Recent studies have shown remarkable advances in 3D human pose estimation from monocular images, with the help of large-scale in-door 3D datasets and sophisticated network architectures. However, the generalizability to different environments remains an elusive goal. In this work, we propose a geometry-aware 3D representation for the human pose to address this limitation by using multiple views in a simple auto-encoder model at the training stage and only 2D keypoint information as supervision. A view synthesis framework is proposed to learn the shared 3D representation between viewpoints with synthesizing the human pose from one viewpoint to the other one. Instead of performing a direct transfer in the raw image-level, we propose a skeleton-based encoder-decoder mechanism to distil only pose-related representation in the latent space. A learning-based representation consistency constraint is further introduced to facilitate the robustness of latent 3D representation. Since the learnt representation encodes 3D geometry information, mapping it to 3D pose will be much easier than conventional frameworks that use an image or 2D coordinates as the input of 3D pose estimator. We demonstrate our approach on the task of 3D human pose estimation. Comprehensive experiments on three popular benchmarks show that our model can significantly improve the performance of state-of-the-art methods with simply injecting the representation as a robust 3D prior.
Despite the progress made in sentence-level NMT, current systems still fall short at achieving fluent, good quality translation for a full document. Recent works in context-aware NMT consider only a few previous sentences as context and may not scale to entire documents. To this end, we propose a novel and scalable top-down approach to hierarchical attention for context-aware NMT which uses sparse attention to selectively focus on relevant sentences in the document context and then attends to key words in those sentences. We also propose single-level attention approaches based on sentence or word-level information in the context. The document-level context representation, produced from these attention modules, is integrated into the encoder or decoder of the Transformer model depending on whether we use monolingual or bilingual context. Our experiments and evaluation on English-German datasets in different document MT settings show that our selective attention approach not only significantly outperforms context-agnostic baselines but also surpasses context-aware baselines in most cases.
Convolutional neural networks (CNN) have shown state-of-the-art results for low-level computer vision problems such as stereo and monocular disparity estimations, but still, have much room to further improve their performance in terms of accuracy, numbers of parameters, etc. Recent works have uncovered the advantages of using an unsupervised scheme to train CNN's to estimate monocular disparity, where only the relatively-easy-to-obtain stereo images are needed for training. We propose a novel encoder-decoder architecture that outperforms previous unsupervised monocular depth estimation networks by (i) taking into account ambiguities, (ii) efficient fusion between encoder and decoder features with rectangular convolutions and (iii) domain transformations between encoder and decoder. Our architecture outperforms the Monodepth baseline in all metrics, even with a considerable reduction of parameters. Furthermore, our architecture is capable of estimating a full disparity map in a single forward pass, whereas the baseline needs two passes. We perform extensive experiments to verify the effectiveness of our method on the KITTI dataset.
We propose a convolutional recurrent sparse auto-encoder model. The model consists of a sparse encoder, which is a convolutional extension of the learned ISTA (LISTA) method, and a linear convolutional decoder. Our strategy offers a simple method for learning a task-driven sparse convolutional dictionary (CD), and producing an approximate convolutional sparse code (CSC) over the learned dictionary. We trained the model to minimize reconstruction loss via gradient decent with back-propagation and have achieved competitive results to KSVD image denoising and to leading CSC methods in image inpainting requiring only a small fraction of their run-time.
Current approaches to Natural Language Generation (NLG) for dialog mainly focus on domain-specific, task-oriented applications (e.g. restaurant booking) using limited ontologies (up to 20 slot types), usually without considering the previous conversation context. Furthermore, these approaches require large amounts of data for each domain, and do not benefit from examples that may be available for other domains. This work explores the feasibility of applying statistical NLG to scenarios requiring larger ontologies, such as multi-domain dialog applications or open-domain question answering (QA) based on knowledge graphs. We model NLG through an Encoder-Decoder framework using a large dataset of interactions between real-world users and a conversational agent for open-domain QA. First, we investigate the impact of increasing the number of slot types on the generation quality and experiment with different partitions of the QA data with progressively larger ontologies (up to 369 slot types). Second, we perform multi-task learning experiments between open-domain QA and task-oriented dialog, and benchmark our model on a popular NLG dataset. Moreover, we experiment with using the conversational context as an additional input to improve response generation quality. Our experiments show the feasibility of learning statistical NLG models for open-domain QA with larger ontologies.
