Research papers and code for "Peng Zhou":
In many large-scale machine learning applications, data are accumulated with time, and thus, an appropriate model should be able to update in an online paradigm. Moreover, as the whole data volume is unknown when constructing the model, it is desired to scan each data item only once with a storage independent with the data volume. It is also noteworthy that the distribution underlying may change during the data accumulation procedure. To handle such tasks, in this paper we propose DFOP, a distribution-free one-pass learning approach. This approach works well when distribution change occurs during data accumulation, without requiring prior knowledge about the change. Every data item can be discarded once it has been scanned. Besides, theoretical guarantee shows that the estimate error, under a mild assumption, decreases until convergence with high probability. The performance of DFOP for both regression and classification are validated in experiments.

Click to Read Paper and Get Code
In this paper, we study how to make clustering benefiting from differentiable programming whose basic idea is treating the neural network as a language instead of a machine learning method. To this end, we recast the vanilla $k$-means as a novel feedforward neural network in an elegant way. Our contribution is two-fold. On the one hand, the proposed \textit{k}-meansNet is a neural network implementation of the vanilla \textit{k}-means, which enjoys four advantages highly desired, i.e., robustness to initialization, fast inference speed, the capability of handling new coming data, and provable convergence. On the other hand, this work may provide novel insights into differentiable programming. More specifically, most existing differentiable programming works unroll an \textbf{optimizer} as a \textbf{recurrent neural network}, namely, the neural network is employed to solve an existing optimization problem. In contrast, we reformulate the \textbf{objective function} of \textit{k}-means as a \textbf{feedforward neural network}, namely, we employ the neural network to describe a problem. In such a way, we advance the boundary of differentiable programming by treating the neural network as from an alternative optimization approach to the problem formulation. Extensive experimental studies show that our method achieves promising performance comparing with 12 clustering methods on some challenging datasets.

* 10 pages
Click to Read Paper and Get Code
This paper presents an improvement to model learning when using multi-class LogitBoost for classification. Motivated by the statistical view, LogitBoost can be seen as additive tree regression. Two important factors in this setting are: 1) coupled classifier output due to a sum-to-zero constraint, and 2) the dense Hessian matrices that arise when computing tree node split gain and node value fittings. In general, this setting is too complicated for a tractable model learning algorithm. However, too aggressive simplification of the setting may lead to degraded performance. For example, the original LogitBoost is outperformed by ABC-LogitBoost due to the latter's more careful treatment of the above two factors. In this paper we propose techniques to address the two main difficulties of the LogitBoost setting: 1) we adopt a vector tree (i.e. each node value is vector) that enforces a sum-to-zero constraint, and 2) we use an adaptive block coordinate descent that exploits the dense Hessian when computing tree split gain and node values. Higher classification accuracy and faster convergence rates are observed for a range of public data sets when compared to both the original and the ABC-LogitBoost implementations.

* 8-pages camera ready version for ICML2012
Click to Read Paper and Get Code
We consider the thresholding bandit problem, whose goal is to find arms of mean rewards above a given threshold $\theta$, with a fixed budget of $T$ trials. We introduce LSA, a new, simple and anytime algorithm that aims to minimize the aggregate regret (or the expected number of mis-classified arms). We prove that our algorithm is instance-wise asymptotically optimal. We also provide comprehensive empirical results to demonstrate the algorithm's superior performance over existing algorithms under a variety of different scenarios.

Click to Read Paper and Get Code
Multiple-choice reading comprehension (MCRC) is the task of selecting the correct answer from multiple options given a question and an article. Existing MCRC models typically either read each option independently or compute a fixed-length representation for each option before comparing them. However, humans typically compare the options at multiple-granularity level before reading the article in detail to make reasoning more efficient. Mimicking humans, we propose an option comparison network (OCN) for MCRC which compares options at word-level to better identify their correlations to help reasoning. Specially, each option is encoded into a vector sequence using a skimmer to retain fine-grained information as much as possible. An attention mechanism is leveraged to compare these sequences vector-by-vector to identify more subtle correlations between options, which is potentially valuable for reasoning. Experimental results on the human English exam MCRC dataset RACE show that our model outperforms existing methods significantly. Moreover, it is also the first model that surpasses Amazon Mechanical Turker performance on the whole dataset.

* 6 pages, 2 tables
Click to Read Paper and Get Code
In many real-world applications, data are often collected in the form of stream, and thus the distribution usually changes in nature, which is referred as concept drift in literature. We propose a novel and effective approach to handle concept drift via model reuse, leveraging previous knowledge by reusing models. Each model is associated with a weight representing its reusability towards current data, and the weight is adaptively adjusted according to the model performance. We provide generalization and regret analysis. Experimental results also validate the superiority of our approach on both synthetic and real-world datasets.

