The accuracies for many pattern recognition tasks have increased rapidly year by year,
achieving or even outperforming human performance. From the perspective of accuracy …

While deep learning and deep reinforcement learning (RL) systems have demonstrated
impressive results in domains such as image classification, game playing, and robotic …

In multi-task learning, multiple tasks are solved jointly, sharing inductive bias between them.
Multi-task learning is inherently a multi-objective problem because different tasks may …

Many computer vision applications require solving multiple tasks in real-time. A neural
network can be trained to solve multiple tasks simultaneously using multi-task learning. This …

Do visual tasks have a relationship, or are they unrelated? For instance, could having
surface normals simplify estimating the depth of an image? Intuition answers these …

This work presents a method for adapting a single, fixed deep neural network to multiple
tasks without affecting performance on already learned tasks. By building upon ideas from …

There is a growing interest in learning data representations that work well for many different
types of problems and data. In this paper, we look in particular at the task of learning a single …

Abstract Traditional methods for Unsupervised Domain Adaptation (UDA) targeting semantic
segmentation exploit information common to the source and target domains, using both …

We propose dynamic task prioritization for multitask learning. This allows a model to
dynamically prioritize difficult tasks during training, where difficulty is inversely proportional …

A practical limitation of deep neural networks is their high degree of specialization to a
single task and visual domain. In complex applications such as mobile platforms, this …