PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2002.03230

Hierarchical Generation of Molecular Graphs using Structural Motifs

Graph generation techniques are increasingly being adopted for drug discovery. Previous graph generation approaches have utilized relatively small molecular building blocks such as atoms or simple cycles, limiting their effectiveness to smaller molecules. Indeed, as we demonstrate, their performance degrades significantly for larger molecules. In this paper, we propose a new hierarchical graph encoder-decoder that employs significantly larger and more flexible graph motifs as basic building blocks. Our encoder produces a multi-resolution representation for each molecule in a fine-to-coarse fashion, from atoms to connected motifs. Each level integrates the encoding of constituents below with the graph at that level. Our autoregressive coarse-to-fine decoder adds one motif at a time, interleaving the decision of selecting a new motif with the process of resolving its attachments to the emerging molecule. We evaluate our model on multiple molecule generation tasks, including polymers, and show that our model significantly outperforms previous state-of-the-art baselines.

arXiv:2002.03665공식 코드 · Papers with Code

AnomalyDAE: Dual autoencoder for anomaly detection on attributed networks

Anomaly detection on attributed networks aims at finding nodes whose patterns deviate significantly from the majority of reference nodes, which is pervasive in many applications such as network intrusion detection and social spammer detection. However, most existing methods neglect the complex cross-modality interactions between network structure and node attribute. In this paper, we propose a deep joint representation learning framework for anomaly detection through a dual autoencoder (AnomalyDAE), which captures the complex interactions between network structure and node attribute for high-quality embeddings. Specifically, AnomalyDAE consists of a structure autoencoder and an attribute autoencoder to learn both node embedding and attribute embedding jointly in latent space. Moreover, attention mechanism is employed in structure encoder to learn the importance between a node and its neighbors for an effective capturing of structure pattern, which is important to anomaly detection. Besides, by taking both the node embedding and attribute embedding as inputs of attribute decoder, the cross-modality interactions between network structure and node attribute are learned during the reconstruction of node attribute. Finally, anomalies can be detected by measuring the reconstruction errors of nodes from both the structure and attribute perspectives. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed method.

arXiv:2002.03651

CRVOS: Clue Refining Network for Video Object Segmentation

The encoder-decoder based methods for semi-supervised video object segmentation (Semi-VOS) have received extensive attention due to their superior performances. However, most of them have complex intermediate networks which generate strong specifiers to be robust against challenging scenarios, and this is quite inefficient when dealing with relatively simple scenarios. To solve this problem, we propose a real-time network, Clue Refining Network for Video Object Segmentation (CRVOS), that does not have any intermediate network to efficiently deal with these scenarios. In this work, we propose a simple specifier, referred to as the Clue, which consists of the previous frame's coarse mask and coordinates information. We also propose a novel refine module which shows the better performance compared with the general ones by using a deconvolution layer instead of a bilinear upsampling layer. Our proposed method shows the fastest speed among the existing methods with a competitive accuracy. On DAVIS 2016 validation set, our method achieves 63.5 fps and J&F score of 81.6%.

arXiv:2002.03921

End-to-End Multi-speaker Speech Recognition with Transformer

Recently, fully recurrent neural network (RNN) based end-to-end models have been proven to be effective for multi-speaker speech recognition in both the single-channel and multi-channel scenarios. In this work, we explore the use of Transformer models for these tasks by focusing on two aspects. First, we replace the RNN-based encoder-decoder in the speech recognition model with a Transformer architecture. Second, in order to use the Transformer in the masking network of the neural beamformer in the multi-channel case, we modify the self-attention component to be restricted to a segment rather than the whole sequence in order to reduce computation. Besides the model architecture improvements, we also incorporate an external dereverberation preprocessing, the weighted prediction error (WPE), enabling our model to handle reverberated signals. Experiments on the spatialized wsj1-2mix corpus show that the Transformer-based models achieve 40.9% and 25.6% relative WER reduction, down to 12.1% and 6.4% WER, under the anechoic condition in single-channel and multi-channel tasks, respectively, while in the reverberant case, our methods achieve 41.5% and 13.8% relative WER reduction, down to 16.5% and 15.2% WER.

