PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1903.11834

Feature Fusion Encoder Decoder Network For Automatic Liver Lesion Segmentation

Liver lesion segmentation is a difficult yet critical task for medical image analysis. Recently, deep learning based image segmentation methods have achieved promising performance, which can be divided into three categories: 2D, 2.5D and 3D, based on the dimensionality of the models. However, 2.5D and 3D methods can have very high complexity and 2D methods may not perform satisfactorily. To obtain competitive performance with low complexity, in this paper, we propose a Feature-fusion Encoder-Decoder Network (FED-Net) based 2D segmentation model to tackle the challenging problem of liver lesion segmentation from CT images. Our feature fusion method is based on the attention mechanism, which fuses high-level features carrying semantic information with low-level features having image details. Additionally, to compensate for the information loss during the upsampling process, a dense upsampling convolution and a residual convolutional structure are proposed. We tested our method on the dataset of MICCAI 2017 Liver Tumor Segmentation (LiTS) Challenge and achieved competitive results compared with other state-of-the-art methods.

arXiv:1903.11340

Multilevel Text Normalization with Sequence-to-Sequence Networks and Multisource Learning

We define multilevel text normalization as sequence-to-sequence processing that transforms naturally noisy text into a sequence of normalized units of meaning (morphemes) in three steps: 1) writing normalization, 2) lemmatization, 3) canonical segmentation. These steps are traditionally considered separate NLP tasks, with diverse solutions, evaluation schemes and data sources. We exploit the fact that all these tasks involve sub-word sequence-to-sequence transformation to propose a systematic solution for all of them using neural encoder-decoder technology. The specific challenge that we tackle in this paper is integrating the traditional know-how on separate tasks into the neural sequence-to-sequence framework to improve the state of the art. We address this challenge by enriching the general framework with mechanisms that allow processing the information on multiple levels of text organization (characters, morphemes, words, sentences) in combination with structural information (multilevel language model, part-of-speech) and heterogeneous sources (text, dictionaries). We show that our solution consistently improves on the current methods in all three steps. In addition, we analyze the performance of our system to show the specific contribution of the integrating components to the overall improvement.

arXiv:1903.11249

W-Net: Reinforced U-Net for Density Map Estimation

Crowd management is of paramount importance when it comes to preventing stampedes and saving lives, especially in a countries like China and India where the combined population is a third of the global population. Millions of people convene annually all around the nation to celebrate a myriad of events and crowd count estimation is the linchpin of the crowd management system that could prevent stampedes and save lives. We present a network for crowd counting which reports state of the art results on crowd counting benchmarks. Our contributions are, first, a U-Net inspired model which affords us to report state of the art results. Second, we propose an independent decoding Reinforcement branch which helps the network converge much earlier and also enables the network to estimate density maps with high Structural Similarity Index (SSIM). Third, we discuss the drawbacks of the contemporary architectures and empirically show that even though our architecture achieves state of the art results, the merit may be due to the encoder-decoder pipeline instead. Finally, we report the error analysis which shows that the contemporary line of work is at saturation and leaves certain prominent problems unsolved.

arXiv:1903.11228공식 코드 · Papers with Code

BAE-NET: Branched Autoencoder for Shape Co-Segmentation

We treat shape co-segmentation as a representation learning problem and introduce BAE-NET, a branched autoencoder network, for the task. The unsupervised BAE-NET is trained with a collection of un-segmented shapes, using a shape reconstruction loss, without any ground-truth labels. Specifically, the network takes an input shape and encodes it using a convolutional neural network, whereas the decoder concatenates the resulting feature code with a point coordinate and outputs a value indicating whether the point is inside/outside the shape. Importantly, the decoder is branched: each branch learns a compact representation for one commonly recurring part of the shape collection, e.g., airplane wings. By complementing the shape reconstruction loss with a label loss, BAE-NET is easily tuned for one-shot learning. We show unsupervised, weakly supervised, and one-shot learning results by BAE-NET, demonstrating that using only a couple of exemplars, our network can generally outperform state-of-the-art supervised methods trained on hundreds of segmented shapes. Code is available at https://github.com/czq142857/BAE-NET.

arXiv:1903.10869

V2CNet: A Deep Learning Framework to Translate Videos to Commands for Robotic Manipulation

We propose V2CNet, a new deep learning framework to automatically translate the demonstration videos to commands that can be directly used in robotic applications. Our V2CNet has two branches and aims at understanding the demonstration video in a fine-grained manner. The first branch has the encoder-decoder architecture to encode the visual features and sequentially generate the output words as a command, while the second branch uses a Temporal Convolutional Network (TCN) to learn the fine-grained actions. By jointly training both branches, the network is able to model the sequential information of the command, while effectively encodes the fine-grained actions. The experimental results on our new large-scale dataset show that V2CNet outperforms recent state-of-the-art methods by a substantial margin, while its output can be applied in real robotic applications. The source code and trained models will be made available.

