In this paper, we propose a progressive margin loss (PML) approach for unconstrained facial age classification. Conventional methods make strong assumption on that each class owns adequate instances to outline its data distribution, likely leading to bias prediction where the training samples are sparse across age classes. Instead, our PML aims to adaptively refine the age label pattern by enforcing a couple of margins, which fully takes in the in-between discrepancy of the intra-class variance, inter-class variance and class center. Our PML typically incorporates with the ordinal margin and the variational margin, simultaneously plugging in the globally-tuned deep neural network paradigm. More specifically, the ordinal margin learns to exploit the correlated relationship of the real-world age labels. Accordingly, the variational margin is leveraged to minimize the influence of head classes that misleads the prediction of tailed samples. Moreover, our optimization carefully seeks a series of indicator curricula to achieve robust and efficient model training. Extensive experimental results on three face aging datasets demonstrate that our PML achieves compelling performance compared to state of the art. Code will be made publicly.

In this paper, we propose a spatial-temporal relational reasoning networks (STRRN) approach to investigate the problem of omni-supervised face alignment in videos. Unlike existing fully supervised methods which rely on numerous annotations by hand, our learner exploits large scale unlabeled videos plus available labeled data to generate auxiliary plausible training annotations. Motivated by the fact that neighbouring facial landmarks are usually correlated and coherent across consecutive frames, our approach automatically reasons about discriminative spatial-temporal relationships among landmarks for stable face tracking. Specifically, we carefully develop an interpretable and efficient network module, which disentangles facial geometry relationship for every static frame and simultaneously enforces the bi-directional cycle-consistency across adjacent frames, thus allowing the modeling of intrinsic spatial-temporal relations from raw face sequences. Extensive experimental results demonstrate that our approach surpasses the performance of most fully supervised state-of-the-arts.

MOTIVATION: Allele dropout (ADO) and unbalanced amplification of alleles are main technical issues of single-cell sequencing (SCS), and effectively emulating these issues is necessary for reliably benchmarking SCS-based bioinformatics tools. Unfortunately, currently available sequencing simulators are free of whole-genome amplification involved in SCS technique and therefore not suited for generating SCS datasets. We develop a new software package (SCSsim) that can efficiently simulate SCS datasets in a parallel fashion with minimal user intervention. SCSsim first constructs the genome sequence of single cell by mimicking a complement of genomic variations under user-controlled manner, and then amplifies the genome according to MALBAC technique and finally yields sequencing reads from the amplified products based on inferred sequencing profiles. Comprehensive evaluation in simulating different ADO rates, variation detection efficiency and genome coverage demonstrates that SCSsim is a very useful tool in mimicking single-cell sequencing data with high efficiency. AVAILABILITY AND IMPLEMENTATION: SCSsim is freely available at https://github.com/qasimyu/scssim. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

In this paper, we propose a similarity-aware deep adversarial learning (SADAL) approach for facial age estimation. Instead of making full access to the limited training samples which likely leads to bias age prediction, our SADAL aims to seek batches of unobserved hard-negative samples based on existing training samples, which typically reinforces the discriminativeness of the learned feature representation for facial ages. Motivated by the fact that age labels are usually correlated in real-world scenarios, we carefully develop a similarity-aware function to well measure the distance of each face pair based on the age value gaps. Consequently, the age-difference information is exploited in the synthetic feature space for robust age estimation. During the learning process, we jointly optimize both procedures of generating hard negatives and learning discriminative age ranker via a sequence of adversarial-game iterations. Another major issue lies on that existing methods only enforce the indiscriminativeness within each class, which is probably trapped into model overfitting and thus the generation capacity is limited particularly on unseen age classes with many individuals. To circumvent this problem, we propose a variational deep adversarial learning (VDAL) paradigm, which learns to encode each face sample in two factorized parts, i.e., the intra-class variance distribution and the intra-class invariant class center. Moreover, our VDAL principally optimizes the variational confidence lower bound on the variational factorized feature representation. To better enhance the discriminativeness of the age representation, our VDAL further learns to encode the ordinal relationship among age labels in the reconstructed subspace. Experimental results on folds of widely-evaluated benchmarking datasets demonstrate that our approach achieves promising performance in contrast to most state-of-the-art age estimation methods.

In this paper, we propose a deformable hourglass networks (DHGN) approach to investigate the problem of face alignment, especially in such challenging cases when faces undergo large variations including severe poses, diverse expressions and partial occlusions in unconstrained environments. Unlike conventional feature extractions which cannot explicitly exploit irregular geometric structures for facial shapes, our DHGN learns a deformable mask to reduce the variances of facial deformation and extract attentional facial regions for robust feature representation. To achieve this, we carefully design a differential module, dubbed the deformable transformer, which typically incorporates with a regression sub-net to predict a set of offsets and a masking operator to filter the semantic facial parts for feature representation learning. To further reinforce the alignment performance, we integrate our designed modules in the paradigm of stacked hourglass networks and jointly optimize the network parameters in an end-to-end manner. Extensive experimental results demonstrate very compelling performance in comparisons to most state-of-the-art methods.

This paper proposes a new data compression algorithm to store the routing table in a tree structure using very little memory. This data structure is tailored to a hardware design reference model presented in this paper. By exploiting the low memory access latency and high bandwidth of on-chip memory, high-speed packet forwarding can be achieved using this data structure. With the addition of pipeline in the hardware, IP address lookup can only be limited by the memory access speed. The algorithm is also flexible for different implementation. Experimental analysis shows that, given the memory width of 144 bits, our algorithm needs only 400kb memory for storing a 20k entries IPv4 routing table and five memory accesses for a search. For a 1M entries IPv4 routing table, 9Mb memory and seven memory accesses are needed. With memory width of 1,068 bits, we estimate that we need 100Mb memory and six memory accesses for a routing table with 1M IPv6 prefixes.

In order to provide more value-added services, the Internet needs to classify packets into flows for different treatment. This function becomes a bottleneck in the router. High performance packet classification algorithms are therefore in high demand. This paper describes a new algorithm for packet classification using the concept of independent sets. The algorithm has very small memory requirements. The search speed is not sensitive to the size of the rule table or to the percentage of wildcards in the fields. It also scales well from two-dimensional classifiers to high-dimensional ones. In particular, the algorithm is inherently parallel. Hardware tailored to this algorithm can achieve very fast search speed. The update algorithm proposed is also very fast in general.

This paper describes a new algorithm for packet classification using the concept of independent sets. The algorithm has very small memory requirements. The search speed is neither sensitive to the rule table nor to the percentage of wildcards in the fields. It also scales well from two dimensional classifiers to high dimensional ones. In particular, the algorithm is inherently parallel. Hardware tailored to this algorithm can achieve very fast search speed.