PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1807.00099

Generating Titles for Web Tables

Descriptive titles provide crucial context for interpreting tables that are extracted from web pages and are a key component of table-based web applications. Prior approaches have attempted to produce titles by selecting existing text snippets associated with the table. These approaches, however, are limited by their dependence on suitable titles existing a priori. In our user study, we observe that the relevant information for the title tends to be scattered across the page, and often--more than 80% of the time--does not appear verbatim anywhere in the page. We propose instead the application of a sequence-to-sequence neural network model as a more generalizable means of generating high-quality titles. This is accomplished by extracting many text snippets that have potentially relevant information to the table, encoding them into an input sequence, and using both copy and generation mechanisms in the decoder to balance relevance and readability of the generated title. We validate this approach with human evaluation on sample web tables and report that while sequence models with only a copy mechanism or only a generation mechanism are easily outperformed by simple selection-based baselines, the model with both capabilities outperforms them all, approaching the quality of crowdsourced titles while training on fewer than ten thousand examples. To the best of our knowledge, the proposed technique is the first to consider text generation methods for table titles and establishes a new state of the art.

arXiv:1807.00583

Sample Efficient Semantic Segmentation using Rotation Equivariant Convolutional Networks

We propose a semantic segmentation model that exploits rotation and reflection symmetries. We demonstrate significant gains in sample efficiency due to increased weight sharing, as well as improvements in robustness to symmetry transformations. The group equivariant CNN framework is extended for segmentation by introducing a new equivariant (G->Z2)-convolution that transforms feature maps on a group to planar feature maps. Also, equivariant transposed convolution is formulated for up-sampling in an encoder-decoder network. To demonstrate improvements in sample efficiency we evaluate on multiple data regimes of a rotation-equivariant segmentation task: cancer metastases detection in histopathology images. We further show the effectiveness of exploiting more symmetries by varying the size of the group.

arXiv:1806.11266

Gated Feedback Refinement Network for Coarse-to-Fine Dense Semantic Image Labeling

Effective integration of local and global contextual information is crucial for semantic segmentation and dense image labeling. We develop two encoder-decoder based deep learning architectures to address this problem. We first propose a network architecture called Label Refinement Network (LRN) that predicts segmentation labels in a coarse-to-fine fashion at several spatial resolutions. In this network, we also define loss functions at several stages to provide supervision at different stages of training. However, there are limits to the quality of refinement possible if ambiguous information is passed forward. In order to address this issue, we also propose Gated Feedback Refinement Network (G-FRNet) that addresses this limitation. Initially, G-FRNet makes a coarse-grained prediction which it progressively refines to recover details by effectively integrating local and global contextual information during the refinement stages. This is achieved by gate units proposed in this work, that control information passed forward in order to resolve the ambiguity. Experiments were conducted on four challenging dense labeling datasets (CamVid, PASCAL VOC 2012, Horse-Cow Parsing, PASCAL-Person-Part, and SUN-RGBD). G-FRNet achieves state-of-the-art semantic segmentation results on the CamVid and Horse-Cow Parsing datasets and produces results competitive with the best performing approaches that appear in the literature for the other three datasets.

arXiv:1806.11249

Neural Machine Translation with Key-Value Memory-Augmented Attention

Although attention-based Neural Machine Translation (NMT) has achieved remarkable progress in recent years, it still suffers from issues of repeating and dropping translations. To alleviate these issues, we propose a novel key-value memory-augmented attention model for NMT, called KVMEMATT. Specifically, we maintain a timely updated keymemory to keep track of attention history and a fixed value-memory to store the representation of source sentence throughout the whole translation process. Via nontrivial transformations and iterative interactions between the two memories, the decoder focuses on more appropriate source word(s) for predicting the next target word at each decoding step, therefore can improve the adequacy of translations. Experimental results on Chinese=>English and WMT17 German<=>English translation tasks demonstrate the superiority of the proposed model.

