Research papers and code for "Pengfei Zhu":
We exam various geometric active contour methods for radar image segmentation. Due to special properties of radar images, we propose our new model based on modified Chan-Vese functional. Our method is efficient in separating non-meteorological noises from meteorological images.

Click to Read Paper and Get Code
We characterize the asymptotic performance of nonparametric goodness of fit testing, otherwise known as universal hypothesis testing in information theory and statistics. The exponential decay rate of the type-II error probability is used as the asymptotic performance metric, and an optimal test achieves the maximum rate subject to a constant level constraint on the type-I error probability. We show that two classes of Maximum Mean Discrepancy (MMD) based tests attain this optimality on $\mathbb R^d$, while the quadratic-time Kernel Stein Discrepancy (KSD) based tests achieve the same exponential decay rate under an asymptotic level constraint. With bootstrap thresholds, these kernel based tests have similar statistical performance in our experiments of finite samples. Key to our approach are Sanov's theorem~in large deviation theory and the weak convergence properties of the MMD and KSD.

* 12 pages
Click to Read Paper and Get Code
Machine reading comprehension is a task to model relationship between passage and query. In terms of deep learning framework, most of state-of-the-art models simply concatenate word and character level representations, which has been shown suboptimal for the concerned task. In this paper, we empirically explore different integration strategies of word and character embeddings and propose a character-augmented reader which attends character-level representation to augment word embedding with a short list to improve word representations, especially for rare words. Experimental results show that the proposed approach helps the baseline model significantly outperform state-of-the-art baselines on various public benchmarks.

* Accepted by NLPCC 2018. arXiv admin note: text overlap with arXiv:1806.09103
Click to Read Paper and Get Code
Deep Reinforcement Learning (RL) recently emerged as one of the most competitive approaches for learning in sequential decision making problems with fully observable environments, e.g., computer Go. However, very little work has been done in deep RL to handle partially observable environments. We propose a new architecture called Action-specific Deep Recurrent Q-Network (ADRQN) to enhance learning performance in partially observable domains. Actions are encoded by a fully connected layer and coupled with a convolutional observation to form an action-observation pair. The time series of action-observation pairs are then integrated by an LSTM layer that learns latent states based on which a fully connected layer computes Q-values as in conventional Deep Q-Networks (DQNs). We demonstrate the effectiveness of our new architecture in several partially observable domains, including flickering Atari games.

* 7 pages, 6 figures, 3 tables
Click to Read Paper and Get Code
Along with the deraining performance improvement of deep networks, their structures and learning become more and more complicated and diverse, making it difficult to analyze the contribution of various network modules when developing new deraining networks. To handle this issue, this paper provides a better and simpler baseline deraining network by considering network architecture, input and output, and loss functions. Specifically, by repeatedly unfolding a shallow ResNet, progressive ResNet (PRN) is proposed to take advantage of recursive computation. A recurrent layer is further introduced to exploit the dependencies of deep features across stages, forming our progressive recurrent network (PReNet). Furthermore, intra-stage recursive computation of ResNet can be adopted in PRN and PReNet to notably reduce network parameters with graceful degradation in deraining performance. For network input and output, we take both stage-wise result and original rainy image as input to each ResNet and finally output the prediction of {residual image}. As for loss functions, single MSE or negative SSIM losses are sufficient to train PRN and PReNet. Experiments show that PRN and PReNet perform favorably on both synthetic and real rainy images. Considering its simplicity, efficiency and effectiveness, our models are expected to serve as a suitable baseline in future deraining research. The source codes are available at https://github.com/csdwren/PReNet.

* The codes, pre-trained models and results are available at https://github.com/csdwren/PReNet
Click to Read Paper and Get Code
Multi-turn conversation understanding is a major challenge for building intelligent dialogue systems. This work focuses on retrieval-based response matching for multi-turn conversation whose related work simply concatenates the conversation utterances, ignoring the interactions among previous utterances for context modeling. In this paper, we formulate previous utterances into context using a proposed deep utterance aggregation model to form a fine-grained context representation. In detail, a self-matching attention is first introduced to route the vital information in each utterance. Then the model matches a response with each refined utterance and the final matching score is obtained after attentive turns aggregation. Experimental results show our model outperforms the state-of-the-art methods on three multi-turn conversation benchmarks, including a newly introduced e-commerce dialogue corpus.

* COLING 2018, pages 3740-3752
* Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018)
Click to Read Paper and Get Code
Traditional chatbots usually need a mass of human dialogue data, especially when using supervised machine learning method. Though they can easily deal with single-turn question answering, for multi-turn the performance is usually unsatisfactory. In this paper, we present Lingke, an information retrieval augmented chatbot which is able to answer questions based on given product introduction document and deal with multi-turn conversations. We will introduce a fine-grained pipeline processing to distill responses based on unstructured documents, and attentive sequential context-response matching for multi-turn conversations.

