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

Streaming video algorithms dynamically select between different versions of a video to deliver the highest quality version that can be viewed without buffering over the client's connection. To improve the quality for viewers, the backing video service can generate more and/or better versions, but at a significant computational overhead. Processing all videos uploaded to Facebook in the most intensive way would require a prohibitively large cluster. Facebook's video popularity distribution is highly skewed, however, with analysis on sampled videos showing 1% of them accounting for 83% of the total watch time by users. Thus, if we can predict the future popularity of videos, we can focus the intensive processing on those videos that improve the quality of the most watch time.

To address this challenge, we designed Chess, the first popularity prediction algorithm that is both scalable and accurate. Chess is scalable because, unlike the state-of-the-art approaches, it requires only constant space per video, enabling it to handle Facebook's video workload. Chess is accurate because it delivers superior predictions using a combination of historical access patterns with social signals in a unified online learning framework. We have built a video prediction service, ChessVPS, using our new algorithm that can handle Facebook's workload with only four machines. We find that re-encoding popular videos predicted by ChessVPS enables a higher percentage of total user watch time to benefit from intensive encoding, with less overhead than a recent production heuristic, e.g., 80% of watch time with one-third as much overhead.

/pdf/popularity-prediction-of-facebook-videos-for-higher-quality-4hi0ys4git.pdf

Popularity prediction of facebook videos for higher quality streaming

Background. circRNAs are part of the competitive endogenous RNA network, which putatively function as miRNA sponges and play a crucial role in the development of numerous diseases. However, studies of circRNAs in rheumatoid arthritis (RA) disease are limited. This work aims to identify the expression pattern of circRNAs in synovial tissues and their inflammatory regulation mechanism. Methods. We first compared the mRNA expression in rheumatoid arthritis patients with that in healthy volunteers by GEO database mining to identify gene loci specifically expressed in synovial tissues. Functional enrichment algorithms were then used to draw the interactome diagram of circRNAs-miRNAs-mRNAs. Finally, loss-of-function and rescue assays of the candidate circRNAs were performed in vitro. Results. A total of 29 differentially expressed circRNAs related to rheumatoid arthritis were discovered. Silencing of hsa_circ_0001859 suppressed ATF2 expression and decreased inflammatory activity in SW982 cells. Hsa_circ_0001859 could compete with ATF2 for miR-204/211. Discussion. These findings indicate that hsa_circ_0001859 participates deeply in the process of chronic inflammatory disease in synovial tissue.

/pdf/hsa-circ-0001859-regulates-atf2-expression-by-functioning-as-27edq6kir1.pdf

Hsa_circ_0001859 Regulates ATF2 Expression by Functioning as an MiR-204/211 Sponge in Human Rheumatoid Arthritis.

Sketches are compact data structures that can be used to estimate properties of the original data in building large-scale search engines and data analysis systems. Recent theoretical and experimental studies have shown that sketches constructed from feature vectors using randomized projections can effectively approximate L1 distance on the feature vectors with the Hamming distance on their sketches. Furthermore, such sketches can achieve good filtering accuracy while reducing the metadata space requirement and speeding up similarity searches by an order of magnitude. However, it is not clear how to choose the size of the sketches since it depends ondata type, dataset size, and desired filtering quality. In real systems designs, it is necessary to understand how to choose sketch size without the dataset, or at least without the whole datase. This paper presents an analytical model and experimental results to help system designers make such design decisions. We present arank-based filtering model that describes the relationship between sketch size and data set size based on the dataset distance distribution. Our experimental results with several datasets including images, audio, and 3D shapes show that the model yields good, conservative predictions. We show that the parameters of the model can be set with a small sample data set and the resulting model can make good predictions for a large dataset. We illustrate how to apply the approach with a concrete example.

/pdf/sizing-sketches-a-rank-based-analysis-for-similarity-search-51k7f9qty6.pdf

Sizing sketches: a rank-based analysis for similarity search

Full correlation matrix analysis (FCMA): An unbiased method for task-related functional connectivity.

This paper describes VFerret, a content-based similarity search tool for continuous archived video. Instead of depending on attributes or annotations to search desired data from long-time archived video, our system allows users to perform content-based similarity search using visual and audio features, and to combine content-based similarity search with traditional search methods. Our preliminary experience and evaluation shows that content-based similarity search is easy to use and can achieve 0.79 average precision on our simple benchmark. The system is constructed using Ferret toolkit and its memory footprint for metadata is quite small, requiring about 1.4Gbytes for one year of continuous archived video data.

http://soundlab.cs.princeton.edu/publications/2006_carpe.pdf

Kai Li

Papers

Popularity prediction of facebook videos for higher quality streaming

Hsa_circ_0001859 Regulates ATF2 Expression by Functioning as an MiR-204/211 Sponge in Human Rheumatoid Arthritis.

Sizing sketches: a rank-based analysis for similarity search

Full correlation matrix analysis (FCMA): An unbiased method for task-related functional connectivity.

VFerret: content-based similarity search tool for continuous archived video