Click to Read Paper and Get Code
Graph Neural Networks (GNNs) have been popularly used for analyzing non-Euclidean data such as social network data and biological data. Despite their success, the design of graph neural networks requires a lot of manual work and domain knowledge. In this paper, we propose a Graph Neural Architecture Search method (GraphNAS for short) that enables automatic search of the best graph neural architecture based on reinforcement learning. Specifically, GraphNAS first uses a recurrent network to generate variable-length strings that describe the architectures of graph neural networks, and then trains the recurrent network with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation data set. Extensive experimental results on node classification tasks in both transductive and inductive learning settings demonstrate that GraphNAS can achieve consistently better performance on the Cora, Citeseer, Pubmed citation network, and protein-protein interaction network. On node classification tasks, GraphNAS can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy.

Click to Read Paper and Get Code
Image manipulation detection is different from traditional semantic object detection because it pays more attention to tampering artifacts than to image content, which suggests that richer features need to be learned. We propose a two-stream Faster R-CNN network and train it endto- end to detect the tampered regions given a manipulated image. One of the two streams is an RGB stream whose purpose is to extract features from the RGB image input to find tampering artifacts like strong contrast difference, unnatural tampered boundaries, and so on. The other is a noise stream that leverages the noise features extracted from a steganalysis rich model filter layer to discover the noise inconsistency between authentic and tampered regions. We then fuse features from the two streams through a bilinear pooling layer to further incorporate spatial co-occurrence of these two modalities. Experiments on four standard image manipulation datasets demonstrate that our two-stream framework outperforms each individual stream, and also achieves state-of-the-art performance compared to alternative methods with robustness to resizing and compression.

* CVPR 2018 Camera Ready
Click to Read Paper and Get Code
We propose a two-stream network for face tampering detection. We train GoogLeNet to detect tampering artifacts in a face classification stream, and train a patch based triplet network to leverage features capturing local noise residuals and camera characteristics as a second stream. In addition, we use two different online face swapping applications to create a new dataset that consists of 2010 tampered images, each of which contains a tampered face. We evaluate the proposed two-stream network on our newly collected dataset. Experimental results demonstrate the effectiveness of our method.

* 2017 CVPR workshop
Click to Read Paper and Get Code
Automatic extraction of temporal information in text is an important component of natural language understanding. It involves two basic tasks: (1) Understanding time expressions that are mentioned explicitly in text (e.g., February 27, 1998 or tomorrow), and (2) Understanding temporal information that is conveyed implicitly via relations. In this paper, we introduce CogCompTime, a system that has these two important functionalities. It incorporates the most recent progress, achieves state-of-the-art performance, and is publicly available.1 We believe that this demo will be useful for multiple time-aware applications and provide valuable insight for future research in temporal understanding.

* Demo paper appeared in EMNLP'18. 6 pages and 3 figures
Click to Read Paper and Get Code
Open Neural Network Exchange (ONNX) is an open format to represent AI models and is supported by many machine learning frameworks. While ONNX defines unified and portable computation operators across various frameworks, the conformance tests for those operators are insufficient, which makes it difficult to verify if an operator's behavior in an ONNX backend implementation complies with the ONNX standard. In this paper, we present the first automatic unit test generator named Sionnx for verifying the compliance of ONNX implementation. First, we propose a compact yet complete set of rules to describe the operator's attributes and the properties of its operands. Second, we design an Operator Specification Language (OSL) to provide a high-level description for the operator's syntax. Finally, through this easy-to-use specification language, we are able to build a full testing specification which leverages LLVM TableGen to automatically generate unit tests for ONNX operators with much large coverage. Sionnx is lightweight and flexible to support cross-framework verification. The Sionnx framework is open-sourced in the github repository (https://github.com/alibaba/Sionnx).

Click to Read Paper and Get Code
Goal-oriented reinforcement learning has recently been a practical framework for robotic manipulation tasks, in which an agent is required to reach a certain goal defined by a function on the state space. However, the sparsity of such reward definition makes traditional reinforcement learning algorithms very inefficient. Hindsight Experience Replay (HER), a recent advance, has greatly improved sample efficiency and practical applicability for such problems. It exploits previous replays by constructing imaginary goals in a simple heuristic way, acting like an implicit curriculum to alleviate the challenge of sparse reward signal. In this paper, we introduce Hindsight Goal Generation (HGG), a novel algorithmic framework that generates valuable hindsight goals which are easy for an agent to achieve in the short term and are also potential for guiding the agent to reach the actual goal in the long term. We have extensively evaluated our goal generation algorithm on a number of robotic manipulation tasks and demonstrated substantially improvement over the original HER in terms of sample efficiency.

