PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2011.07680

Reinforced Medical Report Generation with X-Linear Attention and Repetition Penalty

To reduce doctors' workload, deep-learning-based automatic medical report generation has recently attracted more and more research efforts, where attention mechanisms and reinforcement learning are integrated with the classic encoder-decoder architecture to enhance the performance of deep models. However, these state-of-the-art solutions mainly suffer from two shortcomings: (i) their attention mechanisms cannot utilize high-order feature interactions, and (ii) due to the use of TF-IDF-based reward functions, these methods are fragile with generating repeated terms. Therefore, in this work, we propose a reinforced medical report generation solution with x-linear attention and repetition penalty mechanisms (ReMRG-XR) to overcome these problems. Specifically, x-linear attention modules are used to explore high-order feature interactions and achieve multi-modal reasoning, while repetition penalty is used to apply penalties to repeated terms during the model's training process. Extensive experimental studies have been conducted on two public datasets, and the results show that ReMRG-XR greatly outperforms the state-of-the-art baselines in terms of all metrics.

arXiv:2011.06409

End-to-end optimized image compression for machines, a study

An increasing share of image and video content is analyzed by machines rather than viewed by humans, and therefore it becomes relevant to optimize codecs for such applications where the analysis is performed remotely. Unfortunately, conventional coding tools are challenging to specialize for machine tasks as they were originally designed for human perception. However, neural network based codecs can be jointly trained end-to-end with any convolutional neural network (CNN)-based task model. In this paper, we propose to study an end-to-end framework enabling efficient image compression for remote machine task analysis, using a chain composed of a compression module and a task algorithm that can be optimized end-to-end. We show that it is possible to significantly improve the task accuracy when fine-tuning jointly the codec and the task networks, especially at low bit-rates. Depending on training or deployment constraints, selective fine-tuning can be applied only on the encoder, decoder or task network and still achieve rate-accuracy improvements over an off-the-shelf codec and task network. Our results also demonstrate the flexibility of end-to-end pipelines for practical applications.

arXiv:2011.06125공식 코드 · Papers with Code

Hurricane Forecasting: A Novel Multimodal Machine Learning Framework

This paper describes a novel machine learning (ML) framework for tropical cyclone intensity and track forecasting, combining multiple ML techniques and utilizing diverse data sources. Our multimodal framework, called Hurricast, efficiently combines spatial-temporal data with statistical data by extracting features with deep-learning encoder-decoder architectures and predicting with gradient-boosted trees. We evaluate our models in the North Atlantic and Eastern Pacific basins on 2016-2019 for 24-hour lead time track and intensity forecasts and show they achieve comparable mean absolute error and skill to current operational forecast models while computing in seconds. Furthermore, the inclusion of Hurricast into an operational forecast consensus model could improve over the National Hurricane Center's official forecast, thus highlighting the complementary properties with existing approaches. In summary, our work demonstrates that utilizing machine learning techniques to combine different data sources can lead to new opportunities in tropical cyclone forecasting.

arXiv:2011.06427

Realization of Stochastic Neural Networks and Its Potential Applications

Successive Cancellation Decoders have come a long way since the implementation of traditional SC decoders, but there still is a potential for improvement. The main struggle over the years was to find an optimal algorithm to implement them. Most of the proposed algorithms are not practical enough to be implemented in real-life. In this research, we aim to introduce the Efficiency of stochastic neural networks as an SC decoder and Find the possible ways of improving its performance and practicality. In this paper, after a brief introduction to stochastic neurons and SNNs, we introduce methods to realize Stochastic NNs on both deterministic and stochastic platforms.