arXiv:1806.11191공식 코드 · Papers with Code

CR-GAN: Learning Complete Representations for Multi-view Generation

Generating multi-view images from a single-view input is an essential yet challenging problem. It has broad applications in vision, graphics, and robotics. Our study indicates that the widely-used generative adversarial network (GAN) may learn "incomplete" representations due to the single-pathway framework: an encoder-decoder network followed by a discriminator network. We propose CR-GAN to address this problem. In addition to the single reconstruction path, we introduce a generation sideway to maintain the completeness of the learned embedding space. The two learning pathways collaborate and compete in a parameter-sharing manner, yielding considerably improved generalization ability to "unseen" dataset. More importantly, the two-pathway framework makes it possible to combine both labeled and unlabeled data for self-supervised learning, which further enriches the embedding space for realistic generations. The experimental results prove that CR-GAN significantly outperforms state-of-the-art methods, especially when generating from "unseen" inputs in wild conditions.

arXiv:1806.10175공식 코드 · Papers with Code

Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling

Linear encoding of sparse vectors is widely popular, but is commonly data-independent -- missing any possible extra (but a priori unknown) structure beyond sparsity. In this paper we present a new method to learn linear encoders that adapt to data, while still performing well with the widely used $\ell_1$ decoder. The convex $\ell_1$ decoder prevents gradient propagation as needed in standard gradient-based training. Our method is based on the insight that unrolling the convex decoder into $T$ projected subgradient steps can address this issue. Our method can be seen as a data-driven way to learn a compressed sensing measurement matrix. We compare the empirical performance of 10 algorithms over 6 sparse datasets (3 synthetic and 3 real). Our experiments show that there is indeed additional structure beyond sparsity in the real datasets; our method is able to discover it and exploit it to create excellent reconstructions with fewer measurements (by a factor of 1.1-3x) compared to the previous state-of-the-art methods. We illustrate an application of our method in learning label embeddings for extreme multi-label classification, and empirically show that our method is able to match or outperform the precision scores of SLEEC, which is one of the state-of-the-art embedding-based approaches.

arXiv:1806.09792

A Multi-Modal Chinese Poetry Generation Model

Recent studies in sequence-to-sequence learning demonstrate that RNN encoder-decoder structure can successfully generate Chinese poetry. However, existing methods can only generate poetry with a given first line or user's intent theme. In this paper, we proposed a three-stage multi-modal Chinese poetry generation approach. Given a picture, the first line, the title and the other lines of the poem are successively generated in three stages. According to the characteristics of Chinese poems, we propose a hierarchy-attention seq2seq model which can effectively capture character, phrase, and sentence information between contexts and improve the symmetry delivered in poems. In addition, the Latent Dirichlet allocation (LDA) model is utilized for title generation and improve the relevance of the whole poem and the title. Compared with strong baseline, the experimental results demonstrate the effectiveness of our approach, using machine evaluations as well as human judgments.

arXiv:1806.09300

Improving Chemical Autoencoder Latent Space and Molecular De novo Generation Diversity with Heteroencoders

Chemical autoencoders are attractive models as they combine chemical space navigation with possibilities for de-novo molecule generation in areas of interest. This enables them to produce focused chemical libraries around a single lead compound for employment early in a drug discovery project. Here it is shown that the choice of chemical representation, such as SMILES strings, has a large influence on the properties of the latent space. It is further explored to what extent translating between different chemical representations influences the latent space similarity to the SMILES strings or circular fingerprints. By employing SMILES enumeration for either the encoder or decoder, it is found that the decoder has the largest influence on the properties of the latent space. Training a sequence to sequence heteroencoder based on recurrent neural networks(RNNs) with long short-term memory cells (LSTM) to predict different enumerated SMILES strings from the same canonical SMILES string gives the largest similarity between latent space distance and molecular similarity measured as circular fingerprints similarity. Using the output from the bottleneck in QSAR modelling of five molecular datasets shows that heteroencoder derived vectors markedly outperforms autoencoder derived vectors as well as models built using ECFP4 fingerprints, underlining the increased chemical relevance of the latent space. However, the use of enumeration during training of the decoder leads to a markedly increase in the rate of decoding to a different molecules than encoded, a tendency that can be counteracted with more complex network architectures.

