Xiaodong He

is this you? claim profile


Deputy Managing Director of JD AI Research and Head of the Deep learning, NLP and Speech Lab, and a Technical Vice President of JD.com. He is also an Affiliate Professor at the University of Washington (Seattle)

  • Mappa Mundi: An Interactive Artistic Mind Map Generator with Artificial Imagination

    We present a novel real-time, collaborative, and interactive AI painting system, Mappa Mundi, for artistic Mind Map creation. The system consists of a voice-based input interface, an automatic topic expansion module, and an image projection module. The key innovation is to inject Artificial Imagination into painting creation by considering lexical and phonological similarities of language, learning and inheriting artist's original painting style, and applying the principles of Dadaism and impossibility of improvisation. Our system indicates that AI and artist can collaborate seamlessly to create imaginative artistic painting and Mappa Mundi has been applied in art exhibition in UCCA, Beijing

    05/09/2019 ∙ by Ruixue Liu, et al. ∙ 20 share

    read it

  • Object-driven Text-to-Image Synthesis via Adversarial Training

    In this paper, we propose Object-driven Attentive Generative Adversarial Newtorks (Obj-GANs) that allow object-centered text-to-image synthesis for complex scenes. Following the two-step (layout-image) generation process, a novel object-driven attentive image generator is proposed to synthesize salient objects by paying attention to the most relevant words in the text description and the pre-generated semantic layout. In addition, a new Fast R-CNN based object-wise discriminator is proposed to provide rich object-wise discrimination signals on whether the synthesized object matches the text description and the pre-generated layout. The proposed Obj-GAN significantly outperforms the previous state of the art in various metrics on the large-scale COCO benchmark, increasing the Inception score by 27 score by 11 the new object-driven attention is provided through analyzing their mechanisms and visualizing their attention layers, showing insights of how the proposed model generates complex scenes in high quality.

    02/27/2019 ∙ by Wenbo Li, et al. ∙ 6 share

    read it

  • End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion

    Knowledge graph embedding has been an active research topic for knowledge base completion, with progressive improvement from the initial TransE, TransH, DistMult et al to the current state-of-the-art ConvE. ConvE uses 2D convolution over embeddings and multiple layers of nonlinear features to model knowledge graphs. The model can be efficiently trained and scalable to large knowledge graphs. However, there is no structure enforcement in the embedding space of ConvE. The recent graph convolutional network (GCN) provides another way of learning graph node embedding by successfully utilizing graph connectivity structure. In this work, we propose a novel end-to-end Structure-Aware Convolutional Networks (SACN) that take the benefit of GCN and ConvE together. SACN consists of an encoder of a weighted graph convolutional network (WGCN), and a decoder of a convolutional network called Conv-TransE. WGCN utilizes knowledge graph node structure, node attributes and relation types. It has learnable weights that collect adaptive amount of information from neighboring graph nodes, resulting in more accurate embeddings of graph nodes. In addition, the node attributes are added as the nodes and are easily integrated into the WGCN. The decoder Conv-TransE extends the state-of-the-art ConvE to be translational between entities and relations while keeps the state-of-the-art performance as ConvE. We demonstrate the effectiveness of our proposed SACN model on standard FB15k-237 and WN18RR datasets, and present about 10 improvement over the state-of-the-art ConvE in terms of HITS@1, HITS@3 and HITS@10.

    11/11/2018 ∙ by Chao Shang, et al. ∙ 4 share

    read it

  • Multiple instance learning with graph neural networks

    Multiple instance learning (MIL) aims to learn the mapping between a bag of instances and the bag-level label. In this paper, we propose a new end-to-end graph neural network (GNN) based algorithm for MIL: we treat each bag as a graph and use GNN to learn the bag embedding, in order to explore the useful structural information among instances in bags. The final graph representation is fed into a classifier for label prediction. Our algorithm is the first attempt to use GNN for MIL. We empirically show that the proposed algorithm achieves the state of the art performance on several popular MIL data sets without losing model interpretability.

    06/12/2019 ∙ by Ming Tu, et al. ∙ 3 share

    read it

  • AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks

    In this paper, we propose an Attentional Generative Adversarial Network (AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation. With a novel attentional generative network, the AttnGAN can synthesize fine-grained details at different subregions of the image by paying attentions to the relevant words in the natural language description. In addition, a deep attentional multimodal similarity model is proposed to compute a fine-grained image-text matching loss for training the generator. The proposed AttnGAN significantly outperforms the previous state of the art, boosting the best reported inception score by 14.14 dataset and 170.25 is also performed by visualizing the attention layers of the AttnGAN. It for the first time shows that the layered attentional GAN is able to automatically select the condition at the word level for generating different parts of the image.

