Related papers: Learning Discrete Representations via Information …

We propose a novel explanation method that explains the decisions of a deep neural network by investigating how the intermediate representations at each layer of the deep network were refined during the training process. This way we can a)…

Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems. In this paper, we empirically show data augmentation might introduce noisy augmented examples and consequently hurt the performance on…

Generalized linear mixed models are useful in studying hierarchical data with possibly non-Gaussian responses. However, the intractability of likelihood functions poses challenges for estimation. We develop a new method suitable for this…

Learning latent representations of nodes in graphs is an important and ubiquitous task with widespread applications such as link prediction, node classification, and graph visualization. Previous methods on graph representation learning…

Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…

Feature representations, both hand-designed and learned ones, are often hard to analyze and interpret, even when they are extracted from visual data. We propose a new approach to study image representations by inverting them with an…

Data assimilation is a central problem in many geophysical applications, such as weather forecasting. It aims to estimate the state of a potentially large system, such as the atmosphere, from sparse observations, supplemented by prior…

Although well-trained deep neural networks have shown remarkable performance on numerous tasks, they rapidly forget what they have learned as soon as they begin to learn with additional data with the previous data stop being provided. In…

Imitation learning is widely used for learning to act in complex environments. While pure neural-based methods handle high dimensional data effectively, they suffer from the requirement of large number of samples and are prone to…

Deep learning often faces the challenge of efficiently processing dynamic inputs, such as sensor data or user inputs. For example, an AI writing assistant is required to update its suggestions in real time as a document is edited.…

Integrating functions on discrete domains into neural networks is key to developing their capability to reason about discrete objects. But, discrete domains are (1) not naturally amenable to gradient-based optimization, and (2) incompatible…

Previous attempts for data augmentation are designed manually, and the augmentation policies are dataset-specific. Recently, an automatic data augmentation approach, named AutoAugment, is proposed using reinforcement learning. AutoAugment…

In supervised deep learning, learning good representations for remote--sensing images (RSI) relies on manual annotations. However, in the area of remote sensing, it is hard to obtain huge amounts of labeled data. Recently, self--supervised…

In this paper, we introduce a novel methodology for characterising the performance of deep learning networks (ResNets and DenseNet) with respect to training convergence and generalisation as a function of mini-batch size and learning rate…

Deep Learning models have shown remarkable performance in a broad range of vision tasks. However, they are often vulnerable against domain shifts at test-time. Test-time training (TTT) methods have been developed in an attempt to mitigate…

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most methods mainly focus on the instance level information (\ie,…

Contrastive learning is a recent promising approach in unsupervised representation learning where a feature representation of data is learned by solving a pseudo classification problem from unlabelled data. However, it is not…

Finetuning large language models on instruction data is crucial for enhancing pre-trained knowledge and improving instruction-following capabilities. As instruction datasets proliferate, selecting optimal data for effective training becomes…

This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner. InfoGAN is a generative adversarial network that…

Large and rich data is a prerequisite for effective training of deep neural networks. However, the irregularity of point cloud data makes manual annotation time-consuming and laborious. Self-supervised representation learning, which…