arXiv:2002.02758공식 코드 · Papers with Code

Neural Machine Translation System of Indic Languages -- An Attention based Approach

Neural machine translation (NMT) is a recent and effective technique which led to remarkable improvements in comparison of conventional machine translation techniques. Proposed neural machine translation model developed for the Gujarati language contains encoder-decoder with attention mechanism. In India, almost all the languages are originated from their ancestral language - Sanskrit. They are having inevitable similarities including lexical and named entity similarity. Translating into Indic languages is always be a challenging task. In this paper, we have presented the neural machine translation system (NMT) that can efficiently translate Indic languages like Hindi and Gujarati that together covers more than 58.49 percentage of total speakers in the country. We have compared the performance of our NMT model with automatic evaluation matrices such as BLEU, perplexity and TER matrix. The comparison of our network with Google translate is also presented where it outperformed with a margin of 6 BLEU score on English-Gujarati translation.

arXiv:2002.02709공식 코드 · Papers with Code

FourierNet: Compact mask representation for instance segmentation using differentiable shape decoders

We present FourierNet, a single shot, anchor-free, fully convolutional instance segmentation method that predicts a shape vector. Consequently, this shape vector is converted into the masks' contour points using a fast numerical transform. Compared to previous methods, we introduce a new training technique, where we utilize a differentiable shape decoder, which manages the automatic weight balancing of the shape vector's coefficients. We used the Fourier series as a shape encoder because of its coefficient interpretability and fast implementation. FourierNet shows promising results compared to polygon representation methods, achieving 30.6 mAP on the MS COCO 2017 benchmark. At lower image resolutions, it runs at 26.6 FPS with 24.3 mAP. It reaches 23.3 mAP using just eight parameters to represent the mask (note that at least four parameters are needed for bounding box prediction only). Qualitative analysis shows that suppressing a reasonable proportion of higher frequencies of Fourier series, still generates meaningful masks. These results validate our understanding that lower frequency components hold higher information for the segmentation task, and therefore, we can achieve a compressed representation. Code is available at: github.com/cogsys-tuebingen/FourierNet.

arXiv:2002.02649

Multimodal Matching Transformer for Live Commenting

Automatic live commenting aims to provide real-time comments on videos for viewers. It encourages users engagement on online video sites, and is also a good benchmark for video-to-text generation. Recent work on this task adopts encoder-decoder models to generate comments. However, these methods do not model the interaction between videos and comments explicitly, so they tend to generate popular comments that are often irrelevant to the videos. In this work, we aim to improve the relevance between live comments and videos by modeling the cross-modal interactions among different modalities. To this end, we propose a multimodal matching transformer to capture the relationships among comments, vision, and audio. The proposed model is based on the transformer framework and can iteratively learn the attention-aware representations for each modality. We evaluate the model on a publicly available live commenting dataset. Experiments show that the multimodal matching transformer model outperforms the state-of-the-art methods.

arXiv:2002.01568

DVNet: A Memory-Efficient Three-Dimensional CNN for Large-Scale Neurovascular Reconstruction

Maps of brain microarchitecture are important for understanding neurological function and behavior, including alterations caused by chronic conditions such as neurodegenerative disease. Techniques such as knife-edge scanning microscopy (KESM) provide the potential for whole organ imaging at sub-cellular resolution. However, multi-terabyte data sizes make manual annotation impractical and automatic segmentation challenging. Densely packed cells combined with interconnected microvascular networks are a challenge for current segmentation algorithms. The massive size of high-throughput microscopy data necessitates fast and largely unsupervised algorithms. In this paper, we investigate a fully-convolutional, deep, and densely-connected encoder-decoder for pixel-wise semantic segmentation. The excessive memory complexity often encountered with deep and dense networks is mitigated using skip connections, resulting in fewer parameters and enabling a significant performance increase over prior architectures. The proposed network provides superior performance for semantic segmentation problems applied to open-source benchmarks. We finally demonstrate our network for cellular and microvascular segmentation, enabling quantitative metrics for organ-scale neurovascular analysis.