arXiv:2011.06380

Automatic Neural Lyrics and Melody Composition

In this paper, we propose a technique to address the most challenging aspect of algorithmic songwriting process, which enables the human community to discover original lyrics, and melodies suitable for the generated lyrics. The proposed songwriting system, Automatic Neural Lyrics and Melody Composition (AutoNLMC) is an attempt to make the whole process of songwriting automatic using artificial neural networks. Our lyric to vector (lyric2vec) model trained on a large set of lyric-melody pairs dataset parsed at syllable, word and sentence levels are large scale embedding models enable us to train data driven model such as recurrent neural networks for popular English songs. AutoNLMC is a encoder-decoder sequential recurrent neural network model consisting of a lyric generator, a lyric encoder and melody decoder trained end-to-end. AutoNLMC is designed to generate both lyrics and corresponding melody automatically for an amateur or a person without music knowledge. It can also take lyrics from professional lyric writer to generate matching melodies. The qualitative and quantitative evaluation measures revealed that the proposed method is indeed capable of generating original lyrics and corresponding melody for composing new songs.

arXiv:2011.06224

Decomposing Normal and Abnormal Features of Medical Images for Content-based Image Retrieval

Medical images can be decomposed into normal and abnormal features, which is considered as the compositionality. Based on this idea, we propose an encoder-decoder network to decompose a medical image into two discrete latent codes: a normal anatomy code and an abnormal anatomy code. Using these latent codes, we demonstrate a similarity retrieval by focusing on either normal or abnormal features of medical images.

arXiv:2011.05449

From Unsupervised Machine Translation To Adversarial Text Generation

We present a self-attention based bilingual adversarial text generator (B-GAN) which can learn to generate text from the encoder representation of an unsupervised neural machine translation system. B-GAN is able to generate a distributed latent space representation which can be paired with an attention based decoder to generate fluent sentences. When trained on an encoder shared between two languages and paired with the appropriate decoder, it can generate sentences in either language. B-GAN is trained using a combination of reconstruction loss for auto-encoder, a cross domain loss for translation and a GAN based adversarial loss for text generation. We demonstrate that B-GAN, trained on monolingual corpora only using multiple losses, generates more fluent sentences compared to monolingual baselines while effectively using half the number of parameters.

arXiv:2011.05680공식 코드 · Papers with Code

Zero-Pair Image to Image Translation using Domain Conditional Normalization

In this paper, we propose an approach based on domain conditional normalization (DCN) for zero-pair image-to-image translation, i.e., translating between two domains which have no paired training data available but each have paired training data with a third domain. We employ a single generator which has an encoder-decoder structure and analyze different implementations of domain conditional normalization to obtain the desired target domain output. The validation benchmark uses RGB-depth pairs and RGB-semantic pairs for training and compares performance for the depth-semantic translation task. The proposed approaches improve in qualitative and quantitative terms over the compared methods, while using much fewer parameters. Code available at https://github.com/samarthshukla/dcn

arXiv:2011.05670공식 코드 · Papers with Code

FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification

Deep learning techniques have provided significant improvements in hyperspectral image (HSI) classification. The current deep learning based HSI classifiers follow a patch-based learning framework by dividing the image into overlapping patches. As such, these methods are local learning methods, which have a high computational cost. In this paper, a fast patch-free global learning (FPGA) framework is proposed for HSI classification. In FPGA, an encoder-decoder based FCN is utilized to consider the global spatial information by processing the whole image, which results in fast inference. However, it is difficult to directly utilize the encoder-decoder based FCN for HSI classification as it always fails to converge due to the insufficiently diverse gradients caused by the limited training samples. To solve the divergence problem and maintain the abilities of FCN of fast inference and global spatial information mining, a global stochastic stratified sampling strategy is first proposed by transforming all the training samples into a stochastic sequence of stratified samples. This strategy can obtain diverse gradients to guarantee the convergence of the FCN in the FPGA framework. For a better design of FCN architecture, FreeNet, which is a fully end-to-end network for HSI classification, is proposed to maximize the exploitation of the global spatial information and boost the performance via a spectral attention based encoder and a lightweight decoder. A lateral connection module is also designed to connect the encoder and decoder, fusing the spatial details in the encoder and the semantic features in the decoder. The experimental results obtained using three public benchmark datasets suggest that the FPGA framework is superior to the patch-based framework in both speed and accuracy for HSI classification. Code has been made available at: https://github.com/Z-Zheng/FreeNet.

arXiv:2011.05161

Improving Prosody Modelling with Cross-Utterance BERT Embeddings for End-to-end Speech Synthesis