Encoder-decoder models have become an effective approach for sequence learning tasks like machine translation, image captioning and speech recognition, but have yet to show competitive results for handwritten text recognition. To this end, we propose an attention-based sequence-to-sequence model. It combines a convolutional neural network as a generic feature extractor with a recurrent neural network to encode both the visual information, as well as the temporal context between characters in the input image, and uses a separate recurrent neural network to decode the actual character sequence. We make experimental comparisons between various attention mechanisms and positional encodings, in order to find an appropriate alignment between the input and output sequence. The model can be trained end-to-end and the optional integration of a hybrid loss allows the encoder to retain an interpretable and usable output, if desired. We achieve competitive results on the IAM and ICFHR2016 READ data sets compared to the state-of-the-art without the use of a language model, and we significantly improve over any recent sequence-to-sequence approaches.
Lemmatization of standard languages is concerned with (i) abstracting over morphological differences and (ii) resolving token-lemma ambiguities of inflected words in order to map them to a dictionary headword. In the present paper we aim to improve lemmatization performance on a set of non-standard historical languages in which the difficulty is increased by an additional aspect (iii): spelling variation due to lacking orthographic standards. We approach lemmatization as a string-transduction task with an encoder-decoder architecture which we enrich with sentence context information using a hierarchical sentence encoder. We show significant improvements over the state-of-the-art when training the sentence encoder jointly for lemmatization and language modeling. Crucially, our architecture does not require POS or morphological annotations, which are not always available for historical corpora. Additionally, we also test the proposed model on a set of typologically diverse standard languages showing results on par or better than a model without enhanced sentence representations and previous state-of-the-art systems. Finally, to encourage future work on processing of non-standard varieties, we release the dataset of non-standard languages underlying the present study, based on openly accessible sources.
In this paper, we present a generative retrieval method for sponsored search engine, which uses neural machine translation (NMT) to generate keywords directly from query. This method is completely end-to-end, which skips query rewriting and relevance judging phases in traditional retrieval systems. Different from standard machine translation, the target space in the retrieval setting is a constrained closed set, where only committed keywords should be generated. We present a Trie-based pruning technique in beam search to address this problem. The biggest challenge in deploying this method into a real industrial environment is the latency impact of running the decoder. Self-normalized training coupled with Trie-based dynamic pruning dramatically reduces the inference time, yielding a speedup of more than 20 times. We also devise an mixed online-offline serving architecture to reduce the latency and CPU consumption. To encourage the NMT to generate new keywords uncovered by the existing system, training data is carefully selected. This model has been successfully applied in Baidu's commercial search engine as a supplementary retrieval branch, which has brought a remarkable revenue improvement of more than 10 percents.
Expert programmers' eye-movements during source code reading are valuable sources that are considered to be associated with their domain expertise. We advocate a vision of new intelligent systems incorporating expertise of experts for software development tasks, such as issue localization, comment generation, and code generation. We present a conceptual framework of neural autonomous agents based on imitation learning (IL), which enables agents to mimic the visual attention of an expert via his/her eye movement. In this framework, an autonomous agent is constructed as a context-based attention model that consists of encoder/decoder network and trained with state-action sequences generated by an experts' demonstration. Challenges to implement an IL-based autonomous agent specialized for software development task are discussed in this paper.
Multilayer switch networks are proposed as artificial generators of high-dimensional discrete data (e.g., binary vectors, categorical data, natural language, network log files, and discrete-valued time series). Unlike deconvolution networks which generate continuous-valued data and which consist of upsampling filters and reverse pooling layers, multilayer switch networks are composed of adaptive switches which model conditional distributions of discrete random variables. An interpretable, statistical framework is introduced for training these nonlinear networks based on a maximum-likelihood objective function. To learn network parameters, stochastic gradient descent is applied to the objective. This direct optimization is stable until convergence, and does not involve back-propagation over separate encoder and decoder networks, or adversarial training of dueling networks. While training remains tractable for moderately sized networks, Markov-chain Monte Carlo (MCMC) approximations of gradients are derived for deep networks which contain latent variables. The statistical framework is evaluated on synthetic data, high-dimensional binary data of handwritten digits, and web-crawled natural language data. Aspects of the model's framework such as interpretability, computational complexity, and generalization ability are discussed.
