arXiv subjects

Ziming Zhang

Publications and source records attributed to Ziming Zhang.

68 records · Page 4Linked to original sources

arXiv2017

Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks

By lifting the ReLU function into a higher dimensional space, we develop a smooth multi-convex formulation for training feed-forward deep neural networks (DNNs). This allows us to develop a block coordinate descent (BCD) training algorithm consisting of a sequence of numerically well-behaved convex optimizations. Using ideas from proximal point methods in convex analysis, we prove that this BCD algorithm will converge globally to a stationary point with R-linear convergence rate of order one. In experiments with the MNIST database, DNNs trained with this BCD algorithm consistently yielded better test-set error rates than identical DNN architectures trained via all the stochastic gradient descent (SGD) variants in the Caffe toolbox.

stat.ML↗

arXiv2017

BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning

Understanding the global optimality in deep learning (DL) has been attracting more and more attention recently. Conventional DL solvers, however, have not been developed intentionally to seek for such global optimality. In this paper we propose a novel approximation algorithm, BPGrad, towards optimizing deep models globally via branch and pruning. Our BPGrad algorithm is based on the assumption of Lipschitz continuity in DL, and as a result it can adaptively determine the step size for current gradient given the history of previous updates, wherein theoretically no smaller steps can achieve the global optimality. We prove that, by repeating such branch-and-pruning procedure, we can locate the global optimality within finite iterations. Empirically an efficient solver based on BPGrad for DL is proposed as well, and it outperforms conventional DL solvers such as Adagrad, Adadelta, RMSProp, and Adam in the tasks of object recognition, detection, and segmentation.

stat.ML↗

arXiv2017

Sequential Optimization for Efficient High-Quality Object Proposal Generation

We are motivated by the need for a generic object proposal generation algorithm which achieves good balance between object detection recall, proposal localization quality and computational efficiency. We propose a novel object proposal algorithm, BING++, which inherits the virtue of good computational efficiency of BING but significantly improves its proposal localization quality. At high level we formulate the problem of object proposal generation from a novel probabilistic perspective, based on which our BING++ manages to improve the localization quality by employing edges and segments to estimate object boundaries and update the proposals sequentially. We propose learning the parameters efficiently by searching for approximate solutions in a quantized parameter space for complexity reduction. We demonstrate the generalization of BING++ with the same fixed parameters across different object classes and datasets. Empirically our BING++ can run at half speed of BING on CPU, but significantly improve the localization quality by 18.5% and 16.7% on both VOC2007 and Microhsoft COCO datasets, respectively. Compared with other state-of-the-art approaches, BING++ can achieve comparable performance, but run significantly faster.

cs.CV↗

arXiv2016

Learning Joint Feature Adaptation for Zero-Shot Recognition

Zero-shot recognition (ZSR) aims to recognize target-domain data instances of unseen classes based on the models learned from associated pairs of seen-class source and target domain data. One of the key challenges in ZSR is the relative scarcity of source-domain features (e.g. one feature vector per class), which do not fully account for wide variability in target-domain instances. In this paper we propose a novel framework of learning data-dependent feature transforms for scoring similarity between an arbitrary pair of source and target data instances to account for the wide variability in target domain. Our proposed approach is based on optimizing over a parameterized family of local feature displacements that maximize the source-target adaptive similarity functions. Accordingly we propose formulating zero-shot learning (ZSL) using latent structural SVMs to learn our similarity functions from training data. As demonstration we design a specific algorithm under the proposed framework involving bilinear similarity functions and regularized least squares as penalties for feature displacement. We test our approach on several benchmark datasets for ZSR and show significant improvement over the state-of-the-art. For instance, on aP&Y dataset we can achieve 80.89% in terms of recognition accuracy, outperforming the state-of-the-art by 11.15%.

cs.CV↗

arXiv2016

Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter Learning

Correlation filtering based tracking model has received lots of attention and achieved great success in real-time tracking, however, the lost function in current correlation filtering paradigm could not reliably response to the appearance changes caused by occlusion and illumination variations. This study intends to promote the robustness of the correlation filter learning. By exploiting the anisotropy of the filter response, three sparsity related loss functions are proposed to alleviate the overfitting issue of previous methods and improve the overall tracking performance. As a result, three real-time trackers are implemented. Extensive experiments in various challenging situations demonstrate that the robustness of the learned correlation filter has been greatly improved via the designed loss functions. In addition, the study reveals, from an experimental perspective, how different loss functions essentially influence the tracking performance. An important conclusion is that the sensitivity of the peak values of the filter in successive frames is consistent with the tracking performance. This is a useful reference criterion in designing a robust correlation filter for visual tracking.