arXiv:1806.08730공식 코드 · Papers with Code

The Natural Language Decathlon: Multitask Learning as Question Answering

Deep learning has improved performance on many natural language processing (NLP) tasks individually. However, general NLP models cannot emerge within a paradigm that focuses on the particularities of a single metric, dataset, and task. We introduce the Natural Language Decathlon (decaNLP), a challenge that spans ten tasks: question answering, machine translation, summarization, natural language inference, sentiment analysis, semantic role labeling, zero-shot relation extraction, goal-oriented dialogue, semantic parsing, and commonsense pronoun resolution. We cast all tasks as question answering over a context. Furthermore, we present a new Multitask Question Answering Network (MQAN) jointly learns all tasks in decaNLP without any task-specific modules or parameters in the multitask setting. MQAN shows improvements in transfer learning for machine translation and named entity recognition, domain adaptation for sentiment analysis and natural language inference, and zero-shot capabilities for text classification. We demonstrate that the MQAN's multi-pointer-generator decoder is key to this success and performance further improves with an anti-curriculum training strategy. Though designed for decaNLP, MQAN also achieves state of the art results on the WikiSQL semantic parsing task in the single-task setting. We also release code for procuring and processing data, training and evaluating models, and reproducing all experiments for decaNLP.

arXiv:1806.08522

Efficient Semantic Segmentation using Gradual Grouping

Deep CNNs for semantic segmentation have high memory and run time requirements. Various approaches have been proposed to make CNNs efficient like grouped, shuffled, depth-wise separable convolutions. We study the effectiveness of these techniques on a real-time semantic segmentation architecture like ERFNet for improving run time by over 5X. We apply these techniques to CNN layers partially or fully and evaluate the testing accuracies on Cityscapes dataset. We obtain accuracy vs parameters/FLOPs trade offs, giving accuracy scores for models that can run under specified runtime budgets. We further propose a novel training procedure which starts out with a dense convolution but gradually evolves towards a grouped convolution. We show that our proposed training method and efficient architecture design can improve accuracies by over 8% with depth wise separable convolutions applied on the encoder of ERFNet and attaching a light weight decoder. This results in a model which has a 5X improvement in FLOPs while only suffering a 4% degradation in accuracy with respect to ERFNet.

arXiv:1806.08015

Stability of Scattering Decoder For Nonlinear Diffractive Imaging

The problem of image reconstruction under multiple light scattering is usually formulated as a regularized non-convex optimization. A deep learning architecture, Scattering Decoder (ScaDec), was recently proposed to solve this problem in a purely data-driven fashion. The proposed method was shown to substantially outperform optimization-based baselines and achieve state-of-the-art results. In this paper, we thoroughly test the robustness of ScaDec to different permittivity contrasts, number of transmissions, and input signal-to-noise ratios. The results on high-fidelity simulated datasets show that the performance of ScaDec is stable in different settings.

arXiv:1806.07416

Fast CapsNet for Lung Cancer Screening

Lung cancer is the leading cause of cancer-related deaths in the past several years. A major challenge in lung cancer screening is the detection of lung nodules from computed tomography (CT) scans. State-of-the-art approaches in automated lung nodule classification use deep convolutional neural networks (CNNs). However, these networks require a large number of training samples to generalize well. This paper investigates the use of capsule networks (CapsNets) as an alternative to CNNs. We show that CapsNets significantly outperforms CNNs when the number of training samples is small. To increase the computational efficiency, our paper proposes a consistent dynamic routing mechanism that results in $3\times$ speedup of CapsNet. Finally, we show that the original image reconstruction method of CapNets performs poorly on lung nodule data. We propose an efficient alternative, called convolutional decoder, that yields lower reconstruction error and higher classification accuracy.

