Related papers: Identity-Based Patterns in Deep Convolutional Netw…

Inspired by the philosophy employed by human beings to determine whether a presented face example is genuine or not, i.e., to glance at the example globally first and then carefully observe the local regions to gain more discriminative…

Successful training of convolutional neural networks is often associated with sufficiently deep architectures composed of high amounts of features. These networks typically rely on a variety of regularization and pruning techniques to…

This paper describes a general, scalable, end-to-end framework that uses the generative adversarial network (GAN) objective to enable robust speech recognition. Encoders trained with the proposed approach enjoy improved invariance by…

Recent studies show that deep neural networks are vulnerable to adversarial examples which can be generated via certain types of transformations. Being robust to a desired family of adversarial attacks is then equivalent to being invariant…

We introduce LOGAN, a deep neural network aimed at learning general-purpose shape transforms from unpaired domains. The network is trained on two sets of shapes, e.g., tables and chairs, while there is neither a pairing between shapes from…

Deep learning, a rebranding of deep neural network research works, has achieved a remarkable success in recent years. With multiple hidden layers, deep learning models aim at computing the hierarchical feature representations of the…

Deep generative models provide powerful tools for distributions over complicated manifolds, such as those of natural images. But many of these methods, including generative adversarial networks (GANs), can be difficult to train, in part…

Recent advancements in unsupervised feature learning have developed powerful latent representations of words. However, it is still not clear what makes one representation better than another and how we can learn the ideal representation.…

The interpretability of neural networks (NNs) is a challenging but essential topic for transparency in the decision-making process using machine learning. One of the reasons for the lack of interpretability is random weight initialization,…

Human learners can readily understand speech, or a melody, when it is presented slower or faster than usual. Although deep convolutional neural networks (CNNs) are extremely powerful in extracting information from time series, they require…

The learning of interpretable representations from raw data presents significant challenges for time series data like speech. In this work, we propose a relevance weighting scheme that allows the interpretation of the speech representations…

We propose a new algorithm for training generative adversarial networks that jointly learns latent codes for both identities (e.g. individual humans) and observations (e.g. specific photographs). By fixing the identity portion of the latent…

Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data. They achieve this through deriving backpropagation signals through a competitive process involving a pair of…

Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data. However, manipulating such representation to perform meaningful and controllable transformations in the…

The ability to predict future states of the environment is a central pillar of intelligence. At its core, effective prediction requires an internal model of the world and an understanding of the rules by which the world changes. Here, we…

Deep learning is found to be vulnerable to adversarial examples. However, its adversarial susceptibility in image caption generation is under-explored. We study adversarial examples for vision and language models, which typically adopt an…

Interpretability work on the convolutional layers of CNNs has primarily focused on computer vision, but some studies also explore correspondences between the latent space and the output in the audio domain. However, it has not been…

In recent years, person re-identification (re-id) catches great attention in both computer vision community and industry. In this paper, we propose a new framework for person re-identification with a triplet-based deep similarity learning…

Deep learning is currently playing a crucial role toward higher levels of artificial intelligence. This paradigm allows neural networks to learn complex and abstract representations, that are progressively obtained by combining simpler…

Learning concepts that are consistent with human perception is important for Deep Neural Networks to win end-user trust. Post-hoc interpretation methods lack transparency in the feature representations learned by the models. This work…