PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2003.01479공식 코드 · Papers with Code

End-to-End Fast Training of Communication Links Without a Channel Model via Online Meta-Learning

When a channel model is not available, the end-to-end training of encoder and decoder on a fading noisy channel generally requires the repeated use of the channel and of a feedback link. An important limitation of the approach is that training should be generally carried out from scratch for each new channel. To cope with this problem, prior works considered joint training over multiple channels with the aim of finding a single pair of encoder and decoder that works well on a class of channels. In this paper, we propose to obviate the limitations of joint training via meta-learning. The proposed approach is based on a meta-training phase in which the online gradient-based meta-learning of the decoder is coupled with the joint training of the encoder via the transmission of pilots and the use of a feedback link. Accounting for channel variations during the meta-training phase, this work demonstrates the advantages of meta-learning in terms of number of pilots as compared to conventional methods when the feedback link is only available for meta-training and not at run time.

arXiv:2003.01086공식 코드 · Papers with Code

Predictive Coding for Locally-Linear Control

High-dimensional observations and unknown dynamics are major challenges when applying optimal control to many real-world decision making tasks. The Learning Controllable Embedding (LCE) framework addresses these challenges by embedding the observations into a lower dimensional latent space, estimating the latent dynamics, and then performing control directly in the latent space. To ensure the learned latent dynamics are predictive of next-observations, all existing LCE approaches decode back into the observation space and explicitly perform next-observation prediction---a challenging high-dimensional task that furthermore introduces a large number of nuisance parameters (i.e., the decoder) which are discarded during control. In this paper, we propose a novel information-theoretic LCE approach and show theoretically that explicit next-observation prediction can be replaced with predictive coding. We then use predictive coding to develop a decoder-free LCE model whose latent dynamics are amenable to locally-linear control. Extensive experiments on benchmark tasks show that our model reliably learns a controllable latent space that leads to superior performance when compared with state-of-the-art LCE baselines.

arXiv:2003.00674

Style Example-Guided Text Generation using Generative Adversarial Transformers

We introduce a language generative model framework for generating a styled paragraph based on a context sentence and a style reference example. The framework consists of a style encoder and a texts decoder. The style encoder extracts a style code from the reference example, and the text decoder generates texts based on the style code and the context. We propose a novel objective function to train our framework. We also investigate different network design choices. We conduct extensive experimental validation with comparison to strong baselines to validate the effectiveness of the proposed framework using a newly collected dataset with diverse text styles. Both code and dataset will be released upon publication.

arXiv:2003.00576공식 코드 · Papers with Code

StructSum: Summarization via Structured Representations

Abstractive text summarization aims at compressing the information of a long source document into a rephrased, condensed summary. Despite advances in modeling techniques, abstractive summarization models still suffer from several key challenges: (i) layout bias: they overfit to the style of training corpora; (ii) limited abstractiveness: they are optimized to copying n-grams from the source rather than generating novel abstractive summaries; (iii) lack of transparency: they are not interpretable. In this work, we propose a framework based on document-level structure induction for summarization to address these challenges. To this end, we propose incorporating latent and explicit dependencies across sentences in the source document into end-to-end single-document summarization models. Our framework complements standard encoder-decoder summarization models by augmenting them with rich structure-aware document representations based on implicitly learned (latent) structures and externally-derived linguistic (explicit) structures. We show that our summarization framework, trained on the CNN/DM dataset, improves the coverage of content in the source documents, generates more abstractive summaries by generating more novel n-grams, and incorporates interpretable sentence-level structures, while performing on par with standard baselines.

arXiv:2003.00830

GSANet: Semantic Segmentation with Global and Selective Attention

This paper proposes a novel deep learning architecture for semantic segmentation. The proposed Global and Selective Attention Network (GSANet) features Atrous Spatial Pyramid Pooling (ASPP) with a novel sparsemax global attention and a novel selective attention that deploys a condensation and diffusion mechanism to aggregate the multi-scale contextual information from the extracted deep features. A selective attention decoder is also proposed to process the GSA-ASPP outputs for optimizing the softmax volume. We are the first to benchmark the performance of semantic segmentation networks with the low-complexity feature extraction network (FXN) MobileNetEdge, that is optimized for low latency on edge devices. We show that GSANet can result in more accurate segmentation with MobileNetEdge, as well as with strong FXNs, such as Xception. GSANet improves the state-of-art semantic segmentation accuracy on both the ADE20k and the Cityscapes datasets.

arXiv:2003.00825

SIP-SegNet: A Deep Convolutional Encoder-Decoder Network for Joint Semantic Segmentation and Extraction of Sclera, Iris and Pupil based on Periocular Region Suppression

