Related papers: Eliminating Catastrophic Interference with Biased …
Typical active learning strategies are designed for tasks, such as classification, with the assumption that the output space is mutually exclusive. The assumption that these tasks always have exactly one correct answer has resulted in the…
Visual question answering (VQA) is an interesting learning setting for evaluating the abilities and shortcomings of current systems for image understanding. Many of the recently proposed VQA systems include attention or memory mechanisms…
Visual Question Answering (VQA) concerns providing answers to Natural Language questions about images. Several deep neural network approaches have been proposed to model the task in an end-to-end fashion. Whereas the task is grounded in…
Conventional deep learning models have limited capacity in learning multiple tasks sequentially. The issue of forgetting the previously learned tasks in continual learning is known as catastrophic forgetting or interference. When the input…
In real-world scenarios we often need to perform multiple tasks simultaneously. Multi-Task Learning (MTL) is an adequate method to do so, but usually requires datasets labeled for all tasks. We propose a method that can leverage datasets…
Though beneficial for encouraging the Visual Question Answering (VQA) models to discover the underlying knowledge by exploiting the input-output correlation beyond image and text contexts, the existing knowledge VQA datasets are mostly…
Learning-based solutions for vision tasks require a large amount of labeled training data to ensure their performance and reliability. In single-task vision-based settings, inconsistency-based active learning has proven to be effective in…
Meta-learning is a powerful paradigm for tackling few-shot tasks. However, recent studies indicate that models trained with the whole-class training strategy can achieve comparable performance to those trained with meta-learning in few-shot…
The widespread success of deep learning models today is owed to the curation of extensive datasets significant in size and complexity. However, such models frequently pick up inherent biases in the data during the training process, leading…
QA models are faced with complex and open-ended contextual reasoning problems, but can often learn well-performing solution heuristics by exploiting dataset-specific patterns in their training data. These patterns, or "dataset artifacts",…
Despite the fast progress in training specialized models for various tasks, learning a single general model that works well for many tasks is still challenging for computer vision. Here we introduce multi-task self-training (MuST), which…
In this article, we propose a novel form of unsupervised learning, continual competitive memory (CCM), as well as a computational framework to unify related neural models that operate under the principles of competition. The resulting…
This work aims to address the long-established problem of learning diversified representations. To this end, we combine information-theoretic arguments with stochastic competition-based activations, namely Stochastic Local Winner-Takes-All…
Sharing knowledge between tasks is vital for efficient learning in a multi-task setting. However, most research so far has focused on the easier case where knowledge transfer is not harmful, i.e., where knowledge from one task cannot…
Multi-task learning has recently emerged as a promising solution for a comprehensive understanding of complex scenes. In addition to being memory-efficient, multi-task models, when appropriately designed, can facilitate the exchange of…
Existing visual model-based reinforcement learning (MBRL) algorithms with observation reconstruction often suffer from information conflicts, making it difficult to learn compact representations and hence result in less robust policies,…
Multi-task learning aims to acquire a set of functions, either regressors or classifiers, that perform well for diverse tasks. At its core, the idea behind multi-task learning is to exploit the intrinsic similarity across data sources to…
In the present work we propose a Deep Feed Forward network architecture which can be trained according to a sequential learning paradigm, where tasks of increasing difficulty are learned sequentially, yet avoiding catastrophic forgetting.…
Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optimal ability to learn…
Attention mechanism has gained huge popularity due to its effectiveness in achieving high accuracy in different domains. But attention is opportunistic and is not justified by the content or usability of the content. Transformer like…