* Accepted by COLING 2018 demonstration paper
Click to Read Paper and Get Code
In this paper we present a large-scale visual object detection and tracking benchmark, named VisDrone2018, aiming at advancing visual understanding tasks on the drone platform. The images and video sequences in the benchmark were captured over various urban/suburban areas of 14 different cities across China from north to south. Specifically, VisDrone2018 consists of 263 video clips and 10,209 images (no overlap with video clips) with rich annotations, including object bounding boxes, object categories, occlusion, truncation ratios, etc. With intensive amount of effort, our benchmark has more than 2.5 million annotated instances in 179,264 images/video frames. Being the largest such dataset ever published, the benchmark enables extensive evaluation and investigation of visual analysis algorithms on the drone platform. In particular, we design four popular tasks with the benchmark, including object detection in images, object detection in videos, single object tracking, and multi-object tracking. All these tasks are extremely challenging in the proposed dataset due to factors such as occlusion, large scale and pose variation, and fast motion. We hope the benchmark largely boost the research and development in visual analysis on drone platforms.

* 11 pages, 11 figures
Click to Read Paper and Get Code
With the rapid development of digital imaging and communication technologies, image set based face recognition (ISFR) is becoming increasingly important. One key issue of ISFR is how to effectively and efficiently represent the query face image set by using the gallery face image sets. The set-to-set distance based methods ignore the relationship between gallery sets, while representing the query set images individually over the gallery sets ignores the correlation between query set images. In this paper, we propose a novel image set based collaborative representation and classification method for ISFR. By modeling the query set as a convex or regularized hull, we represent this hull collaboratively over all the gallery sets. With the resolved representation coefficients, the distance between the query set and each gallery set can then be calculated for classification. The proposed model naturally and effectively extends the image based collaborative representation to an image set based one, and our extensive experiments on benchmark ISFR databases show the superiority of the proposed method to state-of-the-art ISFR methods under different set sizes in terms of both recognition rate and efficiency.

Click to Read Paper and Get Code
Multi-view subspace clustering aims to discover the inherent structure by fusing multi-view complementary information. Most existing methods first extract multiple types of hand-crafted features and then learn a joint affinity matrix for clustering. The disadvantage lies in two aspects: 1) Multi-view relations are not embedded into feature learning. 2) The end-to-end learning manner of deep learning is not well used in multi-view clustering. To address the above issues, we propose a novel multi-view deep subspace clustering network (MvDSCN) by learning a multi-view self-representation matrix in an end-to-end manner. MvDSCN consists of two sub-networks, i.e., diversity network (Dnet) and universality network (Unet). A latent space is built upon deep convolutional auto-encoders and a self-representation matrix is learned in the latent space using a fully connected layer. Dnet learns view-specific self-representation matrices while Unet learns a common self-representation matrix for all views. To exploit the complementarity of multi-view representations, Hilbert Schmidt Independence Criterion (HSIC) is introduced as a diversity regularization, which can capture the non-linear and high-order inter-view relations. As different views share the same label space, the self-representation matrices of each view are aligned to the common one by a universality regularization. Experiments on both multi-feature and multi-modality learning validate the superiority of the proposed multi-view subspace clustering model.

* Submitted to the IEEE Transactions on Image Processing (TIP)
Click to Read Paper and Get Code
We present a Few-Shot Relation Classification Dataset (FewRel), consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers. The relation of each sentence is first recognized by distant supervision methods, and then filtered by crowdworkers. We adapt the most recent state-of-the-art few-shot learning methods for relation classification and conduct a thorough evaluation of these methods. Empirical results show that even the most competitive few-shot learning models struggle on this task, especially as compared with humans. We also show that a range of different reasoning skills are needed to solve our task. These results indicate that few-shot relation classification remains an open problem and still requires further research. Our detailed analysis points multiple directions for future research. All details and resources about the dataset and baselines are released on http://zhuhao.me/fewrel.

* EMNLP 2018. The first four authors contribute equally. The order is determined by dice rolling. Visit our website http://zhuhao.me/fewrel
Click to Read Paper and Get Code
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones. The challenge consisted of two tracks. In the first one, participants were solving the classical image super-resolution problem with a bicubic downscaling factor of 4. The second track was aimed at real-world photo enhancement, and the goal was to map low-quality photos from the iPhone 3GS device to the same photos captured with a DSLR camera. The target metric used in this challenge combined the runtime, PSNR scores and solutions' perceptual results measured in the user study. To ensure the efficiency of the submitted models, we additionally measured their runtime and memory requirements on Android smartphones. The proposed solutions significantly improved baseline results defining the state-of-the-art for image enhancement on smartphones.

Click to Read Paper and Get Code