Click to Read Paper and Get Code
This paper proposes a deep Convolutional Neural Network(CNN) with strong generalization ability for structural topology optimization. The architecture of the neural network is made up of encoding and decoding parts, which provide down- and up-sampling operations. In addition, a popular technique, namely U-Net, was adopted to improve the performance of the proposed neural network. The input of the neural network is a well-designed tensor with each channel includes different information for the problem, and the output is the layout of the optimal structure. To train the neural network, a large dataset is generated by a conventional topology optimization approach, i.e. SIMP. The performance of the proposed method was evaluated by comparing its efficiency and accuracy with SIMP on a series of typical optimization problems. Results show that a significant reduction in computation cost was achieved with little sacrifice on the optimality of design solutions. Furthermore, the proposed method can intelligently solve problems under boundary conditions not being included in the training dataset.

* 13 pages, 6 figures, The paper is under review to be published in the Structural and Multidisciplinary Optimization journal, Springer
Click to Read Paper and Get Code
This paper addresses the challenge of 6DoF pose estimation from a single RGB image under severe occlusion or truncation. Many recent works have shown that a two-stage approach, which first detects keypoints and then solves a Perspective-n-Point (PnP) problem for pose estimation, achieves remarkable performance. However, most of these methods only localize a set of sparse keypoints by regressing their image coordinates or heatmaps, which are sensitive to occlusion and truncation. Instead, we introduce a Pixel-wise Voting Network (PVNet) to regress pixel-wise unit vectors pointing to the keypoints and use these vectors to vote for keypoint locations using RANSAC. This creates a flexible representation for localizing occluded or truncated keypoints. Another important feature of this representation is that it provides uncertainties of keypoint locations that can be further leveraged by the PnP solver. Experiments show that the proposed approach outperforms the state of the art on the LINEMOD, Occlusion LINEMOD and YCB-Video datasets by a large margin, while being efficient for real-time pose estimation. We further create a Truncation LINEMOD dataset to validate the robustness of our approach against truncation. The code will be avaliable at https://zju-3dv.github.io/pvnet/.

* The first two authors contributed equally to this paper. Project page: https://zju-3dv.github.io/pvnet/
Click to Read Paper and Get Code
Traditional dictionary learning based CT reconstruction methods are patch-based and the features learned with these methods often contain shifted versions of the same features. To deal with these problems, the convolutional sparse coding (CSC) has been proposed and introduced into various applications. In this paper, inspired by the successful applications of CSC in the field of signal processing, we propose a novel sparse-view CT reconstruction method based on CSC with gradient regularization on feature maps. By directly working on whole image, which need not to divide the image into overlapped patches like dictionary learning based methods, the proposed method can maintain more details and avoid the artifacts caused by patch aggregation. Experimental results demonstrate that the proposed method has better performance than several existing algorithms in both qualitative and quantitative aspects.

Click to Read Paper and Get Code
As a key technique for enabling artificial intelligence, machine learning (ML) has been shown to be capable of solving complex problems without explicit programming. Motivated by its successful applications to many practical tasks like image recognition and recommendation systems, both industry and the research community have advocated the applications of ML in wireless communication. This paper comprehensively surveys the recent advances of the applications of ML in wireless communication, which are classified as: resource management in the MAC layer, networking and mobility management in the network layer, and localization in the application layer. The applications in resource management further include power control, spectrum management, backhaul management, cache management, beamformer design, and computation resource management, while ML-based networking focuses on the applications in base station (BS) clustering, BS switching control, user association, and routing. Each aspect is further categorized according to the adopted ML techniques. Additionally, given the extensiveness of the research area, challenges and unresolved issues are presented to facilitate future studies, where the topics of ML-based network slicing, infrastructure update to support ML-based paradigms, open data sets and platforms for researchers, theoretical guidance for ML implementation, and so on are discussed.