arXiv:2002.01276

GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition

Connectionist Temporal Classification (CTC) and attention mechanism are two main approaches used in recent scene text recognition works. Compared with attention-based methods, CTC decoder has a much shorter inference time, yet a lower accuracy. To design an efficient and effective model, we propose the guided training of CTC (GTC), where CTC model learns a better alignment and feature representations from a more powerful attentional guidance. With the benefit of guided training, CTC model achieves robust and accurate prediction for both regular and irregular scene text while maintaining a fast inference speed. Moreover, to further leverage the potential of CTC decoder, a graph convolutional network (GCN) is proposed to learn the local correlations of extracted features. Extensive experiments on standard benchmarks demonstrate that our end-to-end model achieves a new state-of-the-art for regular and irregular scene text recognition and needs 6 times shorter inference time than attentionbased methods.

arXiv:2002.01145공식 코드 · Papers with Code

Syntactically Look-Ahead Attention Network for Sentence Compression

Sentence compression is the task of compressing a long sentence into a short one by deleting redundant words. In sequence-to-sequence (Seq2Seq) based models, the decoder unidirectionally decides to retain or delete words. Thus, it cannot usually explicitly capture the relationships between decoded words and unseen words that will be decoded in the future time steps. Therefore, to avoid generating ungrammatical sentences, the decoder sometimes drops important words in compressing sentences. To solve this problem, we propose a novel Seq2Seq model, syntactically look-ahead attention network (SLAHAN), that can generate informative summaries by explicitly tracking both dependency parent and child words during decoding and capturing important words that will be decoded in the future. The results of the automatic evaluation on the Google sentence compression dataset showed that SLAHAN achieved the best kept-token-based-F1, ROUGE-1, ROUGE-2 and ROUGE-L scores of 85.5, 79.3, 71.3 and 79.1, respectively. SLAHAN also improved the summarization performance on longer sentences. Furthermore, in the human evaluation, SLAHAN improved informativeness without losing readability.

arXiv:2002.01127공식 코드 · Papers with Code

Variational Template Machine for Data-to-Text Generation

How to generate descriptions from structured data organized in tables? Existing approaches using neural encoder-decoder models often suffer from lacking diversity. We claim that an open set of templates is crucial for enriching the phrase constructions and realizing varied generations. Learning such templates is prohibitive since it often requires a large paired <table, description> corpus, which is seldom available. This paper explores the problem of automatically learning reusable "templates" from paired and non-paired data. We propose the variational template machine (VTM), a novel method to generate text descriptions from data tables. Our contributions include: a) we carefully devise a specific model architecture and losses to explicitly disentangle text template and semantic content information, in the latent spaces, and b)we utilize both small parallel data and large raw text without aligned tables to enrich the template learning. Experiments on datasets from a variety of different domains show that VTM is able to generate more diversely while keeping a good fluency and quality.

arXiv:2002.00522

Novelty Detection via Non-Adversarial Generative Network

One-class novelty detection is the process of determining if a query example differs from the training examples (the target class). Most of previous strategies attempt to learn the real characteristics of target sample by using generative adversarial networks (GANs) methods. However, the training process of GANs remains challenging, suffering from instability issues such as mode collapse and vanishing gradients. In this paper, by adopting non-adversarial generative networks, a novel decoder-encoder framework is proposed for novelty detection task, insteading of classical encoder-decoder style. Under the non-adversarial framework, both latent space and image reconstruction space are jointly optimized, leading to a more stable training process with super fast convergence and lower training losses. During inference, inspired by cycleGAN, we design a new testing scheme to conduct image reconstruction, which is the reverse way of training sequence. Experiments show that our model has the clear superiority over cutting-edge novelty detectors and achieves the state-of-the-art results on the datasets.