arXiv:1806.07409

Built-in Vulnerabilities to Imperceptible Adversarial Perturbations

Designing models that are robust to small adversarial perturbations of their inputs has proven remarkably difficult. In this work we show that the reverse problem---making models more vulnerable---is surprisingly easy. After presenting some proofs of concept on MNIST, we introduce a generic tilting attack that injects vulnerabilities into the linear layers of pre-trained networks by increasing their sensitivity to components of low variance in the training data without affecting their performance on test data. We illustrate this attack on a multilayer perceptron trained on SVHN and use it to design a stand-alone adversarial module which we call a steganogram decoder. Finally, we show on CIFAR-10 that a poisoning attack with a poisoning rate as low as 0.1% can induce vulnerabilities to chosen imperceptible backdoor signals in state-of-the-art networks. Beyond their practical implications, these different results shed new light on the nature of the adversarial example phenomenon.

arXiv:1806.07380공식 코드 · Papers with Code

Deep Sequence Learning with Auxiliary Information for Traffic Prediction

Predicting traffic conditions from online route queries is a challenging task as there are many complicated interactions over the roads and crowds involved. In this paper, we intend to improve traffic prediction by appropriate integration of three kinds of implicit but essential factors encoded in auxiliary information. We do this within an encoder-decoder sequence learning framework that integrates the following data: 1) offline geographical and social attributes. For example, the geographical structure of roads or public social events such as national celebrations; 2) road intersection information. In general, traffic congestion occurs at major junctions; 3) online crowd queries. For example, when many online queries issued for the same destination due to a public performance, the traffic around the destination will potentially become heavier at this location after a while. Qualitative and quantitative experiments on a real-world dataset from Baidu have demonstrated the effectiveness of our framework.

arXiv:1806.07042공식 코드 · Papers with Code

Response Generation by Context-aware Prototype Editing

Open domain response generation has achieved remarkable progress in recent years, but sometimes yields short and uninformative responses. We propose a new paradigm for response generation, that is response generation by editing, which significantly increases the diversity and informativeness of the generation results. Our assumption is that a plausible response can be generated by slightly revising an existing response prototype. The prototype is retrieved from a pre-defined index and provides a good start-point for generation because it is grammatical and informative. We design a response editing model, where an edit vector is formed by considering differences between a prototype context and a current context, and then the edit vector is fed to a decoder to revise the prototype response for the current context. Experiment results on a large scale dataset demonstrate that the response editing model outperforms generative and retrieval-based models on various aspects.

arXiv:1806.06886

Learning to Decode 7T-like MR Image Reconstruction from 3T MR Images

Increasing demand for high field magnetic resonance (MR) scanner indicates the need for high-quality MR images for accurate medical diagnosis. However, cost constraints, instead, motivate a need for algorithms to enhance images from low field scanners. We propose an approach to process the given low field (3T) MR image slices to reconstruct the corresponding high field (7T-like) slices. Our framework involves a novel architecture of a merged convolutional autoencoder with a single encoder and multiple decoders. Specifically, we employ three decoders with random initializations, and the proposed training approach involves selection of a particular decoder in each weight-update iteration for back propagation. We demonstrate that the proposed algorithm outperforms some related contemporary methods in terms of performance and reconstruction time.

