Related papers: Improving Model's Focus Improves Performance of De…

Deep image inpainting research mainly focuses on constructing various neural network architectures or imposing novel optimization objectives. However, on the one hand, building a state-of-the-art deep inpainting model is an extremely…

Autoencoders are commonly trained using element-wise loss. However, element-wise loss disregards high-level structures in the image which can lead to embeddings that disregard them as well. A recent improvement to autoencoders that helps…

Recurrent neural networks with differentiable attention mechanisms have had success in generative and classification tasks. We show that the classification performance of such models can be enhanced by guiding a randomly initialized model…

The generalization performance of deep neural networks in classification tasks is a major concern in machine learning research. Despite widespread techniques used to diminish the over-fitting issue such as data augmentation,…

Recent studies have shown that many deep metric learning loss functions perform very similarly under the same experimental conditions. One potential reason for this unexpected result is that all losses let the network focus on similar image…

Deep Learning has revolutionized machine learning and artificial intelligence, achieving superhuman performance in several standard benchmarks. It is well-known that deep learning models are inefficient to train; they learn by processing…

Humans can often quickly and efficiently solve complex new learning tasks given only a small set of examples. In contrast, modern artificially intelligent systems often require thousands or millions of observations in order to solve even…

Despite the large volume of face recognition datasets, there is a significant portion of subjects, of which the samples are insufficient and thus under-represented. Ignoring such significant portion results in insufficient training data.…

Learning discriminative representations is a central goal of supervised deep learning. While cross-entropy (CE) remains the dominant objective for classification, it does not explicitly enforce desirable geometric properties in the…

We propose a focus of attention mechanism to speed up the Perceptron algorithm. Focus of attention speeds up the Perceptron algorithm by lowering the number of features evaluated throughout training and prediction. Whereas the traditional…

Developing effective world models is crucial for creating artificial agents that can reason about and navigate complex environments. In this paper, we investigate a deep supervision technique for encouraging the development of a world model…

We present ongoing work to harness biological approaches to achieving highly efficient egocentric perception by combining the space-variant imaging architecture of the mammalian retina with Deep Learning methods. By pre-processing images…

Deep learning has been shown to achieve impressive results in several domains like computer vision and natural language processing. A key element of this success has been the development of new loss functions, like the popular cross-entropy…

In face detection, low-resolution faces, such as numerous small faces of a human group in a crowded scene, are common in dense face prediction tasks. They usually contain limited visual clues and make small faces less distinguishable from…

Deep learning models are often deployed in downstream tasks that the training procedure may not be aware of. For example, models solely trained to achieve accurate predictions may struggle to perform well on downstream tasks because…

Ensembles of Convolutional neural networks have shown remarkable results in learning discriminative semantic features for image classification tasks. Though, the models in the ensemble often concentrate on similar regions in images. This…

Crowdsourced 3D CAD models are becoming easily accessible online, and can potentially generate an infinite number of training images for almost any object category.We show that augmenting the training data of contemporary Deep Convolutional…

Attention mechanisms are widely used in salient object detection models based on deep learning, which can effectively promote the extraction and utilization of useful information by neural networks. However, most of the existing attention…

Cross-entropy loss is the standard metric used to train classification models in deep learning and gradient boosting. It is well-known that this loss function fails to account for similarities between the different values of the target. We…

Surveillance scenarios are prone to several problems since they usually involve low-resolution footage, and there is no control of how far the subjects may be from the camera in the first place. This situation is suitable for the…