Although variational autoencoders (VAEs) represent a widely influential deep generative model, many aspects of the underlying energy function remain poorly understood. In particular, it is commonly believed that Gaussian encoder/decoder assumptions reduce the effectiveness of VAEs in generating realistic samples. In this regard, we rigorously analyze the VAE objective, differentiating situations where this belief is and is not actually true. We then leverage the corresponding insights to develop a simple VAE enhancement that requires no additional hyperparameters or sensitive tuning. Quantitatively, this proposal produces crisp samples and stable FID scores that are actually competitive with a variety of GAN models, all while retaining desirable attributes of the original VAE architecture. A shorter version of this work will appear in the ICLR 2019 conference proceedings (Dai and Wipf, 2019). The code for our model is available at https://github.com/daib13/ TwoStageVAE.
Steganography refers to the art of concealing secret messages within multiple media carriers so that an eavesdropper is unable to detect the presence and content of the hidden messages. In this paper, we firstly propose a novel key-dependent steganographic scheme that achieves steganographic objectives with adversarial training. Symmetric (secret-key) and Asymmetric (public-key) steganographic scheme are separately proposed and each scheme is successfully designed and implemented. We show that these encodings produced by our scheme improve the invisibility by 20% than previous deep-leanring-based work, and further that perform competitively remarkable undetectability 25% better than classic steganographic algorithms. Finally, we simulated our scheme in a real situation where the decoder achieved an accuracy of more than 98% of the original message.
This paper focuses on the challenging task of learning 3D object surface reconstructions from single RGB images. Existing methods achieve varying degrees of success by using different geometric representations. However, they all have their own drawbacks, and cannot well reconstruct those surfaces of complex topologies. To this end, we propose in this paper a skeleton-bridged, stage-wise learning approach to address the challenge. Our use of skeleton is due to its nice property of topology preservation, while being of lower complexity to learn. To learn skeleton from an input image, we design a deep architecture whose decoder is based on a novel design of parallel streams respectively for synthesis of curve- and surface-like skeleton points. We use different shape representations of point cloud, volume, and mesh in our stage-wise learning, in order to take their respective advantages. We also propose multi-stage use of the input image to correct prediction errors that are possibly accumulated in each stage. We conduct intensive experiments to investigate the efficacy of our proposed approach. Qualitative and quantitative results on representative object categories of both simple and complex topologies demonstrate the superiority of our approach over existing ones. We will make our ShapeNet-Skeleton dataset publicly available.
In this work, a deep learning-based method for log-likelihood ratio (LLR) lossy compression and quantization is proposed, with emphasis on a single-input single-output uncorrelated fading communication setting. A deep autoencoder network is trained to compress, quantize and reconstruct the bit log-likelihood ratios corresponding to a single transmitted symbol. Specifically, the encoder maps to a latent space with dimension equal to the number of sufficient statistics required to recover the inputs - equal to three in this case - while the decoder aims to reconstruct a noisy version of the latent representation with the purpose of modeling quantization effects in a differentiable way. Simulation results show that, when applied to a standard rate-1/2 low-density parity-check (LDPC) code, a finite precision compression factor of nearly three times is achieved when storing an entire codeword, with an incurred loss of performance lower than 0.1 dB compared to straightforward scalar quantization of the log-likelihood ratios.
This paper addresses the problem of inferring unseen cross-modal image-to-image translations between multiple modalities. We assume that only some of the pairwise translations have been seen (i.e. trained) and infer the remaining unseen translations (where training pairs are not available). We propose mix and match networks, an approach where multiple encoders and decoders are aligned in such a way that the desired translation can be obtained by simply cascading the source encoder and the target decoder, even when they have not interacted during the training stage (i.e. unseen). The main challenge lies in the alignment of the latent representations at the bottlenecks of encoder-decoder pairs. We propose an architecture with several tools to encourage alignment, including autoencoders and robust side information and latent consistency losses. We show the benefits of our approach in terms of effectiveness and scalability compared with other pairwise image-to-image translation approaches. We also propose zero-pair cross-modal image translation, a challenging setting where the objective is inferring semantic segmentation from depth (and vice-versa) without explicit segmentation-depth pairs, and only from two (disjoint) segmentation-RGB and depth-RGB training sets. We observe that a certain part of the shared information between unseen modalities might not be reachable, so we further propose a variant that leverages pseudo-pairs which allows us to exploit this shared information between the unseen modalities.