Despite prosody is related to the linguistic information up to the discourse structure, most text-to-speech (TTS) systems only take into account that within each sentence, which makes it challenging when converting a paragraph of texts into natural and expressive speech. In this paper, we propose to use the text embeddings of the neighboring sentences to improve the prosody generation for each utterance of a paragraph in an end-to-end fashion without using any explicit prosody features. More specifically, cross-utterance (CU) context vectors, which are produced by an additional CU encoder based on the sentence embeddings extracted by a pre-trained BERT model, are used to augment the input of the Tacotron2 decoder. Two types of BERT embeddings are investigated, which leads to the use of different CU encoder structures. Experimental results on a Mandarin audiobook dataset and the LJ-Speech English audiobook dataset demonstrate the use of CU information can improve the naturalness and expressiveness of the synthesized speech. Subjective listening testing shows most of the participants prefer the voice generated using the CU encoder over that generated using standard Tacotron2. It is also found that the prosody can be controlled indirectly by changing the neighbouring sentences.

arXiv:2011.05088공식 코드 · Papers with Code

MP-ResNet: Multi-path Residual Network for the Semantic segmentation of High-Resolution PolSAR Images

There are limited studies on the semantic segmentation of high-resolution Polarimetric Synthetic Aperture Radar (PolSAR) images due to the scarcity of training data and the inference of speckle noises. The Gaofen contest has provided open access of a high-quality PolSAR semantic segmentation dataset. Taking this chance, we propose a Multi-path ResNet (MP-ResNet) architecture for the semantic segmentation of high-resolution PolSAR images. Compared to conventional U-shape encoder-decoder convolutional neural network (CNN) architectures, the MP-ResNet learns semantic context with its parallel multi-scale branches, which greatly enlarges its valid receptive fields and improves the embedding of local discriminative features. In addition, MP-ResNet adopts a multi-level feature fusion design in its decoder to make the best use of the features learned from its different branches. Ablation studies show that the MPResNet has significant advantages over its baseline method (FCN with ResNet34). It also surpasses several classic state-of-the-art methods in terms of overall accuracy (OA), mean F1 and fwIoU, whereas its computational costs are not much increased. This CNN architecture can be used as a baseline method for future studies on the semantic segmentation of PolSAR images. The code is available at: https://github.com/ggsDing/SARSeg.

arXiv:2011.04887공식 코드 · Papers with Code

CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection

Co-Salient Object Detection (CoSOD) aims at discovering salient objects that repeatedly appear in a given query group containing two or more relevant images. One challenging issue is how to effectively capture co-saliency cues by modeling and exploiting inter-image relationships. In this paper, we present an end-to-end collaborative aggregation-and-distribution network (CoADNet) to capture both salient and repetitive visual patterns from multiple images. First, we integrate saliency priors into the backbone features to suppress the redundant background information through an online intra-saliency guidance structure. After that, we design a two-stage aggregate-and-distribute architecture to explore group-wise semantic interactions and produce the co-saliency features. In the first stage, we propose a group-attentional semantic aggregation module that models inter-image relationships to generate the group-wise semantic representations. In the second stage, we propose a gated group distribution module that adaptively distributes the learned group semantics to different individuals in a dynamic gating mechanism. Finally, we develop a group consistency preserving decoder tailored for the CoSOD task, which maintains group constraints during feature decoding to predict more consistent full-resolution co-saliency maps. The proposed CoADNet is evaluated on four prevailing CoSOD benchmark datasets, which demonstrates the remarkable performance improvement over ten state-of-the-art competitors.

