Related papers: Disentangling Shared and Task-Specific Representat…

Multimodal representation learning is commonly built on a shared-private decomposition, treating latent information as either common to all modalities or specific to one. This binary view is often inadequate: many factors are shared by only…

This paper studies task-oriented, otherwise known as goal-oriented, communications, in a setting where a transmitter communicates with multiple receivers, each with its own task to complete on a dataset, e.g., images, available at the…

We investigate multi-task learning approaches that use a shared feature representation for all tasks. To better understand the transfer of task information, we study an architecture with a shared module for all tasks and a separate output…

Machine learning has a recognised need for large amounts of annotated data. Due to the high cost of expert annotations, crowdsourcing, where non-experts are asked to label or outline images, has been proposed as an alternative. Although…

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint…

Multi-task learning solves multiple correlated tasks. However, conflicts may exist between them. In such circumstances, a single solution can rarely optimize all the tasks, leading to performance trade-offs. To arrive at a set of optimized…

Recent randomised clinical trials have shown that patients with ischaemic stroke {due to occlusion of a large intracranial blood vessel} benefit from endovascular thrombectomy. However, predicting outcome of treatment in an individual…

Multimodal data fusion is a key approach for enhancing diagnosis in medical applications. We propose an asymmetric fusion strategy starting from a primary modality and integrating secondary modalities by disentangling shared and…

To enhance the interpretability of multimodal unified representations, many studies have focused on discrete unified representations. These efforts typically start with contrastive learning and gradually extend to the disentanglement of…

We propose an end-to-end Multitask Learning Transformer framework, named MulT, to simultaneously learn multiple high-level vision tasks, including depth estimation, semantic segmentation, reshading, surface normal estimation, 2D keypoint…

Multi-Task Learning (MTL) is a framework, where multiple related tasks are learned jointly and benefit from a shared representation space, or parameter transfer. To provide sufficient learning support, modern MTL uses annotated data with…

The current cancer treatment practice collects multimodal data, such as radiology images, histopathology slides, genomics and clinical data. The importance of these data sources taken individually has fostered the recent raise of radiomics…

Multimodal fusion leverages information across modalities to learn better feature representations with the goal of improving performance in fusion-based tasks. However, multimodal datasets, especially in medical settings, are typically…

Purpose: The integration of multimodal imaging into operating rooms paves the way for comprehensive surgical scene understanding. In ophthalmic surgery, by now, two complementary imaging modalities are available: operating microscope (OPMI)…

Multi-task learning aims to learn multiple tasks jointly by exploiting their relatedness to improve the generalization performance for each task. Traditionally, to perform multi-task learning, one needs to centralize data from all the tasks…

One of the main arguments behind studying disentangled representations is the assumption that they can be easily reused in different tasks. At the same time finding a joint, adaptable representation of data is one of the key challenges in…

Merging models fine-tuned for different tasks into a single unified model has become an increasingly important direction for building versatile, efficient multi-task systems. Existing approaches predominantly rely on parameter interpolation…

Estimating individual-level treatment effect from observational data is a fundamental problem in causal inference and has attracted increasing attention in the fields of education, healthcare, and public policy.In this work, we concentrate…

Traffic scene recognition, which requires various visual classification tasks, is a critical ingredient in autonomous vehicles. However, most existing approaches treat each relevant task independently from one another, never considering the…

Multimodal meta-learning is a recent problem that extends conventional few-shot meta-learning by generalizing its setup to diverse multimodal task distributions. This setup makes a step towards mimicking how humans make use of a diverse set…