arXiv subjects

Chun-Liang Li

Publications and source records attributed to Chun-Liang Li.

80 records · Page 5Linked to original sources

arXiv2018

Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond

State-of-the-art pedestrian detection models have achieved great success in many benchmarks. However, these models require lots of annotation information and the labeling process usually takes much time and efforts. In this paper, we propose a method to generate labeled pedestrian data and adapt them to support the training of pedestrian detectors. The proposed framework is built on the Generative Adversarial Network (GAN) with multiple discriminators, trying to synthesize realistic pedestrians and learn the background context simultaneously. To handle the pedestrians of different sizes, we adopt the Spatial Pyramid Pooling (SPP) layer in the discriminator. We conduct experiments on two benchmarks. The results show that our framework can smoothly synthesize pedestrians on background images of variations and different levels of details. To quantitatively evaluate our approach, we add the generated samples into training data of the baseline pedestrian detectors and show the synthetic images are able to improve the detectors' performance.

cs.CV↗

arXiv2017

MMD GAN: Towards Deeper Understanding of Moment Matching Network

Generative moment matching network (GMMN) is a deep generative model that differs from Generative Adversarial Network (GAN) by replacing the discriminator in GAN with a two-sample test based on kernel maximum mean discrepancy (MMD). Although some theoretical guarantees of MMD have been studied, the empirical performance of GMMN is still not as competitive as that of GAN on challenging and large benchmark datasets. The computational efficiency of GMMN is also less desirable in comparison with GAN, partially due to its requirement for a rather large batch size during the training. In this paper, we propose to improve both the model expressiveness of GMMN and its computational efficiency by introducing adversarial kernel learning techniques, as the replacement of a fixed Gaussian kernel in the original GMMN. The new approach combines the key ideas in both GMMN and GAN, hence we name it MMD GAN. The new distance measure in MMD GAN is a meaningful loss that enjoys the advantage of weak topology and can be optimized via gradient descent with relatively small batch sizes. In our evaluation on multiple benchmark datasets, including MNIST, CIFAR- 10, CelebA and LSUN, the performance of MMD-GAN significantly outperforms GMMN, and is competitive with other representative GAN works.

cs.LG↗

arXiv2017

Sobolev GAN

We propose a new Integral Probability Metric (IPM) between distributions: the Sobolev IPM. The Sobolev IPM compares the mean discrepancy of two distributions for functions (critic) restricted to a Sobolev ball defined with respect to a dominant measure $μ$. We show that the Sobolev IPM compares two distributions in high dimensions based on weighted conditional Cumulative Distribution Functions (CDF) of each coordinate on a leave one out basis. The Dominant measure $μ$ plays a crucial role as it defines the support on which conditional CDFs are compared. Sobolev IPM can be seen as an extension of the one dimensional Von-Mises Cramér statistics to high dimensional distributions. We show how Sobolev IPM can be used to train Generative Adversarial Networks (GANs). We then exploit the intrinsic conditioning implied by Sobolev IPM in text generation. Finally we show that a variant of Sobolev GAN achieves competitive results in semi-supervised learning on CIFAR-10, thanks to the smoothness enforced on the critic by Sobolev GAN which relates to Laplacian regularization.

cs.LG↗

arXiv2017

Data-driven Random Fourier Features using Stein Effect

Large-scale kernel approximation is an important problem in machine learning research. Approaches using random Fourier features have become increasingly popular [Rahimi and Recht, 2007], where kernel approximation is treated as empirical mean estimation via Monte Carlo (MC) or Quasi-Monte Carlo (QMC) integration [Yang et al., 2014]. A limitation of the current approaches is that all the features receive an equal weight summing to 1. In this paper, we propose a novel shrinkage estimator from "Stein effect", which provides a data-driven weighting strategy for random features and enjoys theoretical justifications in terms of lowering the empirical risk. We further present an efficient randomized algorithm for large-scale applications of the proposed method. Our empirical results on six benchmark data sets demonstrate the advantageous performance of this approach over representative baselines in both kernel approximation and supervised learning tasks.