arXiv:2011.03568

Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis

We describe a sequence-to-sequence neural network which directly generates speech waveforms from text inputs. The architecture extends the Tacotron model by incorporating a normalizing flow into the autoregressive decoder loop. Output waveforms are modeled as a sequence of non-overlapping fixed-length blocks, each one containing hundreds of samples. The interdependencies of waveform samples within each block are modeled using the normalizing flow, enabling parallel training and synthesis. Longer-term dependencies are handled autoregressively by conditioning each flow on preceding blocks.This model can be optimized directly with maximum likelihood, with-out using intermediate, hand-designed features nor additional loss terms. Contemporary state-of-the-art text-to-speech (TTS) systems use a cascade of separately learned models: one (such as Tacotron) which generates intermediate features (such as spectrograms) from text, followed by a vocoder (such as WaveRNN) which generates waveform samples from the intermediate features. The proposed system, in contrast, does not use a fixed intermediate representation, and learns all parameters end-to-end. Experiments show that the proposed model generates speech with quality approaching a state-of-the-art neural TTS system, with significantly improved generation speed.

arXiv:2011.03722

Template Controllable keywords-to-text Generation

This paper proposes a novel neural model for the understudied task of generating text from keywords. The model takes as input a set of un-ordered keywords, and part-of-speech (POS) based template instructions. This makes it ideal for surface realization in any NLG setup. The framework is based on the encode-attend-decode paradigm, where keywords and templates are encoded first, and the decoder judiciously attends over the contexts derived from the encoded keywords and templates to generate the sentences. Training exploits weak supervision, as the model trains on a large amount of labeled data with keywords and POS based templates prepared through completely automatic means. Qualitative and quantitative performance analyses on publicly available test-data in various domains reveal our system's superiority over baselines, built using state-of-the-art neural machine translation and controllable transfer techniques. Our approach is indifferent to the order of input keywords.

arXiv:2011.04266

BERT-JAM: Boosting BERT-Enhanced Neural Machine Translation with Joint Attention

BERT-enhanced neural machine translation (NMT) aims at leveraging BERT-encoded representations for translation tasks. A recently proposed approach uses attention mechanisms to fuse Transformer's encoder and decoder layers with BERT's last-layer representation and shows enhanced performance. However, their method doesn't allow for the flexible distribution of attention between the BERT representation and the encoder/decoder representation. In this work, we propose a novel BERT-enhanced NMT model called BERT-JAM which improves upon existing models from two aspects: 1) BERT-JAM uses joint-attention modules to allow the encoder/decoder layers to dynamically allocate attention between different representations, and 2) BERT-JAM allows the encoder/decoder layers to make use of BERT's intermediate representations by composing them using a gated linear unit (GLU). We train BERT-JAM with a novel three-phase optimization strategy that progressively unfreezes different components of BERT-JAM. Our experiments show that BERT-JAM achieves SOTA BLEU scores on multiple translation tasks.

arXiv:2011.04197공식 코드 · Papers with Code

Detecting Outliers with Foreign Patch Interpolation

In medical imaging, outliers can contain hypo/hyper-intensities, minor deformations, or completely altered anatomy. To detect these irregularities it is helpful to learn the features present in both normal and abnormal images. However this is difficult because of the wide range of possible abnormalities and also the number of ways that normal anatomy can vary naturally. As such, we leverage the natural variations in normal anatomy to create a range of synthetic abnormalities. Specifically, the same patch region is extracted from two independent samples and replaced with an interpolation between both patches. The interpolation factor, patch size, and patch location are randomly sampled from uniform distributions. A wide residual encoder decoder is trained to give a pixel-wise prediction of the patch and its interpolation factor. This encourages the network to learn what features to expect normally and to identify where foreign patterns have been introduced. The estimate of the interpolation factor lends itself nicely to the derivation of an outlier score. Meanwhile the pixel-wise output allows for pixel- and subject- level predictions using the same model.

arXiv:2011.03428

Illumination Normalization by Partially Impossible Encoder-Decoder Cost Function

Images recorded during the lifetime of computer vision based systems undergo a wide range of illumination and environmental conditions affecting the reliability of previously trained machine learning models. Image normalization is hence a valuable preprocessing component to enhance the models' robustness. To this end, we introduce a new strategy for the cost function formulation of encoder-decoder networks to average out all the unimportant information in the input images (e.g. environmental features and illumination changes) to focus on the reconstruction of the salient features (e.g. class instances). Our method exploits the availability of identical sceneries under different illumination and environmental conditions for which we formulate a partially impossible reconstruction target: the input image will not convey enough information to reconstruct the target in its entirety. Its applicability is assessed on three publicly available datasets. We combine the triplet loss as a regularizer in the latent space representation and a nearest neighbour search to improve the generalization to unseen illuminations and class instances. The importance of the aforementioned post-processing is highlighted on an automotive application. To this end, we release a synthetic dataset of sceneries from three different passenger compartments where each scenery is rendered under ten different illumination and environmental conditions: see https://sviro.kl.dfki.de