The current developments in the field of machine vision have opened new vistas towards deploying multimodal biometric recognition systems in various real-world applications. These systems have the ability to deal with the limitations of unimodal biometric systems which are vulnerable to spoofing, noise, non-universality and intra-class variations. In addition, the ocular traits among various biometric traits are preferably used in these recognition systems. Such systems possess high distinctiveness, permanence, and performance while, technologies based on other biometric traits (fingerprints, voice etc.) can be easily compromised. This work presents a novel deep learning framework called SIP-SegNet, which performs the joint semantic segmentation of ocular traits (sclera, iris and pupil) in unconstrained scenarios with greater accuracy. The acquired images under these scenarios exhibit purkinje reflexes, specular reflections, eye gaze, off-angle shots, low resolution, and various occlusions particularly by eyelids and eyelashes. To address these issues, SIP-SegNet begins with denoising the pristine image using denoising convolutional neural network (DnCNN), followed by reflection removal and image enhancement based on contrast limited adaptive histogram equalization (CLAHE). Our proposed framework then extracts the periocular information using adaptive thresholding and employs the fuzzy filtering technique to suppress this information. Finally, the semantic segmentation of sclera, iris and pupil is achieved using the densely connected fully convolutional encoder-decoder network. We used five CASIA datasets to evaluate the performance of SIP-SegNet based on various evaluation metrics. The simulation results validate the optimal segmentation of the proposed SIP-SegNet, with the mean f1 scores of 93.35, 95.11 and 96.69 for the sclera, iris and pupil classes respectively.

arXiv:2003.00637

A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Dataset

A great deal of research has demonstrated recently that multi-view stereo (MVS) matching can be solved with deep learning methods. However, these efforts were focused on close-range objects and only a very few of the deep learning-based methods were specifically designed for large-scale 3D urban reconstruction due to the lack of multi-view aerial image benchmarks. In this paper, we present a synthetic aerial dataset, called the WHU dataset, we created for MVS tasks, which, to our knowledge, is the first large-scale multi-view aerial dataset. It was generated from a highly accurate 3D digital surface model produced from thousands of real aerial images with precise camera parameters. We also introduce in this paper a novel network, called RED-Net, for wide-range depth inference, which we developed from a recurrent encoder-decoder structure to regularize cost maps across depths and a 2D fully convolutional network as framework. RED-Net's low memory requirements and high performance make it suitable for large-scale and highly accurate 3D Earth surface reconstruction. Our experiments confirmed that not only did our method exceed the current state-of-the-art MVS methods by more than 50% mean absolute error (MAE) with less memory and computational cost, but its efficiency as well. It outperformed one of the best commercial software programs based on conventional methods, improving their efficiency 16 times over. Moreover, we proved that our RED-Net model pre-trained on the synthetic WHU dataset can be efficiently transferred to very different multi-view aerial image datasets without any fine-tuning. Dataset are available at http://gpcv.whu.edu.cn/data.

arXiv:2003.00217

NAS-Count: Counting-by-Density with Neural Architecture Search

Most of the recent advances in crowd counting have evolved from hand-designed density estimation networks, where multi-scale features are leveraged to address the scale variation problem, but at the expense of demanding design efforts. In this work, we automate the design of counting models with Neural Architecture Search (NAS) and introduce an end-to-end searched encoder-decoder architecture, Automatic Multi-Scale Network (AMSNet). Specifically, we utilize a counting-specific two-level search space. The encoder and decoder in AMSNet are composed of different cells discovered from micro-level search, while the multi-path architecture is explored through macro-level search. To solve the pixel-level isolation issue in MSE loss, AMSNet is optimized with an auto-searched Scale Pyramid Pooling Loss (SPPLoss) that supervises the multi-scale structural information. Extensive experiments on four datasets show AMSNet produces state-of-the-art results that outperform hand-designed models, fully demonstrating the efficacy of NAS-Count.

arXiv:2002.12585

Exploring and Distilling Cross-Modal Information for Image Captioning

Recently, attention-based encoder-decoder models have been used extensively in image captioning. Yet there is still great difficulty for the current methods to achieve deep image understanding. In this work, we argue that such understanding requires visual attention to correlated image regions and semantic attention to coherent attributes of interest. Based on the Transformer, to perform effective attention, we explore image captioning from a cross-modal perspective and propose the Global-and-Local Information Exploring-and-Distilling approach that explores and distills the source information in vision and language. It globally provides the aspect vector, a spatial and relational representation of images based on caption contexts, through the extraction of salient region groupings and attribute collocations, and locally extracts the fine-grained regions and attributes in reference to the aspect vector for word selection. Our Transformer-based model achieves a CIDEr score of 129.3 in offline COCO evaluation on the COCO testing set with remarkable efficiency in terms of accuracy, speed, and parameter budget.

