We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.

/pdf/imagenet-classification-with-deep-convolutional-neural-1190x9a6b9.pdf

ImageNet Classification with Deep Convolutional Neural Networks

In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Very Deep Convolutional Networks for Large-Scale Image Recognition

The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data. But exactly how such data can be harnessed and organized remains a critical problem. We introduce here a new database called “ImageNet”, a large-scale ontology of images built upon the backbone of the WordNet structure. ImageNet aims to populate the majority of the 80,000 synsets of WordNet with an average of 500-1000 clean and full resolution images. This will result in tens of millions of annotated images organized by the semantic hierarchy of WordNet. This paper offers a detailed analysis of ImageNet in its current state: 12 subtrees with 5247 synsets and 3.2 million images in total. We show that ImageNet is much larger in scale and diversity and much more accurate than the current image datasets. Constructing such a large-scale database is a challenging task. We describe the data collection scheme with Amazon Mechanical Turk. Lastly, we illustrate the usefulness of ImageNet through three simple applications in object recognition, image classification and automatic object clustering. We hope that the scale, accuracy, diversity and hierarchical structure of ImageNet can offer unparalleled opportunities to researchers in the computer vision community and beyond.

/pdf/imagenet-a-large-scale-hierarchical-image-database-1e8f663s1h.pdf

ImageNet: A large-scale hierarchical image database

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

A hybrid optimization framework for UAV reconnaissance mission planning

Selecting a segment boundary within block b is disclosed. A first anchor location j|j+1 is identified wherein a value of f(b[j−A+1 . . . j+B]) satisfies a constraint and wherein A and B are non-negative integers. A segment boundary location k|k+1 is determined wherein k is greater than minimum distance from j.

Partitioning a data stream using embedded anchors

Implementing the Iterative Soft-Thresholding Algorithm (ISTA) of compressed sensing for MRI image reconstruction is a good candidate for designing accelerators because real-time functional MRI applications require intensive computations. A straightforward mapping of the computation graph of ISTA onto an FPGA, with a wide enough datapath to saturate memory bandwidth, would require substantial resources, such that a modest size FPGA would not fit the reconstruction pipeline for an entire MRI image. This paper proposes several methods to design the kernel components of ISTA, such as matrix transpose, datapath reuse, parallelism within maps, and data buffering to overcome the problem. Our implementation with Intel OpenCL SDK and performance evaluation on Intel HARPv2 show that our methods can map the reconstruction for the entire 256x256 MRI image with 8 or more channels to its FPGA, while achieving good overall performance.

Compressed Sensing MRI Reconstruction on Intel HARPv2

Tiled displays (multiple projector arrays) are quickly becoming technologically viable options for constructing high-end displays at a reasonable cost. Tiled displays address the need for increased resolution, increased field of view, large-scale form factor for group-oriented visualization and provide possible mechanisms for scaling graphics performance and leveraging commodity technologies. Numerous research groups are currently investigating tiled display technologies and their use in visualization applications. While tiled displays have a lot of potential to offer the visualization community, there are still many open research questions that limit their adoption. This panel will discuss the current state-of-the-art and open research issues related to tiled displays in the areas of applications, compute systems, display surfaces, projectors, and overall architecture of complete systems. Some of the questions that will be addressed include:

Next-generation visualization displays: the research challenges of building tiled displays (panel session)

A disk-based archival storage system (20) including a storage unit (26) configured to store archival data, including at least one spindle of disks to magnetically store archival data, an interconnect (24) to either archive to or retrieve data from the storage unit. In one embodiment, the system includes a plurality of the storage units each including at least one spindle of disks. The control unit (22) controls the storage commands to selectively cause the storage unit(s) to shut down or power up, enter a running mode or a standby mode, cause the spindle of disk(s) to either spin up or spin down, and to perform a data integrity check of all the archival data stored in the storage system. In various other embodiments, the control unit runs algorithms that expand the lifetime and longevity of the disk spindles, optimizes power consumption, and performs data migration when a data integrity check identifies correctable errors.

Kai Li

Papers

A hybrid optimization framework for UAV reconnaissance mission planning

Partitioning a data stream using embedded anchors

Compressed Sensing MRI Reconstruction on Intel HARPv2

Next-generation visualization displays: the research challenges of building tiled displays (panel session)

Disk-based archival data storage system and method