arXiv:1903.10863

AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational Transformations

The learning of Transformation-Equivariant Representations (TERs), which is introduced by Hinton et al. \cite{hinton2011transforming}, has been considered as a principle to reveal visual structures under various transformations. It contains the celebrated Convolutional Neural Networks (CNNs) as a special case that only equivary to the translations. In contrast, we seek to train TERs for a generic class of transformations and train them in an {\em unsupervised} fashion. To this end, we present a novel principled method by Autoencoding Variational Transformations (AVT), compared with the conventional approach to autoencoding data. Formally, given transformed images, the AVT seeks to train the networks by maximizing the mutual information between the transformations and representations. This ensures the resultant TERs of individual images contain the {\em intrinsic} information about their visual structures that would equivary {\em extricably} under various transformations in a generalized {\em nonlinear} case. Technically, we show that the resultant optimization problem can be efficiently solved by maximizing a variational lower-bound of the mutual information. This variational approach introduces a transformation decoder to approximate the intractable posterior of transformations, resulting in an autoencoding architecture with a pair of the representation encoder and the transformation decoder. Experiments demonstrate the proposed AVT model sets a new record for the performances on unsupervised tasks, greatly closing the performance gap to the supervised models.

arXiv:1812.00876

Deep Learning based Pedestrian Detection at Distance in Smart Cities

Generative adversarial networks (GANs) have been promising for many computer vision problems due to their powerful capabilities to enhance the data for training and test. In this paper, we leveraged GANs and proposed a new architecture with a cascaded Single Shot Detector (SSD) for pedestrian detection at distance, which is yet a challenge due to the varied sizes of pedestrians in videos at distance. To overcome the low-resolution issues in pedestrian detection at distance, DCGAN is employed to improve the resolution first to reconstruct more discriminative features for a SSD to detect objects in images or videos. A crucial advantage of our method is that it learns a multi-scale metric to distinguish multiple objects at different distances under one image, while DCGAN serves as an encoder-decoder platform to generate parts of an image that contain better discriminative information. To measure the effectiveness of our proposed method, experiments were carried out on the Canadian Institute for Advanced Research (CIFAR) dataset, and it was demonstrated that the proposed new architecture achieved a much better detection rate, particularly on vehicles and pedestrians at distance, making it highly suitable for smart cities applications that need to discover key objects or pedestrians at distance.

arXiv:1903.10842

Improve Diverse Text Generation by Self Labeling Conditional Variational Auto Encoder

Diversity plays a vital role in many text generating applications. In recent years, Conditional Variational Auto Encoders (CVAE) have shown promising performances for this task. However, they often encounter the so called KL-Vanishing problem. Previous works mitigated such problem by heuristic methods such as strengthening the encoder or weakening the decoder while optimizing the CVAE objective function. Nevertheless, the optimizing direction of these methods are implicit and it is hard to find an appropriate degree to which these methods should be applied. In this paper, we propose an explicit optimizing objective to complement the CVAE to directly pull away from KL-vanishing. In fact, this objective term guides the encoder towards the "best encoder" of the decoder to enhance the expressiveness. A labeling network is introduced to estimate the "best encoder". It provides a continuous label in the latent space of CVAE to help build a close connection between latent variables and targets. The whole proposed method is named Self Labeling CVAE~(SLCVAE). To accelerate the research of diverse text generation, we also propose a large native one-to-many dataset. Extensive experiments are conducted on two tasks, which show that our method largely improves the generating diversity while achieving comparable accuracy compared with state-of-art algorithms.

arXiv:1903.10671

Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus

Text style transfer rephrases a text from a source style (e.g., informal) to a target style (e.g., formal) while keeping its original meaning. Despite the success existing works have achieved using a parallel corpus for the two styles, transferring text style has proven significantly more challenging when there is no parallel training corpus. In this paper, we address this challenge by using a reinforcement-learning-based generator-evaluator architecture. Our generator employs an attention-based encoder-decoder to transfer a sentence from the source style to the target style. Our evaluator is an adversarially trained style discriminator with semantic and syntactic constraints that score the generated sentence for style, meaning preservation, and fluency. Experimental results on two different style transfer tasks (sentiment transfer and formality transfer) show that our model outperforms state-of-the-art approaches. Furthermore, we perform a manual evaluation that demonstrates the effectiveness of the proposed method using subjective metrics of generated text quality.

