Related papers: Certainty Pooling for Multiple Instance Learning

Confident prediction is highly relevant in machine learning; for example, in applications such as medical diagnoses, wrong prediction can be fatal. For classification, there already exist procedures that allow to not classify data when the…

We propose a new problem formulation which is similar to, but more informative than, the binary multiple-instance learning problem. In this setting, we are given groups of instances (described by feature vectors) along with estimates of the…

In this paper we address imbalanced binary classification (IBC) tasks. Applying resampling strategies to balance the class distribution of training instances is a common approach to tackle these problems. Many state-of-the-art methods find…

Overfitting & underfitting and stable training are an important challenges in machine learning. Current approaches for these issues are mixup, SamplePairing and BC learning. In our work, we state the hypothesis that mixing many images…

Overconfidence and underconfidence in machine learning classifiers is measured by calibration: the degree to which the probabilities predicted for each class match the accuracy of the classifier on that prediction. How one measures…

The increasing use of machine-learning (ML) enabled systems in critical tasks fuels the quest for novel verification and validation techniques yet grounded in accepted system assurance principles. In traditional system development,…

The purpose of training neural networks is to achieve high generalization performance on unseen inputs. However, when trained on imbalanced datasets, a model's prediction tends to favor majority classes over minority classes, leading to…

We present a new approach for transferring knowledge from groups to individuals that comprise them. We evaluate our method in text, by inferring the ratings of individual sentences using full-review ratings. This approach, which combines…

Training high-quality instance segmentation models requires an abundance of labeled images with instance masks and classifications, which is often expensive to procure. Active learning addresses this challenge by striving for optimum…

We present a comprehensive study of the use of generative modeling approaches for Multiple-Instance Learning (MIL) problems. In MIL a learner receives training instances grouped together into bags with labels for the bags only (which might…

Multiple Instance Learning (MIL) and transformers are increasingly popular in histopathology Whole Slide Image (WSI) classification. However, unlike human pathologists who selectively observe specific regions of histopathology tissues under…

Selective classification is a powerful tool for automated decision-making in high-risk scenarios, allowing classifiers to act only when confident and abstain when uncertainty is high. Given a target accuracy, our goal is to minimize…

Multi-task learning (MTL) is to learn one single model that performs multiple tasks for achieving good performance on all tasks and lower cost on computation. Learning such a model requires to jointly optimize losses of a set of tasks with…

Multi-Instance Learning (MIL) has shown impressive performance for histopathology whole slide image (WSI) analysis using bags or pseudo-bags. It involves instance sampling, feature representation, and decision-making. However, existing…

Self-learning is a classical approach for learning with both labeled and unlabeled observations which consists in giving pseudo-labels to unlabeled training instances with a confidence score over a predetermined threshold. At the same time,…

Whole slide image (WSI) classification is a fundamental task for the diagnosis and treatment of diseases; but, curation of accurate labels is time-consuming and limits the application of fully-supervised methods. To address this, multiple…

Many prediction tasks contain uncertainty. In some cases, uncertainty is inherent in the task itself. In future prediction, for example, many distinct outcomes are equally valid. In other cases, uncertainty arises from the way data is…

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…

This work addresses classification of unknown binaries executed in sandbox by modeling their interaction with system resources (files, mutexes, registry keys and communication with servers over the network) and error messages provided by…

To alleviate the burden of gathering detailed expert annotations when training deep neural networks, we propose a weakly supervised learning approach to recognize metastases in microscopic images of breast lymph nodes. We describe an…