arXiv:2002.00199

Large Hole Image Inpainting With Compress-Decompression Network

Image inpainting technology can patch images with missing pixels. Existing methods propose convolutional neural networks to repair corrupted images. The networks focus on the valid pixels around the missing pixels, use the encoder-decoder structure to extract valuable information, and use the information to fix the vacancy. However, if the missing part is too large to provide useful information, the result will exist blur, color mixing, and object confusion. In order to patch the large hole image, we study the existing approaches and propose a new network, the compression-decompression network. The compression network takes responsibility for inpainting and generating a down-sample image. The decompression network takes responsibility for extending the down-sample image into the original resolution. We construct the compression network with the residual network and propose a similar texture selection algorithm to extend the image that is better than using the super-resolution network. We evaluate our model over Places2 and CelebA data set and use the similarity ratio as the metric. The result shows that our model has better performance when the inpainting task has many conflicts.

arXiv:2001.11694

Pseudo-Bidirectional Decoding for Local Sequence Transduction

Local sequence transduction (LST) tasks are sequence transduction tasks where there exists massive overlapping between the source and target sequences, such as Grammatical Error Correction (GEC) and spell or OCR correction. Previous work generally tackles LST tasks with standard sequence-to-sequence (seq2seq) models that generate output tokens from left to right and suffer from the issue of unbalanced outputs. Motivated by the characteristic of LST tasks, in this paper, we propose a simple but versatile approach named Pseudo-Bidirectional Decoding (PBD) for LST tasks. PBD copies the corresponding representation of source tokens to the decoder as pseudo future context to enable the decoder to attends to its bi-directional context. In addition, the bidirectional decoding scheme and the characteristic of LST tasks motivate us to share the encoder and the decoder of seq2seq models. The proposed PBD approach provides right side context information for the decoder and models the inductive bias of LST tasks, reducing the number of parameters by half and providing good regularization effects. Experimental results on several benchmark datasets show that our approach consistently improves the performance of standard seq2seq models on LST tasks.

arXiv:2001.11690

C-DLinkNet: considering multi-level semantic features for human parsing

Human parsing is an essential branch of semantic segmentation, which is a fine-grained semantic segmentation task to identify the constituent parts of human. The challenge of human parsing is to extract effective semantic features to resolve deformation and multi-scale variations. In this work, we proposed an end-to-end model called C-DLinkNet based on LinkNet, which contains a new module named Smooth Module to combine the multi-level features in Decoder part. C-DLinkNet is capable of producing competitive parsing performance compared with the state-of-the-art methods with smaller input sizes and no additional information, i.e., achiving mIoU=53.05 on the validation set of LIP dataset.

arXiv:2001.11561

Dual Convolutional LSTM Network for Referring Image Segmentation

We consider referring image segmentation. It is a problem at the intersection of computer vision and natural language understanding. Given an input image and a referring expression in the form of a natural language sentence, the goal is to segment the object of interest in the image referred by the linguistic query. To this end, we propose a dual convolutional LSTM (ConvLSTM) network to tackle this problem. Our model consists of an encoder network and a decoder network, where ConvLSTM is used in both encoder and decoder networks to capture spatial and sequential information. The encoder network extracts visual and linguistic features for each word in the expression sentence, and adopts an attention mechanism to focus on words that are more informative in the multimodal interaction. The decoder network integrates the features generated by the encoder network at multiple levels as its input and produces the final precise segmentation mask. Experimental results on four challenging datasets demonstrate that the proposed network achieves superior segmentation performance compared with other state-of-the-art methods.