arXiv:2002.12804공식 코드 · Papers with Code

UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training

We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM). Given an input text with masked tokens, we rely on conventional masks to learn inter-relations between corrupted tokens and context via autoencoding, and pseudo masks to learn intra-relations between masked spans via partially autoregressive modeling. With well-designed position embeddings and self-attention masks, the context encodings are reused to avoid redundant computation. Moreover, conventional masks used for autoencoding provide global masking information, so that all the position embeddings are accessible in partially autoregressive language modeling. In addition, the two tasks pre-train a unified language model as a bidirectional encoder and a sequence-to-sequence decoder, respectively. Our experiments show that the unified language models pre-trained using PMLM achieve new state-of-the-art results on a wide range of natural language understanding and generation tasks across several widely used benchmarks.

arXiv:2002.11847

Echo State Neural Machine Translation

We present neural machine translation (NMT) models inspired by echo state network (ESN), named Echo State NMT (ESNMT), in which the encoder and decoder layer weights are randomly generated then fixed throughout training. We show that even with this extremely simple model construction and training procedure, ESNMT can already reach 70-80% quality of fully trainable baselines. We examine how spectral radius of the reservoir, a key quantity that characterizes the model, determines the model behavior. Our findings indicate that randomized networks can work well even for complicated sequence-to-sequence prediction NLP tasks.

arXiv:2002.12079

Two-stage multi-scale breast mass segmentation for full mammogram analysis without user intervention

Mammography is the primary imaging modality used for early detection and diagnosis of breast cancer. X-ray mammogram analysis mainly refers to the localization of suspicious regions of interest followed by segmentation, towards further lesion classification into benign versus malignant. Among diverse types of breast abnormalities, masses are the most important clinical findings of breast carcinomas. However, manually segmenting breast masses from native mammograms is time-consuming and error-prone. Therefore, an integrated computer-aided diagnosis system is required to assist clinicians for automatic and precise breast mass delineation. In this work, we present a two-stage multi-scale pipeline that provides accurate mass contours from high-resolution full mammograms. First, we propose an extended deep detector integrating a multi-scale fusion strategy for automated mass localization. Second, a convolutional encoder-decoder network using nested and dense skip connections is employed to fine-delineate candidate masses. Unlike most previous studies based on segmentation from regions, our framework handles mass segmentation from native full mammograms without any user intervention. Trained on INbreast and DDSM-CBIS public datasets, the pipeline achieves an overall average Dice of 80.44% on INbreast test images, outperforming state-of-the-art. Our system shows promising accuracy as an automatic full-image mass segmentation system. Extensive experiments reveals robustness against the diversity of size, shape and appearance of breast masses, towards better interaction-free computer-aided diagnosis.

arXiv:2002.12041공식 코드 · Papers with Code

Attention-guided Chained Context Aggregation for Semantic Segmentation

The way features propagate in Fully Convolutional Networks is of momentous importance to capture multi-scale contexts for obtaining precise segmentation masks. This paper proposes a novel series-parallel hybrid paradigm called the Chained Context Aggregation Module (CAM) to diversify feature propagation. CAM gains features of various spatial scales through chain-connected ladder-style information flows and fuses them in a two-stage process, namely pre-fusion and re-fusion. The serial flow continuously increases receptive fields of output neurons and those in parallel encode different region-based contexts. Each information flow is a shallow encoder-decoder with appropriate down-sampling scales to sufficiently capture contextual information. We further adopt an attention model in CAM to guide feature re-fusion. Based on these developments, we construct the Chained Context Aggregation Network (CANet), which employs an asymmetric decoder to recover precise spatial details of prediction maps. We conduct extensive experiments on six challenging datasets, including Pascal VOC 2012, Pascal Context, Cityscapes, CamVid, SUN-RGBD and GATECH. Results evidence that CANet achieves state-of-the-art performance.

arXiv:2002.11886

Hierarchical Memory Decoding for Video Captioning

Recent advances of video captioning often employ a recurrent neural network (RNN) as the decoder. However, RNN is prone to diluting long-term information. Recent works have demonstrated memory network (MemNet) has the advantage of storing long-term information. However, as the decoder, it has not been well exploited for video captioning. The reason partially comes from the difficulty of sequence decoding with MemNet. Instead of the common practice, i.e., sequence decoding with RNN, in this paper, we devise a novel memory decoder for video captioning. Concretely, after obtaining representation of each frame through a pre-trained network, we first fuse the visual and lexical information. Then, at each time step, we construct a multi-layer MemNet-based decoder, i.e., in each layer, we employ a memory set to store previous information and an attention mechanism to select the information related to the current input. Thus, this decoder avoids the dilution of long-term information. And the multi-layer architecture is helpful for capturing dependencies between frames and word sequences. Experimental results show that even without the encoding network, our decoder still could obtain competitive performance and outperform the performance of RNN decoder. Furthermore, compared with one-layer RNN decoder, our decoder has fewer parameters.

