Related papers: Multi-Task Anti-Causal Learning for Reconstructing…

Multi-task learning (MTL) is an active field in deep learning in which we train a model to jointly learn multiple tasks by exploiting relationships between the tasks. It has been shown that MTL helps the model share the learned features…

Foundational vision models, such as the Segment Anything Model (SAM), have achieved significant breakthroughs through extensive pre-training on large-scale visual datasets. Despite their general success, these models may fall short in…

Multitask learning assumes that models capable of learning from multiple tasks can achieve better quality and efficiency via knowledge transfer, a key feature of human learning. Though, state of the art ML models rely on high customization…

Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies.…

We propose a Multi-Task Learning (MTL) paradigm based deep neural network architecture, called MTCNet (Multi-Task Crowd Network) for crowd density and count estimation. Crowd count estimation is challenging due to the non-uniform scale…

We present an online multi-task learning approach for adaptive nonlinear control, which we call Online Meta-Adaptive Control (OMAC). The goal is to control a nonlinear system subject to adversarial disturbance and unknown…

Multitask deep learning has been applied to patient outcome prediction from text, taking clinical notes as input and training deep neural networks with a joint loss function of multiple tasks. However, the joint training scheme of multitask…

Multi-Task Learning is a learning paradigm that uses correlated tasks to improve performance generalization. A common way to learn multiple tasks is through the hard parameter sharing approach, in which a single architecture is used to…

Deep neural networks have achieved impressive performance in various areas, but they are shown to be vulnerable to adversarial attacks. Previous works on adversarial attacks mainly focused on the single-task setting. However, in real…

Recent advances in deep forecasting models have achieved remarkable performance, yet most approaches still struggle to provide both accurate predictions and interpretable insights into temporal dynamics. This paper proposes CaReTS, a novel…

Linear residualization is a common practice for confounding adjustment in machine learning (ML) applications. Recently, causality-aware predictive modeling has been proposed as an alternative causality-inspired approach for adjusting for…

Recently, self-supervised learning methods based on masked latent prediction have proven to encode input data into powerful representations. However, during training, the learned latent space can be further transformed to extract…

Large transformer models, trained on diverse datasets, have demonstrated impressive few-shot performance on previously unseen tasks without requiring parameter updates. This capability has also been explored in Reinforcement Learning (RL),…

We propose a novel multi-task learning architecture, which allows learning of task-specific feature-level attention. Our design, the Multi-Task Attention Network (MTAN), consists of a single shared network containing a global feature pool,…

Human communication is multimodal in nature; it is through multiple modalities such as language, voice, and facial expressions, that opinions and emotions are expressed. Data in this domain exhibits complex multi-relational and temporal…

Anticipating future actions is a highly challenging task due to the diversity and scale of potential future actions; yet, information from different modalities help narrow down plausible action choices. Each modality can provide diverse and…

We explore the usage of meta-learning to derive the causal direction between variables by optimizing over a measure of distribution simplicity. We incorporate a stochastic graph representation which includes latent variables and allows for…

While tasks could come with varying the number of instances and classes in realistic settings, the existing meta-learning approaches for few-shot classification assume that the number of instances per task and class is fixed. Due to such…

Single-task learning in artificial neural networks will be able to learn the model very well, and the benefits brought by transferring knowledge thus become limited. In this regard, when the number of tasks increases (e.g., semantic…

The research addresses sensor task management for radar systems, focusing on efficiently searching and tracking multiple targets using reinforcement learning. The approach develops a 3D simulation environment with an active electronically…