End-to-end deep learning for communication systems, i.e., systems whose encoder and decoder are learned, has attracted significant interest recently, due to its performance which comes close to well-developed classical encoder-decoder designs. However, one of the drawbacks of current learning approaches is that a differentiable channel model is needed for the training of the underlying neural networks. In real-world scenarios, such a channel model is hardly available and often the channel density is not even known at all. Some works, therefore, focus on a generative approach, i.e., generating the channel from samples, or rely on reinforcement learning to circumvent this problem. We present a novel approach which utilizes a recently proposed neural estimator of mutual information. We use this estimator to optimize the encoder for a maximized mutual information, only relying on channel samples. Moreover, we show that our approach achieves the same performance as state-of-the-art end-to-end learning with perfect channel model knowledge.
Most image completion methods produce only one result for each masked input, although there may be many reasonable possibilities. In this paper, we present an approach for \textbf{pluralistic image completion} -- the task of generating multiple and diverse plausible solutions for image completion. A major challenge faced by learning-based approaches is that usually only one ground truth training instance per label. As such, sampling from conditional VAEs still leads to minimal diversity. To overcome this, we propose a novel and probabilistically principled framework with two parallel paths. One is a reconstructive path that utilizes the only one given ground truth to get prior distribution of missing parts and rebuild the original image from this distribution. The other is a generative path for which the conditional prior is coupled to the distribution obtained in the reconstructive path. Both are supported by GANs. We also introduce a new short+long term attention layer that exploits distant relations among decoder and encoder features, improving appearance consistency. When tested on datasets with buildings (Paris), faces (CelebA-HQ), and natural images (ImageNet), our method not only generated higher-quality completion results, but also with multiple and diverse plausible outputs.
Achieving good speed and accuracy trade-off on a target platform is very important in deploying deep neural networks in real world scenarios. However, most existing automatic architecture search approaches only concentrate on high performance. In this work, we propose an algorithm that can offer better speed/accuracy trade-off of searched networks, which is termed "Partial Order Pruning". It prunes the architecture search space with a partial order assumption to automatically search for the architectures with the best speed and accuracy trade-off. Our algorithm explicitly takes profile information about the inference speed on the target platform into consideration. With the proposed algorithm, we present several Dongfeng (DF) networks that provide high accuracy and fast inference speed on various application GPU platforms. By further searching decoder architectures, our DF-Seg real-time segmentation networks yield state-of-the-art speed/accuracy trade-off on both the target embedded device and the high-end GPU.
Depth sensing is a critical function for robotic tasks such as localization, mapping and obstacle detection. There has been a significant and growing interest in depth estimation from a single RGB image, due to the relatively low cost and size of monocular cameras. However, state-of-the-art single-view depth estimation algorithms are based on fairly complex deep neural networks that are too slow for real-time inference on an embedded platform, for instance, mounted on a micro aerial vehicle. In this paper, we address the problem of fast depth estimation on embedded systems. We propose an efficient and lightweight encoder-decoder network architecture and apply network pruning to further reduce computational complexity and latency. In particular, we focus on the design of a low-latency decoder. Our methodology demonstrates that it is possible to achieve similar accuracy as prior work on depth estimation, but at inference speeds that are an order of magnitude faster. Our proposed network, FastDepth, runs at 178 fps on an NVIDIA Jetson TX2 GPU and at 27 fps when using only the TX2 CPU, with active power consumption under 10 W. FastDepth achieves close to state-of-the-art accuracy on the NYU Depth v2 dataset. To the best of the authors' knowledge, this paper demonstrates real-time monocular depth estimation using a deep neural network with the lowest latency and highest throughput on an embedded platform that can be carried by a micro aerial vehicle.
This paper proposes an approach to the joint modeling of the short-time Fourier transform magnitude and phase spectrograms with a deep generative model. We assume that the magnitude follows a Gaussian distribution and the phase follows a von Mises distribution. To improve the consistency of the phase values in the time-frequency domain, we also apply the von Mises distribution to the phase derivatives, i.e., the group delay and the instantaneous frequency. Based on these assumptions, we explore and compare several combinations of loss functions for training our models. Built upon the variational autoencoder framework, our model consists of three convolutional neural networks acting as an encoder, a magnitude decoder, and a phase decoder. In addition to the latent variables, we propose to also condition the phase estimation on the estimated magnitude. Evaluated for a time-domain speech reconstruction task, our models could generate speech with a high perceptual quality and a high intelligibility.