Related papers: Attentive Feature Reuse for Multi Task Meta learni…

Many computer vision tasks address the problem of scene understanding and are naturally interrelated e.g. object classification, detection, scene segmentation, depth estimation, etc. We show that we can leverage the inherent relationships…

Attention-based learning for fine-grained image recognition remains a challenging task, where most of the existing methods treat each object part in isolation, while neglecting the correlations among them. In addition, the multi-stage or…

We propose an approach to Multitask Learning (MTL) to make deep learning models faster and lighter for applications in which multiple tasks need to be solved simultaneously, which is particularly useful in embedded, real-time systems. We…

The representations of the Earth's surface vary from one geographic region to another. For instance, the appearance of urban areas differs between continents, and seasonality influences the appearance of vegetation. To capture the diversity…

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…

Recent works have shown that deep neural networks benefit from multi-task learning by learning a shared representation across several related tasks. However, performance of such systems depend on relative weighting between various losses…

Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by integrating a meta-learning procedure that uses the…

This paper presents a novel optimization method for maximizing generalization over tasks in meta-learning. The goal of meta-learning is to learn a model for an agent adapting rapidly when presented with previously unseen tasks. Tasks are…

Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task…

In driving scenarios, automobile active safety systems are increasingly incorporating deep learning technology. These systems typically need to handle multiple tasks simultaneously, such as detecting fatigue driving and recognizing the…

In order to efficiently learn with small amount of data on new tasks, meta-learning transfers knowledge learned from previous tasks to the new ones. However, a critical challenge in meta-learning is the task heterogeneity which cannot be…

Neural network-based anomaly detection methods have shown to achieve high performance. However, they require a large amount of training data for each task. We propose a neural network-based meta-learning method for supervised anomaly…

In real-world applications, data do not reflect the ones commonly used for neural networks training, since they are usually few, unlabeled and can be available as a stream. Hence many existing deep learning solutions suffer from a limited…

Gradient-based meta-learning methods leverage gradient descent to learn the commonalities among various tasks. While previous such methods have been successful in meta-learning tasks, they resort to simple gradient descent during…

In this work we address task interference in universal networks by considering that a network is trained on multiple tasks, but performs one task at a time, an approach we refer to as "single-tasking multiple tasks". The network thus…

Medical image analysis typically includes several tasks such as enhancement, segmentation, and classification. Traditionally, these tasks are implemented using separate deep learning models for separate tasks, which is not efficient because…

More and more evidence has shown that strengthening layer interactions can enhance the representation power of a deep neural network, while self-attention excels at learning interdependencies by retrieving query-activated information.…

Multi-task learning (MTL) allows deep neural networks to learn from related tasks by sharing parameters with other networks. In practice, however, MTL involves searching an enormous space of possible parameter sharing architectures to find…

Gradient-based meta-learners such as MAML are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One important limitation of such frameworks is that they seek a common…

Imitation learning has gained immense popularity because of its high sample-efficiency. However, in real-world scenarios, where the trajectory distribution of most of the tasks dynamically shifts, model fitting on continuously aggregated…