Sort by: Year Popularity Relevance

Yi Ma, Zinan Zeng, Jiwen Lu, Shenghua Gao, Kui Jia, Tsung-Han Chan - 2014

In this work, we propose a very simple deep learning network for image classification which comprises only the very basic data processing components: cascaded principal component analysis (PCA), binary hashing, and block-wise histograms. In the proposed architecture, PCA is employed to learn multistage filter banks. It is followed by simple binar...

Robert Tibshirani, Iain Johnstone, Trevor Hastie, Bradley Efron - 2004

The purpose of model selection algorithms such as All Subsets, Forward Selection and Backward Elimination is to choose a linear model on the basis of the same set of data to which the model will be applied. Typically we have available a large collection of possible covariates from which we hope to select a parsimonious set for the efficient pre...

Piotr Dollr, Kaiming He, Ross Girshick, Priya Goyal, Tsung-Yi Lin - 2017

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of possible object locations have the potential to be faster and simpler, but have trail...

Koray Kavukcuoglu, Nal Kalchbrenner, Aaron van den Oord - 2016

Modeling the distribution of natural images is a landmark problem in unsupervised learning. This task requires an image model that is at once expressive, tractable and scalable. We present a deep neural network that sequentially predicts the pixels in an image along the two spatial dimensions. Our method models the discrete probability of the raw...

Navdeep Jaitly, Meire Fortunato, Oriol Vinyals - 2015

We introduce a new neural architecture to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence. Such problems cannot be trivially addressed by existent approaches such as sequence-to-sequence and Neural Turing Machines, because the number of target classes i...

Koray Kavukcuoglu, Alex Graves, Nicolas Heess, Volodymyr Mnih - 2014

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of extracting information from an image or video by adaptively selecting a sequence of regions or locations and onl...

Anelia Angelova, Joseph Redmon - 2014

We present an accurate, real-time approach to robotic grasp detection based on convolutional neural networks. Our network performs single-stage regression to graspable bounding boxes without using standard sliding window or region proposal techniques. The model outperforms state-of-the-art approaches by 14 percentage points and runs at 13 frames ...

Aaron Courville, Vincent Dumoulin, Martin Arjovsky, Faruk Ahmed, Ishaan Gulrajani - 2017

Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but can still generate low-quality samples or fail to converge in some settings. We find that these problems are often due to the use of weight cli...

Antonio Torralba, Wojciech Matusik, Suchendra Bhandarkar, Harini Kannan, Petr Kellnhofer, Aditya Khosla, Kyle Krafka - 2016

From scientific research to commercial applications, eye tracking is an important tool across many domains. Despite its range of applications, eye tracking has yet to become a pervasive technology. We believe that we can put the power of eye tracking in everyone's palm by building eye tracking software that works on commodity hardware such as mob...

Kyoung Mu Lee, Seungjun Nah, Heewon Kim, Sanghyun Son, Bee Lim - 2017

Recent research on super-resolution has progressed with the development of deep convolutional neural networks (DCNN). In particular, residual learning techniques exhibit improved performance. In this paper, we develop an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods. The sign...