arXiv:1903.10658

Unpaired Image Captioning via Scene Graph Alignments

Most of current image captioning models heavily rely on paired image-caption datasets. However, getting large scale image-caption paired data is labor-intensive and time-consuming. In this paper, we present a scene graph-based approach for unpaired image captioning. Our framework comprises an image scene graph generator, a sentence scene graph generator, a scene graph encoder, and a sentence decoder. Specifically, we first train the scene graph encoder and the sentence decoder on the text modality. To align the scene graphs between images and sentences, we propose an unsupervised feature alignment method that maps the scene graph features from the image to the sentence modality. Experimental results show that our proposed model can generate quite promising results without using any image-caption training pairs, outperforming existing methods by a wide margin.

arXiv:1903.09746

Residual Pyramid Learning for Single-Shot Semantic Segmentation

Pixel-level semantic segmentation is a challenging task with a huge amount of computation, especially if the size of input is large. In the segmentation model, apart from the feature extraction, the extra decoder structure is often employed to recover spatial information. In this paper, we put forward a method for single-shot segmentation in a feature residual pyramid network (RPNet), which learns the main and residuals of segmentation by decomposing the label at different levels of residual blocks. Specifically speaking, we use the residual features to learn the edges and details, and the identity features to learn the main part of targets. At testing time, the predicted residuals are used to enhance the details of the top-level prediction. Residual learning blocks split the network into several shallow sub-networks which facilitates the training of the RPNet. We then evaluate the proposed method and compare it with recent state-of-the-art methods on CamVid and Cityscapes. The proposed single-shot segmentation based on RPNet achieves impressive results with high efficiency on pixel-level segmentation.

arXiv:1903.10304

Learning a Multi-Modal Policy via Imitating Demonstrations with Mixed Behaviors

We propose a novel approach to train a multi-modal policy from mixed demonstrations without their behavior labels. We develop a method to discover the latent factors of variation in the demonstrations. Specifically, our method is based on the variational autoencoder with a categorical latent variable. The encoder infers discrete latent factors corresponding to different behaviors from demonstrations. The decoder, as a policy, performs the behaviors accordingly. Once learned, the policy is able to reproduce a specific behavior by simply conditioning on a categorical vector. We evaluate our method on three different tasks, including a challenging task with high-dimensional visual inputs. Experimental results show that our approach is better than various baseline methods and competitive with a multi-modal policy trained by ground truth behavior labels.

arXiv:1903.10153

DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image

Recovering 3D human body shape and pose from 2D images is a challenging task due to high complexity and flexibility of human body, and relatively less 3D labeled data. Previous methods addressing these issues typically rely on predicting intermediate results such as body part segmentation, 2D/3D joints, silhouette mask to decompose the problem into multiple sub-tasks in order to utilize more 2D labels. Most previous works incorporated parametric body shape model in their methods and predict parameters in low-dimensional space to represent human body. In this paper, we propose to directly regress the 3D human mesh from a single color image using Convolutional Neural Network(CNN). We use an efficient representation of 3D human shape and pose which can be predicted through an encoder-decoder neural network. The proposed method achieves state-of-the-art performance on several 3D human body datasets including Human3.6M, SURREAL and UP-3D with even faster running speed.

arXiv:1903.10145공식 코드 · Papers with Code

Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing

Variational autoencoders (VAEs) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks. The VAE objective consists of two terms, (i) reconstruction and (ii) KL regularization, balanced by a weighting hyper-parameter \beta. One notorious training difficulty is that the KL term tends to vanish. In this paper we study scheduling schemes for \beta, and show that KL vanishing is caused by the lack of good latent codes in training the decoder at the beginning of optimization. To remedy this, we propose a cyclical annealing schedule, which repeats the process of increasing \beta multiple times. This new procedure allows the progressive learning of more meaningful latent codes, by leveraging the informative representations of previous cycles as warm re-starts. The effectiveness of cyclical annealing is validated on a broad range of NLP tasks, including language modeling, dialog response generation and unsupervised language pre-training.

arXiv:1903.10128

Recurrent Back-Projection Network for Video Super-Resolution

We proposed a novel architecture for the problem of video super-resolution. We integrate spatial and temporal contexts from continuous video frames using a recurrent encoder-decoder module, that fuses multi-frame information with the more traditional, single frame super-resolution path for the target frame. In contrast to most prior work where frames are pooled together by stacking or warping, our model, the Recurrent Back-Projection Network (RBPN) treats each context frame as a separate source of information. These sources are combined in an iterative refinement framework inspired by the idea of back-projection in multiple-image super-resolution. This is aided by explicitly representing estimated inter-frame motion with respect to the target, rather than explicitly aligning frames. We propose a new video super-resolution benchmark, allowing evaluation at a larger scale and considering videos in different motion regimes. Experimental results demonstrate that our RBPN is superior to existing methods on several datasets.