cs.CV↗

arXiv2016

Zero-Shot Learning via Joint Latent Similarity Embedding

Zero-shot recognition (ZSR) deals with the problem of predicting class labels for target domain instances based on source domain side information (e.g. attributes) of unseen classes. We formulate ZSR as a binary prediction problem. Our resulting classifier is class-independent. It takes an arbitrary pair of source and target domain instances as input and predicts whether or not they come from the same class, i.e. whether there is a match. We model the posterior probability of a match since it is a sufficient statistic and propose a latent probabilistic model in this context. We develop a joint discriminative learning framework based on dictionary learning to jointly learn the parameters of our model for both domains, which ultimately leads to our class-independent classifier. Many of the existing embedding methods can be viewed as special cases of our probabilistic model. On ZSR our method shows 4.90\% improvement over the state-of-the-art in accuracy averaged across four benchmark datasets. We also adapt ZSR method for zero-shot retrieval and show 22.45\% improvement accordingly in mean average precision (mAP).

cs.CV↗

arXiv2016

Efficient Training of Very Deep Neural Networks for Supervised Hashing

In this paper, we propose training very deep neural networks (DNNs) for supervised learning of hash codes. Existing methods in this context train relatively "shallow" networks limited by the issues arising in back propagation (e.e. vanishing gradients) as well as computational efficiency. We propose a novel and efficient training algorithm inspired by alternating direction method of multipliers (ADMM) that overcomes some of these limitations. Our method decomposes the training process into independent layer-wise local updates through auxiliary variables. Empirically we observe that our training algorithm always converges and its computational complexity is linearly proportional to the number of edges in the networks. Empirically we manage to train DNNs with 64 hidden layers and 1024 nodes per layer for supervised hashing in about 3 hours using a single GPU. Our proposed very deep supervised hashing (VDSH) method significantly outperforms the state-of-the-art on several benchmark datasets.

cs.CV↗

arXiv2015

Zero-Shot Learning via Semantic Similarity Embedding

In this paper we consider a version of the zero-shot learning problem where seen class source and target domain data are provided. The goal during test-time is to accurately predict the class label of an unseen target domain instance based on revealed source domain side information (\eg attributes) for unseen classes. Our method is based on viewing each source or target data as a mixture of seen class proportions and we postulate that the mixture patterns have to be similar if the two instances belong to the same unseen class. This perspective leads us to learning source/target embedding functions that map an arbitrary source/target domain data into a same semantic space where similarity can be readily measured. We develop a max-margin framework to learn these similarity functions and jointly optimize parameters by means of cross validation. Our test results are compelling, leading to significant improvement in terms of accuracy on most benchmark datasets for zero-shot recognition.

cs.CV↗

arXiv2015

Group Membership Prediction

The group membership prediction (GMP) problem involves predicting whether or not a collection of instances share a certain semantic property. For instance, in kinship verification given a collection of images, the goal is to predict whether or not they share a {\it familial} relationship. In this context we propose a novel probability model and introduce latent {\em view-specific} and {\em view-shared} random variables to jointly account for the view-specific appearance and cross-view similarities among data instances. Our model posits that data from each view is independent conditioned on the shared variables. This postulate leads to a parametric probability model that decomposes group membership likelihood into a tensor product of data-independent parameters and data-dependent factors. We propose learning the data-independent parameters in a discriminative way with bilinear classifiers, and test our prediction algorithm on challenging visual recognition tasks such as multi-camera person re-identification and kinship verification. On most benchmark datasets, our method can significantly outperform the current state-of-the-art.

cs.CV↗

arXiv2015

PRISM: Person Re-Identification via Structured Matching

Person re-identification (re-id), an emerging problem in visual surveillance, deals with maintaining entities of individuals whilst they traverse various locations surveilled by a camera network. From a visual perspective re-id is challenging due to significant changes in visual appearance of individuals in cameras with different pose, illumination and calibration. Globally the challenge arises from the need to maintain structurally consistent matches among all the individual entities across different camera views. We propose PRISM, a structured matching method to jointly account for these challenges. We view the global problem as a weighted graph matching problem and estimate edge weights by learning to predict them based on the co-occurrences of visual patterns in the training examples. These co-occurrence based scores in turn account for appearance changes by inferring likely and unlikely visual co-occurrences appearing in training instances. We implement PRISM on single shot and multi-shot scenarios. PRISM uniformly outperforms state-of-the-art in terms of matching rate while being computationally efficient.

