arXiv subjects

Shuai Zheng

Publications and source records attributed to Shuai Zheng.

75 records · Page 5Linked to original sources

arXiv2015

Asynchronous Distributed Semi-Stochastic Gradient Optimization

With the recent proliferation of large-scale learning problems,there have been a lot of interest on distributed machine learning algorithms, particularly those that are based on stochastic gradient descent (SGD) and its variants. However, existing algorithms either suffer from slow convergence due to the inherent variance of stochastic gradients, or have a fast linear convergence rate but at the expense of poorer solution quality. In this paper, we combine their merits by proposing a fast distributed asynchronous SGD-based algorithm with variance reduction. A constant learning rate can be used, and it is also guaranteed to converge linearly to the optimal solution. Experiments on the Google Cloud Computing Platform demonstrate that the proposed algorithm outperforms state-of-the-art distributed asynchronous algorithms in terms of both wall clock time and solution quality.

cs.LG↗

arXiv2014

ImageSpirit: Verbal Guided Image Parsing

Humans describe images in terms of nouns and adjectives while algorithms operate on images represented as sets of pixels. Bridging this gap between how humans would like to access images versus their typical representation is the goal of image parsing, which involves assigning object and attribute labels to pixel. In this paper we propose treating nouns as object labels and adjectives as visual attribute labels. This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images. We propose an efficient (interactive time) solution. Using the extracted labels as handles, our system empowers a user to verbally refine the results. This enables hands-free parsing of an image into pixel-wise object/attribute labels that correspond to human semantics. Verbally selecting objects of interests enables a novel and natural interaction modality that can possibly be used to interact with new generation devices (e.g. smart phones, Google Glass, living room devices). We demonstrate our system on a large number of real-world images with varying complexity. To help understand the tradeoffs compared to traditional mouse based interactions, results are reported for both a large scale quantitative evaluation and a user study.

cs.GR↗

arXiv2010

Translation-Invariant Representation for Cumulative Foot Pressure Images

Human can be distinguished by different limb movements and unique ground reaction force. Cumulative foot pressure image is a 2-D cumulative ground reaction force during one gait cycle. Although it contains pressure spatial distribution information and pressure temporal distribution information, it suffers from several problems including different shoes and noise, when putting it into practice as a new biometric for pedestrian identification. In this paper, we propose a hierarchical translation-invariant representation for cumulative foot pressure images, inspired by the success of Convolutional deep belief network for digital classification. Key contribution in our approach is discriminative hierarchical sparse coding scheme which helps to learn useful discriminative high-level visual features. Based on the feature representation of cumulative foot pressure images, we develop a pedestrian recognition system which is invariant to three different shoes and slight local shape change. Experiments are conducted on a proposed open dataset that contains more than 2800 cumulative foot pressure images from 118 subjects. Evaluations suggest the effectiveness of the proposed method and the potential of cumulative foot pressure images as a biometric.

cs.AI↗