arXiv:1903.09887공식 코드 · Papers with Code

DRASIC: Distributed Recurrent Autoencoder for Scalable Image Compression

We propose a new architecture for distributed image compression from a group of distributed data sources. The work is motivated by practical needs of data-driven codec design, low power consumption, robustness, and data privacy. The proposed architecture, which we refer to as Distributed Recurrent Autoencoder for Scalable Image Compression (DRASIC), is able to train distributed encoders and one joint decoder on correlated data sources. Its compression capability is much better than the method of training codecs separately. Meanwhile, the performance of our distributed system with 10 distributed sources is only within 2 dB peak signal-to-noise ratio (PSNR) of the performance of a single codec trained with all data sources. We experiment distributed sources with different correlations and show how our data-driven methodology well matches the Slepian-Wolf Theorem in Distributed Source Coding (DSC). To the best of our knowledge, this is the first data-driven DSC framework for general distributed code design with deep learning.

arXiv:1903.09839

Rotated Feature Network for multi-orientation object detection

General detectors follow the pipeline that feature maps extracted from ConvNets are shared between classification and regression tasks. However, there exists obvious conflicting requirements in multi-orientation object detection that classification is insensitive to orientations, while regression is quite sensitive. To address this issue, we provide an Encoder-Decoder architecture, called Rotated Feature Network (RFN), which produces rotation-sensitive feature maps (RS) for regression and rotation-invariant feature maps (RI) for classification. Specifically, the Encoder unit assigns weights for rotated feature maps. The Decoder unit extracts RS and RI by performing resuming operator on rotated and reweighed feature maps, respectively. To make the rotation-invariant characteristics more reliable, we adopt a metric to quantitatively evaluate the rotation-invariance by adding a constrain item in the loss, yielding a promising detection performance. Compared with the state-of-the-art methods, our method can achieve significant improvement on NWPU VHR-10 and RSOD datasets. We further evaluate the RFN on the scene classification in remote sensing images and object detection in natural images, demonstrating its good generalization ability. The proposed RFN can be integrated into an existing framework, leading to great performance with only a slight increase in model complexity.

arXiv:1903.09272

Fast and accurate reconstruction of HARDI using a 1D encoder-decoder convolutional network

High angular resolution diffusion imaging (HARDI) demands a lager amount of data measurements compared to diffusion tensor imaging, restricting its use in practice. In this work, we explore a learning-based approach to reconstruct HARDI from a smaller number of measurements in q-space. The approach aims to directly learn the mapping relationship between the measured and HARDI signals from the collecting HARDI acquisitions of other subjects. Specifically, the mapping is represented as a 1D encoder-decoder convolutional neural network under the guidance of the compressed sensing (CS) theory for HARDI reconstruction. The proposed network architecture mainly consists of two parts: an encoder network produces the sparse coefficients and a decoder network yields a reconstruction result. Experiment results demonstrate we can robustly reconstruct HARDI signals with the accurate results and fast speed.

arXiv:1903.09263

Deep Learning with Anatomical Priors: Imitating Enhanced Autoencoders in Latent Space for Improved Pelvic Bone Segmentation in MRI

We propose a 2D Encoder-Decoder based deep learning architecture for semantic segmentation, that incorporates anatomical priors by imitating the encoder component of an autoencoder in latent space. The autoencoder is additionally enhanced by means of hierarchical features, extracted by an U-Net module. Our suggested architecture is trained in an end-to-end manner and is evaluated on the example of pelvic bone segmentation in MRI. A comparison to the standard U-Net architecture shows promising improvements.

arXiv:1903.08960

Short-Term Prediction and Multi-Camera Fusion on Semantic Grids

An environment representation (ER) is a substantial part of every autonomous system. It introduces a common interface between perception and other system components, such as decision making, and allows downstream algorithms to deal with abstracted data without knowledge of the used sensor. In this work, we propose and evaluate a novel architecture that generates an egocentric, grid-based, predictive, and semantically-interpretable ER. In particular, we provide a proof of concept for the spatio-temporal fusion of multiple camera sequences and short-term prediction in such an ER. Our design utilizes a strong semantic segmentation network together with depth and egomotion estimates to first extract semantic information from multiple camera streams and then transform these separately into egocentric temporally-aligned bird's-eye view grids. A deep encoder-decoder network is trained to fuse a stack of these grids into a unified semantic grid representation and to predict the dynamics of its surrounding. We evaluate this representation on real-world sequences of the Cityscapes dataset and show that our architecture can make accurate predictions in complex sensor fusion scenarios and significantly outperforms a model-driven baseline in a category-based evaluation.