land-cover mapping with machine-learning-based solutions. In this context, weak labels can be gathered in large quantities by leveraging on existing…
The aim of Active Learning is to select the most informative samples from an unlabelled set of data. This is useful in cases where the amount of data is large and labelling is expensive, such as in machine vision or medical imaging. Two…
Our goal is to improve reliability of Machine Learning (ML) systems deployed in the wild. ML models perform exceedingly well when test examples are similar to train examples. However, real-world applications are required to perform on any…
The recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods…
Missing data in supervised learning is well-studied, but the specific issue of missing labels during model evaluation has been overlooked. Ignoring samples with missing values, a common solution, can introduce bias, especially when data is…
Learning with limited labelled data, such as prompting, in-context learning, fine-tuning, meta-learning or few-shot learning, aims to effectively train a model using only a small amount of labelled samples. However, these approaches have…
The current dominant paradigm when building a machine learning model is to iterate over a dataset over and over until convergence. Such an approach is non-incremental, as it assumes access to all images of all categories at once. However,…
Weakly supervised multiple instance learning (MIL) is a challenging task given that only bag-level labels are provided, while each bag typically contains multiple instances. This topic has been extensively studied in histopathological image…
Data scarcity and weak supervision continue to limit the performance of machine learning models in many real-world applications, such as mammography, where Multiple Instance Learning (MIL) often offers the best formulation. While recent…
Learning accurate object detectors often requires large-scale training data with precise object bounding boxes. However, labeling such data is expensive and time-consuming. As the crowd-sourcing labeling process and the ambiguities of the…
The basic underlying assumption of machine learning (ML) models is that the training and test data are sampled from the same distribution. However, in daily practice, this assumption is often broken, i.e. the distribution of the test data…
In a standard multi-output classification scenario, both features and labels of training data are partially observed. This challenging issue is widely witnessed due to sensor or database failures, crowd-sourcing and noisy communication…
Deep Neural Networks inherit spurious correlations embedded in training data and hence may fail to predict desired labels on unseen domains (or environments), which have different distributions from the domain used in training. Invariance…
In the context of Multi Instance Learning, we analyze the Single Instance (SI) learning objective. We show that when the data is unbalanced and the family of classifiers is sufficiently rich, the SI method is a useful learning algorithm. In…
Multimodal learning integrates complementary information from different modalities such as image, text, and audio to improve model performance, but its success relies on large-scale labeled data, which is costly to obtain. Active learning…
Standard supervised learning breaks down under data distribution shift. However, the principle of independent causal mechanisms (ICM, Peters et al. (2017)) can turn this weakness into an opportunity: one can take advantage of distribution…