arXiv:2001.11314

ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation

Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks. To address this issue, we propose an enhanced multi-flow sequence to sequence pre-training and fine-tuning framework named ERNIE-GEN, which bridges the discrepancy between training and inference with an infilling generation mechanism and a noise-aware generation method. To make generation closer to human writing patterns, this framework introduces a span-by-span generation flow that trains the model to predict semantically-complete spans consecutively rather than predicting word by word. Unlike existing pre-training methods, ERNIE-GEN incorporates multi-granularity target sampling to construct pre-training data, which enhances the correlation between encoder and decoder. Experimental results demonstrate that ERNIE-GEN achieves state-of-the-art results with a much smaller amount of pre-training data and parameters on a range of language generation tasks, including abstractive summarization (Gigaword and CNN/DailyMail), question generation (SQuAD), dialogue generation (Persona-Chat) and generative question answering (CoQA).

arXiv:2001.11402공식 코드 · Papers with Code

Graph Convolution Machine for Context-aware Recommender System

The latest advance in recommendation shows that better user and item representations can be learned via performing graph convolutions on the user-item interaction graph. However, such finding is mostly restricted to the collaborative filtering (CF) scenario, where the interaction contexts are not available. In this work, we extend the advantages of graph convolutions to context-aware recommender system (CARS, which represents a generic type of models that can handle various side information). We propose \textit{Graph Convolution Machine} (GCM), an end-to-end framework that consists of three components: an encoder, graph convolution (GC) layers, and a decoder. The encoder projects users, items, and contexts into embedding vectors, which are passed to the GC layers that refine user and item embeddings with context-aware graph convolutions on user-item graph. The decoder digests the refined embeddings to output the prediction score by considering the interactions among user, item, and context embeddings. We conduct experiments on three real-world datasets from Yelp and Amazon, validating the effectiveness of GCM and the benefits of performing graph convolutions for CARS. Our implementations are available at \url{https://github.com/wujcan/GCM}.

arXiv:2001.10291

Spatial-Adaptive Network for Single Image Denoising

Previous works have shown that convolutional neural networks can achieve good performance in image denoising tasks. However, limited by the local rigid convolutional operation, these methods lead to oversmoothing artifacts. A deeper network structure could alleviate these problems, but more computational overhead is needed. In this paper, we propose a novel spatial-adaptive denoising network (SADNet) for efficient single image blind noise removal. To adapt to changes in spatial textures and edges, we design a residual spatial-adaptive block. Deformable convolution is introduced to sample the spatially correlated features for weighting. An encoder-decoder structure with a context block is introduced to capture multiscale information. With noise removal from the coarse to fine, a high-quality noisefree image can be obtained. We apply our method to both synthetic and real noisy image datasets. The experimental results demonstrate that our method can surpass the state-of-the-art denoising methods both quantitatively and visually.

arXiv:2001.10188

Robust Method for Semantic Segmentation of Whole-Slide Blood Cell Microscopic Image

Previous works on segmentation of SEM (scanning electron microscope) blood cell image ignore the semantic segmentation approach of whole-slide blood cell segmentation. In the proposed work, we address the problem of whole-slide blood cell segmentation using the semantic segmentation approach. We design a novel convolutional encoder-decoder framework along with VGG-16 as the pixel-level feature extraction model. -e proposed framework comprises 3 main steps: First, all the original images along with manually generated ground truth masks of each blood cell type are passed through the preprocessing stage. In the preprocessing stage, pixel-level labeling, RGB to grayscale conversion of masked image and pixel fusing, and unity mask generation are performed. After that, VGG16 is loaded into the system, which acts as a pretrained pixel-level feature extraction model. In the third step, the training process is initiated on the proposed model. We have evaluated our network performance on three evaluation metrics. We obtained outstanding results with respect to classwise, as well as global and mean accuracies. Our system achieved classwise accuracies of 97.45%, 93.34%, and 85.11% for RBCs, WBCs, and platelets, respectively, while global and mean accuracies remain 97.18% and 91.96%, respectively.