Related papers: One Model To Learn Them All

The recent surge in performance for image analysis of digitised pathology slides can largely be attributed to the advances in deep learning. Deep models can be used to initially localise various structures in the tissue and hence facilitate…

Neural network models can now recognise images, understand text, translate languages, and play many human games at human or superhuman levels. These systems are highly abstracted, but are inspired by biological brains and use only…

Healthcare clinics regularly encounter dynamic data that changes due to variations in patient populations, treatment policies, medical devices, and emerging disease patterns. Deep learning models can suffer from catastrophic forgetting when…

Deep learning architectures are showing great promise in various computer vision domains including image classification, object detection, event detection and action recognition. In this study, we investigate various aspects of…

While language tasks are naturally expressed in a single, unified, modeling framework, i.e., generating sequences of tokens, this has not been the case in computer vision. As a result, there is a proliferation of distinct architectures and…

Deep learning relies on a very specific kind of neural networks: those superposing several neural layers. In the last few years, deep learning achieved major breakthroughs in many tasks such as image analysis, speech recognition, natural…

We introduce a deep multitask architecture to integrate multityped representations of multimodal objects. This multitype exposition is less abstract than the multimodal characterization, but more machine-friendly, and thus is more precise…

Existing methods for vision-and-language learning typically require designing task-specific architectures and objectives for each task. For example, a multi-label answer classifier for visual question answering, a region scorer for…

Transfer learning has recently become the dominant paradigm of machine learning. Pre-trained models fine-tuned for downstream tasks achieve better performance with fewer labelled examples. Nonetheless, it remains unclear how to develop…

Existing deep architectures cannot operate on very large signals such as megapixel images due to computational and memory constraints. To tackle this limitation, we propose a fully differentiable end-to-end trainable model that samples and…

Availability of labelled data is the major obstacle to the deployment of deep learning algorithms for computer vision tasks in new domains. The fact that many frameworks adopted to solve different tasks share the same architecture suggests…

In this report, we combine the idea of Wide ResNets and transfer learning to optimize the architecture of deep neural networks. The first improvement of the architecture is the use of all layers as information source for the last layer.…

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…

Recent deep learning models can efficiently combine inputs from different modalities (e.g., images and text) and learn to align their latent representations, or to translate signals from one domain to another (as in image captioning, or…

Recently, neural approaches to coherence modeling have achieved state-of-the-art results in several evaluation tasks. However, we show that most of these models often fail on harder tasks with more realistic application scenarios. In…

Modern discriminative predictors have been shown to match natural intelligences in specific perceptual tasks in image classification, object and part detection, boundary extraction, etc. However, a major advantage that natural intelligences…

We describe a DNN for video classification and captioning, trained end-to-end, with shared features, to solve tasks at different levels of granularity, exploring the link between granularity in a source task and the quality of learned…

Our ability to use deep learning approaches to decipher neural activity would likely benefit from greater scale, in terms of both model size and datasets. However, the integration of many neural recordings into one unified model is…

Deep learning has shown promising results on many machine learning tasks but DL models are often complex networks with large number of neurons and layers, and recently, complex layer structures known as building blocks. Finding the best…

Deep Learning refers to a set of machine learning techniques that utilize neural networks with many hidden layers for tasks, such as image classification, speech recognition, language understanding. Deep learning has been proven to be very…