cs.CV↗

arXiv2014

A Novel Visual Word Co-occurrence Model for Person Re-identification

Person re-identification aims to maintain the identity of an individual in diverse locations through different non-overlapping camera views. The problem is fundamentally challenging due to appearance variations resulting from differing poses, illumination and configurations of camera views. To deal with these difficulties, we propose a novel visual word co-occurrence model. We first map each pixel of an image to a visual word using a codebook, which is learned in an unsupervised manner. The appearance transformation between camera views is encoded by a co-occurrence matrix of visual word joint distributions in probe and gallery images. Our appearance model naturally accounts for spatial similarities and variations caused by pose, illumination & configuration change across camera views. Linear SVMs are then trained as classifiers using these co-occurrence descriptors. On the VIPeR and CUHK Campus benchmark datasets, our method achieves 83.86% and 85.49% at rank-15 on the Cumulative Match Characteristic (CMC) curves, and beats the state-of-the-art results by 10.44% and 22.27%.

cs.CV↗

arXiv2014

Object Proposal Generation using Two-Stage Cascade SVMs

Object proposal algorithms have shown great promise as a first step for object recognition and detection. Good object proposal generation algorithms require high object recall rate as well as low computational cost, because generating object proposals is usually utilized as a preprocessing step. The problem of how to accelerate the object proposal generation and evaluation process without decreasing recall is thus of great interest. In this paper, we propose a new object proposal generation method using two-stage cascade SVMs, where in the first stage linear filters are learned for predefined quantized scales/aspect-ratios independently, and in the second stage a global linear classifier is learned across all the quantized scales/aspect-ratios for calibration, so that all the proposals can be compared properly. The proposals with highest scores are our final output. Specifically, we explain our scale/aspect-ratio quantization scheme, and investigate the effects of combinations of $\ell_1$ and $\ell_2$ regularizers in cascade SVMs with/without ranking constraints in learning. Comprehensive experiments on VOC2007 dataset are conducted, and our results achieve the state-of-the-art performance with high object recall rate and high computational efficiency. Besides, our method has been demonstrated to be suitable for not only class-specific but also generic object proposal generation.

cs.CV↗

arXiv2014

RAPID: Rapidly Accelerated Proximal Gradient Algorithms for Convex Minimization

In this paper, we propose a new algorithm to speed-up the convergence of accelerated proximal gradient (APG) methods. In order to minimize a convex function $f(\mathbf{x})$, our algorithm introduces a simple line search step after each proximal gradient step in APG so that a biconvex function $f(θ\mathbf{x})$ is minimized over scalar variable $θ>0$ while fixing variable $\mathbf{x}$. We propose two new ways of constructing the auxiliary variables in APG based on the intermediate solutions of the proximal gradient and the line search steps. We prove that at arbitrary iteration step $t (t\geq1)$, our algorithm can achieve a smaller upper-bound for the gap between the current and optimal objective values than those in the traditional APG methods such as FISTA, making it converge faster in practice. In fact, our algorithm can be potentially applied to many important convex optimization problems, such as sparse linear regression and kernel SVMs. Our experimental results clearly demonstrate that our algorithm converges faster than APG in all of the applications above, even comparable to some sophisticated solvers.

stat.ML↗

arXiv2014

Regularization for Multiple Kernel Learning via Sum-Product Networks

In this paper, we are interested in constructing general graph-based regularizers for multiple kernel learning (MKL) given a structure which is used to describe the way of combining basis kernels. Such structures are represented by sum-product networks (SPNs) in our method. Accordingly we propose a new convex regularization method for MLK based on a path-dependent kernel weighting function which encodes the entire SPN structure in our method. Under certain conditions and from the view of probability, this function can be considered to follow multinomial distributions over the weights associated with product nodes in SPNs. We also analyze the convexity of our regularizer and the complexity of our induced classifiers, and further propose an efficient wrapper algorithm to optimize our formulation. In our experiments, we apply our method to ......

stat.ML↗