Related papers: Information Bottleneck-based Causal Attention for …

In-context learning (ICL) is an emerging capability of large autoregressive language models where a few input-label demonstrations are appended to the input to enhance the model's understanding of downstream NLP tasks, without directly…

Medical image segmentation, or computing voxelwise semantic masks, is a fundamental yet challenging task to compute a voxel-level semantic mask. To increase the ability of encoder-decoder neural networks to perform this task across large…

Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative…

Bridging the gap between internal and external validity is crucial for heterogeneous treatment effect estimation. Randomised controlled trials (RCTs), favoured for their internal validity due to randomisation, often encounter challenges in…

Human Multimodal Language Understanding (MLU) aims to infer human intentions by integrating related cues from heterogeneous modalities. Existing works predominantly follow a ``learning to attend" paradigm, which maximizes mutual information…

We propose a new method for learning image attention masks in a semi-supervised setting based on the Information Bottleneck principle. Provided with a set of labeled images, the mask generation model is minimizing mutual information between…

Continual learning is essential for medical image classification systems to adapt to dynamically evolving clinical environments. The integration of multimodal information can significantly enhance continual learning of image classes.…

Multimodal multilabel classification (MMC) is a challenging task that aims to design a learning algorithm to handle two data sources, the image and text, and learn a comprehensive semantic feature presentation across the modalities. In this…

Multimodal in-context learning (ICL) is becoming a key capability that allows large vision-language models (LVLMs) to adapt to novel tasks without parameter updates, which expands their usefulness in many real-world applications. However,…

The objective of multimodal information fusion is to mathematically analyze information carried in different sources and create a new representation which will be more effectively utilized in pattern recognition and other multimedia…

Multi-Label Remote Sensing Image Classification (MLRSIC) has received increasing research interest. Taking the cooccurrence relationship of multiple labels as additional information helps to improve the performance of this task. Current…

Semi-supervised learning has become increasingly popular in medical image segmentation due to its ability to leverage large amounts of unlabeled data to extract additional information. However, most existing semi-supervised segmentation…

Learning medical visual representations directly from paired radiology reports has become an emerging topic in representation learning. However, existing medical image-text joint learning methods are limited by instance or local supervision…

We propose a novel architecture and method of explainable classification with Concept Bottleneck Models (CBMs). While SOTA approaches to Image Classification task work as a black box, there is a growing demand for models that would provide…

The bottom-up saliency, an early stage of humans' visual attention, can be considered as a binary classification problem between center and surround classes. Discriminant power of features for the classification is measured as mutual…

Automatic International Classification of Diseases (ICD) coding is defined as a kind of text multi-label classification problem, which is difficult because the number of labels is very large and the distribution of labels is unbalanced. The…

Multi-label image recognition is a challenging computer vision task of practical use. Progresses in this area, however, are often characterized by complicated methods, heavy computations, and lack of intuitive explanations. To effectively…

Multi-label classification (MLC) is a prediction task where each sample can have more than one label. We propose a novel contrastive learning boosted multi-label prediction model based on a Gaussian mixture variational autoencoder…

Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture…

Causal learning has long concerned itself with the accurate recovery of underlying causal mechanisms. Such causal modelling enables better explanations of out-of-distribution data. Prior works on causal learning assume that the high-level…