arXiv:2011.03188공식 코드 · Papers with Code

Automatic Brain Tumor Segmentation with Scale Attention Network

Automatic segmentation of brain tumors is an essential but challenging step for extracting quantitative imaging biomarkers for accurate tumor detection, diagnosis, prognosis, treatment planning and assessment. Multimodal Brain Tumor Segmentation Challenge 2020 (BraTS 2020) provides a common platform for comparing different automatic algorithms on multi-parametric Magnetic Resonance Imaging (mpMRI) in tasks of 1) Brain tumor segmentation MRI scans; 2) Prediction of patient overall survival (OS) from pre-operative MRI scans; 3) Distinction of true tumor recurrence from treatment related effects and 4) Evaluation of uncertainty measures in segmentation. We participate the image segmentation challenge by developing a fully automatic segmentation network based on encoder-decoder architecture. In order to better integrate information across different scales, we propose a dynamic scale attention mechanism that incorporates low-level details with high-level semantics from feature maps at different scales. Our framework was trained using the 369 challenge training cases provided by BraTS 2020, and achieved an average Dice Similarity Coefficient (DSC) of 0.8828, 0.8433 and 0.8177, as well as 95% Hausdorff distance (in millimeter) of 5.2176, 17.9697 and 13.4298 on 166 testing cases for whole tumor, tumor core and enhanced tumor, respectively, which ranked itself as the 3rd place among 693 registrations in the BraTS 2020 challenge.

arXiv:2011.02881공식 코드 · Papers with Code

A Two-Stage Cascade Model with Variational Autoencoders and Attention Gates for MRI Brain Tumor Segmentation

Automatic MRI brain tumor segmentation is of vital importance for the disease diagnosis, monitoring, and treatment planning. In this paper, we propose a two-stage encoder-decoder based model for brain tumor subregional segmentation. Variational autoencoder regularization is utilized in both stages to prevent the overfitting issue. The second-stage network adopts attention gates and is trained additionally using an expanded dataset formed by the first-stage outputs. On the BraTS 2020 validation dataset, the proposed method achieves the mean Dice score of 0.9041, 0.8350, and 0.7958, and Hausdorff distance (95%) of 4.953, 6.299, and 23.608 for the whole tumor, tumor core, and enhancing tumor, respectively. The corresponding results on the BraTS 2020 testing dataset are 0.8729, 0.8357, and 0.8205 for Dice score, and 11.4288, 19.9690, and 15.6711 for Hausdorff distance. The code is publicly available at https://github.com/shu-hai/two-stage-VAE-Attention-gate-BraTS2020.

arXiv:2011.02879

Robust building footprint extraction from big multi-sensor data using deep competition network

Building footprint extraction (BFE) from multi-sensor data such as optical images and light detection and ranging (LiDAR) point clouds is widely used in various fields of remote sensing applications. However, it is still challenging research topic due to relatively inefficient building extraction techniques from variety of complex scenes in multi-sensor data. In this study, we develop and evaluate a deep competition network (DCN) that fuses very high spatial resolution optical remote sensing images with LiDAR data for robust BFE. DCN is a deep superpixelwise convolutional encoder-decoder architecture using the encoder vector quantization with classified structure. DCN consists of five encoding-decoding blocks with convolutional weights for robust binary representation (superpixel) learning. DCN is trained and tested in a big multi-sensor dataset obtained from the state of Indiana in the United States with multiple building scenes. Comparison results of the accuracy assessment showed that DCN has competitive BFE performance in comparison with other deep semantic binary segmentation architectures. Therefore, we conclude that the proposed model is a suitable solution to the robust BFE from big multi-sensor data.