Related papers: Deeply learned face representations are sparse, se…

Implicit neural representations are a promising new avenue of representing general signals by learning a continuous function that, parameterized as a neural network, maps the domain of a signal to its codomain; the mapping from spatial…

We introduce a deep convolutional neural networks (CNN) architecture to classify facial attributes and recognize face images simultaneously via a shared learning paradigm to improve the accuracy for facial attribute prediction and face…

Disguised face identification (DFI) is an extremely challenging problem due to the numerous variations that can be introduced using different disguises. This paper introduces a deep learning framework to first detect 14 facial key-points…

One of the central questions in the theory of deep learning is to understand how neural networks learn hierarchical features. The ability of deep networks to extract salient features is crucial to both their outstanding generalization…

Face recognition performance based on deep learning heavily relies on large-scale training data, which is often difficult to acquire in practical applications. To address this challenge, this paper proposes a GAN-based data augmentation…

Deep learning is a topic of considerable current interest. The availability of massive data collections and powerful software resources has led to an impressive amount of results in many application areas that reveal essential but hidden…

In this paper, we propose a novel deep learning network L1-(2D)2PCANet for face recognition, which is based on L1-norm-based two-directional two-dimensional principal component analysis (L1-(2D)2PCA). In our network, the role of L1-(2D)2PCA…

Real-world face recognition requires an ability to perceive the unique features of an individual face across multiple, variable images. The primate visual system solves the problem of image invariance using cascades of neurons that convert…

(This paper was written in November 2011 and never published. It is posted on arXiv.org in its original form in June 2016). Many recent object recognition systems have proposed using a two phase training procedure to learn sparse…

Deep learning has arguably achieved tremendous success in recent years. In simple words, deep learning uses the composition of many nonlinear functions to model the complex dependency between input features and labels. While neural networks…

Multi-modal medical image segmentation plays an essential role in clinical diagnosis. It remains challenging as the input modalities are often not well-aligned spatially. Existing learning-based methods mainly consider sharing trainable…

Deep convolutional neutral networks have achieved great success on image recognition tasks. Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to videos as per-frame evaluation is too slow and unaffordable.…

Nonnegative matrix factorization is usually powerful for learning the "shallow" parts-based representation, but it clearly fails to discover deep hierarchical information within both the basis and representation spaces. In this paper, we…

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a…

Do very high accuracies of deep networks suggest pride of effective AI or are deep networks prejudiced? Do they suffer from in-group biases (own-race-bias and own-age-bias), and mimic the human behavior? Is in-group specific information…

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we…

In real world scenarios, objects are often partially occluded. This requires a robustness for object recognition against these perturbations. Convolutional networks have shown good performances in classification tasks. The learned…

Reusing features in deep networks through dense connectivity is an effective way to achieve high computational efficiency. The recent proposed CondenseNet has shown that this mechanism can be further improved if redundant features are…

We propose to learn a fully-convolutional network model that consists of a Chain of Identity Mapping Modules and residual on the residual architecture for image denoising. Our network structure possesses three distinctive features that are…

Algorithmic detection of facial palsy offers the potential to improve current practices, which usually involve labor-intensive and subjective assessment by clinicians. In this paper, we present a multimodal fusion-based deep learning model…