* 27 pages,8 figures
Click to Read Paper and Get Code
When learning from a batch of logged bandit feedback, the discrepancy between the policy to be learned and the off-policy training data imposes statistical and computational challenges. Unlike classical supervised learning and online learning settings, in batch contextual bandit learning, one only has access to a collection of logged feedback from the actions taken by a historical policy, and expect to learn a policy that takes good actions in possibly unseen contexts. Such a batch learning setting is ubiquitous in online and interactive systems, such as ad platforms and recommendation systems. Existing approaches based on inverse propensity weights, such as Inverse Propensity Scoring (IPS) and Policy Optimizer for Exponential Models (POEM), enjoy unbiasedness but often suffer from large mean squared error. In this work, we introduce a new approach named Maximum Likelihood Inverse Propensity Scoring (MLIPS) for batch learning from logged bandit feedback. Instead of using the given historical policy as the proposal in inverse propensity weights, we estimate a maximum likelihood surrogate policy based on the logged action-context pairs, and then use this surrogate policy as the proposal. We prove that MLIPS is asymptotically unbiased, and moreover, has a smaller nonasymptotic mean squared error than IPS. Such an error reduction phenomenon is somewhat surprising as the estimated surrogate policy is less accurate than the given historical policy. Results on multi-label classification problems and a large- scale ad placement dataset demonstrate the empirical effectiveness of MLIPS. Furthermore, the proposed surrogate policy technique is complementary to existing error reduction techniques, and when combined, is able to consistently boost the performance of several widely used approaches.

* 27 pages, 1 figure, 1 table
Click to Read Paper and Get Code
In recent years, we witnessed a huge success of Convolutional Neural Networks on the task of the image classification. However, these models are notoriously data hungry and require tons of training images to learn the parameters. In contrast, people are far better learner who can learn a new concept very fast with only a few samples. The plausible mysteries making the difference are two fundamental learning mechanisms: learning to learn and learning by analogy. In this paper, we attempt to investigate a new human-like learning method by organically combining these two mechanisms. In particular, we study how to generalize the classification parameters of previously learned concepts to a new concept. we first propose a novel Visual Analogy Network Embedded Regression (VANER) model to jointly learn a low-dimensional embedding space and a linear mapping function from the embedding space to classification parameters for base classes. We then propose an out-of-sample embedding method to learn the embedding of a new class represented by a few samples through its visual analogy with base classes. By inputting the learned embedding into VANER, we can derive the classification parameters for the new class.These classification parameters are purely generalized from base classes (i.e. transferred classification parameters), while the samples in the new class, although only a few, can also be exploited to generate a set of classification parameters (i.e. model classification parameters). Therefore, we further investigate the fusion strategy of the two kinds of parameters so that the prior knowledge and data knowledge can be fully leveraged. We also conduct extensive experiments on ImageNet and the results show that our method can consistently and significantly outperform state-of-the-art baselines.

Click to Read Paper and Get Code
Neural machine translation (NMT) aims at solving machine translation (MT) problems using neural networks and has exhibited promising results in recent years. However, most of the existing NMT models are shallow and there is still a performance gap between a single NMT model and the best conventional MT system. In this work, we introduce a new type of linear connections, named fast-forward connections, based on deep Long Short-Term Memory (LSTM) networks, and an interleaved bi-directional architecture for stacking the LSTM layers. Fast-forward connections play an essential role in propagating the gradients and building a deep topology of depth 16. On the WMT'14 English-to-French task, we achieve BLEU=37.7 with a single attention model, which outperforms the corresponding single shallow model by 6.2 BLEU points. This is the first time that a single NMT model achieves state-of-the-art performance and outperforms the best conventional model by 0.7 BLEU points. We can still achieve BLEU=36.3 even without using an attention mechanism. After special handling of unknown words and model ensembling, we obtain the best score reported to date on this task with BLEU=40.4. Our models are also validated on the more difficult WMT'14 English-to-German task.

* TACL 2016
Click to Read Paper and Get Code
Tracking living cells in video sequence is difficult, because of cell morphology and high similarities between cells. Tracking-by-detection methods are widely used in multi-cell tracking. We perform multi-cell tracking based on the cell centroid detection, and the performance of the detector has high impact on tracking performance. In this paper, UNet is utilized to extract inter-frame and intra-frame spatio-temporal information of cells. Detection performance of cells in mitotic phase is improved by multi-frame input. Good detection results facilitate multi-cell tracking. A mitosis detection algorithm is proposed to detect cell mitosis and the cell lineage is built up. Another UNet is utilized to acquire primary segmentation. Jointly using detection and primary segmentation, cells can be fine segmented in highly dense cell population. Experiments are conducted to evaluate the effectiveness of our method, and results show its state-of-the-art performance.

* Accepted by International Conference on Image and Graphics (ICIG 2019)
Click to Read Paper and Get Code