arXiv:1503.07387공식 코드 · Papers with Code

Vectorized VByte Decoding

We consider the ubiquitous technique of VByte compression, which represents each integer as a variable length sequence of bytes. The low 7 bits of each byte encode a portion of the integer, and the high bit of each byte is reserved as a continuation flag. This flag is set to 1 for all bytes except the last, and the decoding of each integer is complete when a byte with a high bit of 0 is encountered. VByte decoding can be a performance bottleneck especially when the unpredictable lengths of the encoded integers cause frequent branch mispredictions. Previous attempts to accelerate VByte decoding using SIMD vector instructions have been disappointing, prodding search engines such as Google to use more complicated but faster-to-decode formats for performance-critical code. Our decoder (Masked VByte) is 2 to 4 times faster than a conventional scalar VByte decoder, making the format once again competitive with regard to speed.

arXiv:1210.5041

Navigation domain representation for interactive multiview imaging

Enabling users to interactively navigate through different viewpoints of a static scene is a new interesting functionality in 3D streaming systems. While it opens exciting perspectives towards rich multimedia applications, it requires the design of novel representations and coding techniques in order to solve the new challenges imposed by interactive navigation. Interactivity clearly brings new design constraints: the encoder is unaware of the exact decoding process, while the decoder has to reconstruct information from incomplete subsets of data since the server can generally not transmit images for all possible viewpoints due to resource constrains. In this paper, we propose a novel multiview data representation that permits to satisfy bandwidth and storage constraints in an interactive multiview streaming system. In particular, we partition the multiview navigation domain into segments, each of which is described by a reference image and some auxiliary information. The auxiliary information enables the client to recreate any viewpoint in the navigation segment via view synthesis. The decoder is then able to navigate freely in the segment without further data request to the server; it requests additional data only when it moves to a different segment. We discuss the benefits of this novel representation in interactive navigation systems and further propose a method to optimize the partitioning of the navigation domain into independent segments, under bandwidth and storage constraints. Experimental results confirm the potential of the proposed representation; namely, our system leads to similar compression performance as classical inter-view coding, while it provides the high level of flexibility that is required for interactive streaming. Hence, our new framework represents a promising solution for 3D data representation in novel interactive multimedia services.

arXiv:1303.5492

Sample Distortion for Compressed Imaging

We propose the notion of a sample distortion (SD) function for independent and identically distributed (i.i.d) compressive distributions to fundamentally quantify the achievable reconstruction performance of compressed sensing for certain encoder-decoder pairs at a given sampling ratio. Two lower bounds on the achievable performance and the intrinsic convexity property is derived. A zeroing procedure is then introduced to improve non convex SD functions. The SD framework is then applied to analyse compressed imaging with a multi-resolution statistical image model using both the generalized Gaussian distribution and the two-state Gaussian mixture distribution. We subsequently focus on the Gaussian encoder-Bayesian optimal approximate message passing (AMP) decoder pair, whose theoretical SD function is provided by the rigorous analysis of the AMP algorithm. Given the image statistics, analytic bandwise sample allocation for bandwise independent model is derived as a reverse water-filling scheme. Som and Schniter's turbo message passing approach is further deployed to integrate the bandwise sampling with the exploitation of the hidden Markov tree structure of wavelet coefficients. Natural image simulations confirm that with oracle image statistics, the SD function associated with the optimized sample allocation can accurately predict the possible compressed sensing gains. Finally, a general sample allocation profile based on average image statistics not only illustrates preferable performance but also makes the scheme practical.

arXiv:1404.7211

Spatially Directional Predictive Coding for Block-based Compressive Sensing of Natural Images

A novel coding strategy for block-based compressive sens-ing named spatially directional predictive coding (SDPC) is proposed, which efficiently utilizes the intrinsic spatial cor-relation of natural images. At the encoder, for each block of compressive sensing (CS) measurements, the optimal pre-diction is selected from a set of prediction candidates that are generated by four designed directional predictive modes. Then, the resulting residual is processed by scalar quantiza-tion (SQ). At the decoder, the same prediction is added onto the de-quantized residuals to produce the quantized CS measurements, which is exploited for CS reconstruction. Experimental results substantiate significant improvements achieved by SDPC-plus-SQ in rate distortion performance as compared with SQ alone and DPCM-plus-SQ.