arXiv:2002.11624

Deep Attentive Study Session Dropout Prediction in Mobile Learning Environment

Student dropout prediction provides an opportunity to improve student engagement, which maximizes the overall effectiveness of learning experiences. However, researches on student dropout were mainly conducted on school dropout or course dropout, and study session dropout in a mobile learning environment has not been considered thoroughly. In this paper, we investigate the study session dropout prediction problem in a mobile learning environment. First, we define the concept of the study session, study session dropout and study session dropout prediction task in a mobile learning environment. Based on the definitions, we propose a novel Transformer based model for predicting study session dropout, DAS: Deep Attentive Study Session Dropout Prediction in Mobile Learning Environment. DAS has an encoder-decoder structure which is composed of stacked multi-head attention and point-wise feed-forward networks. The deep attentive computations in DAS are capable of capturing complex relations among dynamic student interactions. To the best of our knowledge, this is the first attempt to investigate study session dropout in a mobile learning environment. Empirical evaluations on a large-scale dataset show that DAS achieves the best performance with a significant improvement in area under the receiver operating characteristic curve compared to baseline models.

arXiv:2002.10767

Sequence-to-Sequence Imputation of Missing Sensor Data

Although the sequence-to-sequence (encoder-decoder) model is considered the state-of-the-art in deep learning sequence models, there is little research into using this model for recovering missing sensor data. The key challenge is that the missing sensor data problem typically comprises three sequences (a sequence of observed samples, followed by a sequence of missing samples, followed by another sequence of observed samples) whereas, the sequence-to-sequence model only considers two sequences (an input sequence and an output sequence). We address this problem by formulating a sequence-to-sequence in a novel way. A forward RNN encodes the data observed before the missing sequence and a backward RNN encodes the data observed after the missing sequence. A decoder decodes the two encoders in a novel way to predict the missing data. We demonstrate that this model produces the lowest errors in 12% more cases than the current state-of-the-art.

arXiv:2002.10631

Batch norm with entropic regularization turns deterministic autoencoders into generative models

The variational autoencoder is a well defined deep generative model that utilizes an encoder-decoder framework where an encoding neural network outputs a non-deterministic code for reconstructing an input. The encoder achieves this by sampling from a distribution for every input, instead of outputting a deterministic code per input. The great advantage of this process is that it allows the use of the network as a generative model for sampling from the data distribution beyond provided samples for training. We show in this work that utilizing batch normalization as a source for non-determinism suffices to turn deterministic autoencoders into generative models on par with variational ones, so long as we add a suitable entropic regularization to the training objective.

arXiv:2002.10501

Variational Hyper RNN for Sequence Modeling

In this work, we propose a novel probabilistic sequence model that excels at capturing high variability in time series data, both across sequences and within an individual sequence. Our method uses temporal latent variables to capture information about the underlying data pattern and dynamically decodes the latent information into modifications of weights of the base decoder and recurrent model. The efficacy of the proposed method is demonstrated on a range of synthetic and real-world sequential data that exhibit large scale variations, regime shifts, and complex dynamics.

arXiv:2002.10959

A more abstractive summarization model

Pointer-generator network is an extremely popular method of text summarization. More recent works in this domain still build on top of the baseline pointer generator by augmenting a content selection phase, or by decomposing the decoder into a contextual network and a language model. However, all such models that are based on the pointer-generator base architecture cannot generate novel words in the summary and mostly copy words from the source text. In our work, we first thoroughly investigate why the pointer-generator network is unable to generate novel words, and then address that by adding an Out-of-vocabulary (OOV) penalty. This enables us to improve the amount of novelty/abstraction significantly. We use normalized n-gram novelty scores as a metric for determining the level of abstraction. Moreover, we also report rouge scores of our model since most summarization models are evaluated with R-1, R-2, R-L scores.

arXiv:2002.09545

RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks

The monitoring and management of numerous and diverse time series data at Alibaba Group calls for an effective and scalable time series anomaly detection service. In this paper, we propose RobustTAD, a Robust Time series Anomaly Detection framework by integrating robust seasonal-trend decomposition and convolutional neural network for time series data. The seasonal-trend decomposition can effectively handle complicated patterns in time series, and meanwhile significantly simplifies the architecture of the neural network, which is an encoder-decoder architecture with skip connections. This architecture can effectively capture the multi-scale information from time series, which is very useful in anomaly detection. Due to the limited labeled data in time series anomaly detection, we systematically investigate data augmentation methods in both time and frequency domains. We also introduce label-based weight and value-based weight in the loss function by utilizing the unbalanced nature of the time series anomaly detection problem. Compared with the widely used forecasting-based anomaly detection algorithms, decomposition-based algorithms, traditional statistical algorithms, as well as recent neural network based algorithms, RobustTAD performs significantly better on public benchmark datasets. It is deployed as a public online service and widely adopted in different business scenarios at Alibaba Group.