cs.LG↗

arXiv2017

One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models

While deep learning methods have achieved state-of-the-art performance in many challenging inverse problems like image inpainting and super-resolution, they invariably involve problem-specific training of the networks. Under this approach, different problems require different networks. In scenarios where we need to solve a wide variety of problems, e.g., on a mobile camera, it is inefficient and costly to use these specially-trained networks. On the other hand, traditional methods using signal priors can be used in all linear inverse problems but often have worse performance on challenging tasks. In this work, we provide a middle ground between the two kinds of methods --- we propose a general framework to train a single deep neural network that solves arbitrary linear inverse problems. The proposed network acts as a proximal operator for an optimization algorithm and projects non-image signals onto the set of natural images defined by the decision boundary of a classifier. In our experiments, the proposed framework demonstrates superior performance over traditional methods using a wavelet sparsity prior and achieves comparable performance of specially-trained networks on tasks including compressive sensing and pixel-wise inpainting.

cs.CV↗

arXiv2017

CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding

Galaxy-scale strong gravitational lensing is not only a valuable probe of the dark matter distribution of massive galaxies, but can also provide valuable cosmological constraints, either by studying the population of strong lenses or by measuring time delays in lensed quasars. Due to the rarity of galaxy-scale strongly lensed systems, fast and reliable automated lens finding methods will be essential in the era of large surveys such as LSST, Euclid, and WFIRST. To tackle this challenge, we introduce CMU DeepLens, a new fully automated galaxy-galaxy lens finding method based on Deep Learning. This supervised machine learning approach does not require any tuning after the training step which only requires realistic image simulations of strongly lensed systems. We train and validate our model on a set of 20,000 LSST-like mock observations including a range of lensed systems of various sizes and signal-to-noise ratios (S/N). We find on our simulated data set that for a rejection rate of non-lenses of 99%, a completeness of 90% can be achieved for lenses with Einstein radii larger than 1.4" and S/N larger than 20 on individual $g$-band LSST exposures. Finally, we emphasize the importance of realistically complex simulations for training such machine learning methods by demonstrating that the performance of models of significantly different complexities cannot be distinguished on simpler simulations. We make our code publicly available at https://github.com/McWilliamsCenter/CMUDeepLens .

astro-ph.IM↗

arXiv2016

Annealing Gaussian into ReLU: a New Sampling Strategy for Leaky-ReLU RBM

Restricted Boltzmann Machine (RBM) is a bipartite graphical model that is used as the building block in energy-based deep generative models. Due to numerical stability and quantifiability of the likelihood, RBM is commonly used with Bernoulli units. Here, we consider an alternative member of exponential family RBM with leaky rectified linear units -- called leaky RBM. We first study the joint and marginal distributions of leaky RBM under different leakiness, which provides us important insights by connecting the leaky RBM model and truncated Gaussian distributions. The connection leads us to a simple yet efficient method for sampling from this model, where the basic idea is to anneal the leakiness rather than the energy; -- i.e., start from a fully Gaussian/Linear unit and gradually decrease the leakiness over iterations. This serves as an alternative to the annealing of the temperature parameter and enables numerical estimation of the likelihood that are more efficient and more accurate than the commonly used annealed importance sampling (AIS). We further demonstrate that the proposed sampling algorithm enjoys faster mixing property than contrastive divergence algorithm, which benefits the training without any additional computational cost.

stat.ML↗

arXiv2015

Rivalry of Two Families of Algorithms for Memory-Restricted Streaming PCA

We study the problem of recovering the subspace spanned by the first $k$ principal components of $d$-dimensional data under the streaming setting, with a memory bound of $O(kd)$. Two families of algorithms are known for this problem. The first family is based on the framework of stochastic gradient descent. Nevertheless, the convergence rate of the family can be seriously affected by the learning rate of the descent steps and deserves more serious study. The second family is based on the power method over blocks of data, but setting the block size for its existing algorithms is not an easy task. In this paper, we analyze the convergence rate of a representative algorithm with decayed learning rate (Oja and Karhunen, 1985) in the first family for the general $k>1$ case. Moreover, we propose a novel algorithm for the second family that sets the block sizes automatically and dynamically with faster convergence rate. We then conduct empirical studies that fairly compare the two families on real-world data. The studies reveal the advantages and disadvantages of these two families.

stat.ML↗