相关论文: A bag-to-class divergence approach to multiple-ins…

As a widely used weakly supervised learning scheme, modern multiple instance learning (MIL) models achieve competitive performance at the bag level. However, instance-level prediction, which is essential for many important applications,…

Learning from Label Proportion (LLP) is a weakly supervised learning scenario in which training data is organized into predefined bags of instances, disclosing only the class label proportions per bag. This paradigm is essential for user…

Multi-instance partial-label learning (MIPL) is an emerging learning framework where each training sample is represented as a multi-instance bag associated with a candidate label set. Existing MIPL algorithms often overlook the margins for…

When supervising an object detector with weakly labeled data, most existing approaches are prone to trapping in the discriminative object parts, e.g., finding the face of a cat instead of the full body, due to lacking the supervision on the…

In multi-label classification, the main focus has been to develop ways of learning the underlying dependencies between labels, and to take advantage of this at classification time. Developing better feature-space representations has been…

Weakly supervised instance labeling using only image-level labels, in lieu of expensive fine-grained pixel annotations, is crucial in several applications including medical image analysis. In contrast to conventional instance segmentation…

In many real-world tasks, particularly those involving data objects with complicated semantics such as images and texts, one object can be represented by multiple instances and simultaneously be associated with multiple labels. Such tasks…

In many applications in biology, engineering and economics, identifying similarities and differences between distributions of data from complex processes requires comparing finite categorical samples of discrete counts. Statistical…

We study the problem of learning from aggregate observations where supervision signals are given to sets of instances instead of individual instances, while the goal is still to predict labels of unseen individuals. A well-known example is…

Classification is a major tool of statistics and machine learning. A classification method first processes a training set of objects with given classes (labels), with the goal of afterward assigning new objects to one of these classes. When…

Learning from Label Proportions (LLP) is a learning problem where only aggregate level labels are available for groups of instances, called bags, during training, and the aim is to get the best performance at the instance-level on the test…

Classification and differentiation of small pathological objects may greatly vary among human raters due to differences in training, expertise and their consistency over time. In a radiological setting, objects commonly have high…

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…

Deep learning classification models for medical image analysis often perform well on data from scanners that were used during training. However, when these models are applied to data from different vendors, their performance tends to drop…

In-context learning (ICL) refers to the process of adding a small number of localized examples from a training set of labelled data to an LLM's prompt with an objective to effectively control the generative process seeking to improve the…

Multi-label Recognition (MLR) involves the identification of multiple objects within an image. To address the additional complexity of this problem, recent works have leveraged information from vision-language models (VLMs) trained on large…

Estimating the Kullback-Leibler (KL) divergence between two distributions given samples from them is well-studied in machine learning and information theory. Motivated by considerations of multi-group fairness, we seek KL divergence…

Multiple instance (MI) learning with a convolutional neural network enables end-to-end training in the presence of weak image-level labels. We propose a new method for aggregating predictions from smaller regions of the image into an…

In the task of Learning from Label Proportions (LLP), a model is trained on groups (a.k.a bags) of instances and their corresponding label proportions to predict labels for individual instances. LLP has been applied pre-dominantly on two…

Training generative models to sample from unnormalized density functions is an important and challenging task in machine learning. Traditional training methods often rely on the reverse Kullback-Leibler (KL) divergence due to its…