    11/28/2017 ∙ by Tao Xu, et al. ∙ 0 share

    read it

  • On the Discrimination-Generalization Tradeoff in GANs

    Generative adversarial training can be generally understood as minimizing certain moment matching loss defined by a set of discriminator functions, typically neural networks. The discriminator set should be large enough to be able to uniquely identify the true distribution (discriminative), and also be small enough to go beyond memorizing samples (generalizable). In this paper, we show that a discriminator set is guaranteed to be discriminative whenever its linear span is dense in the set of bounded continuous functions. This is a very mild condition satisfied even by neural networks with a single neuron. Further, we develop generalization bounds between the learned distribution and true distribution under different evaluation metrics. When evaluated with neural or Wasserstein distances, our bounds show that generalization is guaranteed as long as the discriminator set is small enough, regardless of the size of the generator or hypothesis set. When evaluated with KL divergence, our bound provides an explanation on the counter-intuitive behaviors of testing likelihood in GAN training. Our analysis sheds lights on understanding the practical performance of GANs.

    11/07/2017 ∙ by Pengchuan Zhang, et al. ∙ 0 share

    read it

  • Tensor Product Generation Networks

    We present a new tensor product generation network (TPGN) that generates natural language descriptions for images. The model has a novel architecture that instantiates a general framework for encoding and processing symbolic structure through neural network computation. This framework is built on Tensor Product Representations (TPRs). We evaluated the proposed TPGN on the MS COCO image captioning task. The experimental results show that the TPGN outperforms the LSTM based state-of-the-art baseline with a significant margin. Further, we show that our caption generation model can be interpreted as generating sequences of grammatical categories and retrieving words by their categories from a plan encoded as a distributed representation.

    09/26/2017 ∙ by Qiuyuan Huang, et al. ∙ 0 share

    read it

  • Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration

    Tracking of multiple objects is an important application in AI City geared towards solving salient problems related to safety and congestion in an urban environment. Frequent occlusion in traffic surveillance has been a major problem in this research field. In this challenge, we propose a model-based vehicle localization method, which builds a kernel at each patch of the 3D deformable vehicle model and associates them with constraints in 3D space. The proposed method utilizes shape fitness evaluation besides color information to track vehicle objects robustly and efficiently. To build 3D car models in a fully unsupervised manner, we also implement evolutionary camera self-calibration from tracking of walking humans to automatically compute camera parameters. Additionally, the segmented foreground masks which are crucial to 3D modeling and camera self-calibration are adaptively refined by multiple-kernel feedback from tracking. For object detection/classification, the state-of-the-art single shot multibox detector (SSD) is adopted to train and test on the NVIDIA AI City Dataset. To improve the accuracy on categories with only few objects, like bus, bicycle and motorcycle, we also employ the pretrained model from YOLO9000 with multi-scale testing. We combine the results from SSD and YOLO9000 based on ensemble learning. Experiments show that our proposed tracking system outperforms both state-of-the-art of tracking by segmentation and tracking by detection.

    08/22/2017 ∙ by Zheng Tang, et al. ∙ 0 share

    read it

  • Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

    Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. In this work, we propose a combined bottom-up and top-down attention mechanism that enables attention to be calculated at the level of objects and other salient image regions. This is the natural basis for attention to be considered. Within our approach, the bottom-up mechanism (based on Faster R-CNN) proposes image regions, each with an associated feature vector, while the top-down mechanism determines feature weightings. Applying this approach to image captioning, our results on the MSCOCO test server establish a new state-of-the-art for the task, improving the best published result in terms of CIDEr score from 114.7 to 117.9 and BLEU-4 from 35.2 to 36.9. Demonstrating the broad applicability of the method, applying the same approach to VQA we obtain first place in the 2017 VQA Challenge.

    07/25/2017 ∙ by Peter Anderson, et al. ∙ 0 share

    read it

  • Basic Reasoning with Tensor Product Representations

    In this paper we present the initial development of a general theory for mapping inference in predicate logic to computation over Tensor Product Representations (TPRs; Smolensky (1990), Smolensky & Legendre (2006)). After an initial brief synopsis of TPRs (Section 0), we begin with particular examples of inference with TPRs in the 'bAbI' question-answering task of Weston et al. (2015) (Section 1). We then present a simplification of the general analysis that suffices for the bAbI task (Section 2). Finally, we lay out the general treatment of inference over TPRs (Section 3). We also show the simplification in Section 2 derives the inference methods described in Lee et al. (2016); this shows how the simple methods of Lee et al. (2016) can be formally extended to more general reasoning tasks.

    01/12/2016 ∙ by Paul Smolensky, et al. ∙ 0 share

    read it

  • CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise

    In this paper, we study the problem of learning image classification models with label noise. Existing approaches depending on human supervision are generally not scalable as manually identifying correct or incorrect labels is timeconsuming, whereas approaches not relying on human supervision are scalable but less effective. To reduce the amount of human supervision for label noise cleaning, we introduce CleanNet, a joint neural embedding network, which only requires a fraction of the classes being manually verified to provide the knowledge of label noise that can be transferred to other classes. We further integrate CleanNet and conventional convolutional neural network classifier into one framework for image classification learning. We demonstrate the effectiveness of the proposed algorithm on both of the label noise detection task and the image classification on noisy data task on several large-scale datasets. Experimental results show that CleanNet can reduce label noise detection error rate on held-out classes where no human supervision available by 41.5 the performance gain of verifying all images with only 3.2 an image classification task.

    11/20/2017 ∙ by Kuang-Huei Lee, et al. ∙ 0 share

    read it