PyTorchKR Papers

최신 논문

총 9,642편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1709.06508

Face Retrieval using Frequency Decoded Local Descriptor

The local descriptors have been the backbone of most of the computer vision problems. Most of the existing local descriptors are generated over the raw input images. In order to increase the discriminative power of the local descriptors, some researchers converted the raw image into multiple images with the help of some high and low pass frequency filters, then the local descriptors are computed over each filtered image and finally concatenated into a single descriptor. By doing so, these approaches do not utilize the inter frequency relationship which causes the less improvement in the discriminative power of the descriptor that could be achieved. In this paper, this problem is solved by utilizing the decoder concept of multi-channel decoded local binary pattern over the multi-frequency patterns. A frequency decoded local binary pattern (FDLBP) is proposed with two decoders. Each decoder works with one low frequency pattern and two high frequency patterns. Finally, the descriptors from both decoders are concatenated to form the single descriptor. The face retrieval experiments are conducted over four benchmarks and challenging databases such as PaSC, LFW, PubFig, and ESSEX. The experimental results confirm the superiority of the FDLBP descriptor as compared to the state-of-the-art descriptors such as LBP, SOBEL_LBP, BoF_LBP, SVD_S_LBP, mdLBP, etc.

arXiv:1709.05538

DeepLung: 3D Deep Convolutional Nets for Automated Pulmonary Nodule Detection and Classification

In this work, we present a fully automated lung CT cancer diagnosis system, DeepLung. DeepLung contains two parts, nodule detection and classification. Considering the 3D nature of lung CT data, two 3D networks are designed for the nodule detection and classification respectively. Specifically, a 3D Faster R-CNN is designed for nodule detection with a U-net-like encoder-decoder structure to effectively learn nodule features. For nodule classification, gradient boosting machine (GBM) with 3D dual path network (DPN) features is proposed. The nodule classification subnetwork is validated on a public dataset from LIDC-IDRI, on which it achieves better performance than state-of-the-art approaches, and surpasses the average performance of four experienced doctors. For the DeepLung system, candidate nodules are detected first by the nodule detection subnetwork, and nodule diagnosis is conducted by the classification subnetwork. Extensive experimental results demonstrate the DeepLung is comparable to the experienced doctors both for the nodule-level and patient-level diagnosis on the LIDC-IDRI dataset.

arXiv:1709.05074

A Deep Generative Framework for Paraphrase Generation

Paraphrase generation is an important problem in NLP, especially in question answering, information retrieval, information extraction, conversation systems, to name a few. In this paper, we address the problem of generating paraphrases automatically. Our proposed method is based on a combination of deep generative models (VAE) with sequence-to-sequence models (LSTM) to generate paraphrases, given an input sentence. Traditional VAEs when combined with recurrent neural networks can generate free text but they are not suitable for paraphrase generation for a given sentence. We address this problem by conditioning the both, encoder and decoder sides of VAE, on the original sentence, so that it can generate the given sentence's paraphrases. Unlike most existing models, our model is simple, modular and can generate multiple paraphrases, for a given sentence. Quantitative evaluation of the proposed method on a benchmark paraphrase dataset demonstrates its efficacy, and its performance improvement over the state-of-the-art methods by a significant margin, whereas qualitative human evaluation indicate that the generated paraphrases are well-formed, grammatically correct, and are relevant to the input sentence. Furthermore, we evaluate our method on a newly released question paraphrase dataset, and establish a new baseline for future research.

arXiv:1709.05047

Disentangled Variational Auto-Encoder for Semi-supervised Learning

Semi-supervised learning is attracting increasing attention due to the fact that datasets of many domains lack enough labeled data. Variational Auto-Encoder (VAE), in particular, has demonstrated the benefits of semi-supervised learning. The majority of existing semi-supervised VAEs utilize a classifier to exploit label information, where the parameters of the classifier are introduced to the VAE. Given the limited labeled data, learning the parameters for the classifiers may not be an optimal solution for exploiting label information. Therefore, in this paper, we develop a novel approach for semi-supervised VAE without classifier. Specifically, we propose a new model called Semi-supervised Disentangled VAE (SDVAE), which encodes the input data into disentangled representation and non-interpretable representation, then the category information is directly utilized to regularize the disentangled representation via the equality constraint. To further enhance the feature learning ability of the proposed VAE, we incorporate reinforcement learning to relieve the lack of data. The dynamic framework is capable of dealing with both image and text data with its corresponding encoder and decoder networks. Extensive experiments on image and text datasets demonstrate the effectiveness of the proposed framework.

arXiv:1709.06429

Neural Networks for Text Correction and Completion in Keyboard Decoding

Despite the ubiquity of mobile and wearable text messaging applications, the problem of keyboard text decoding is not tackled sufficiently in the light of the enormous success of the deep learning Recurrent Neural Network (RNN) and Convolutional Neural Networks (CNN) for natural language understanding. In particular, considering that the keyboard decoders should operate on devices with memory and processor resource constraints, makes it challenging to deploy industrial scale deep neural network (DNN) models. This paper proposes a sequence-to-sequence neural attention network system for automatic text correction and completion. Given an erroneous sequence, our model encodes character level hidden representations and then decodes the revised sequence thus enabling auto-correction and completion. We achieve this by a combination of character level CNN and gated recurrent unit (GRU) encoder along with and a word level gated recurrent unit (GRU) attention decoder. Unlike traditional language models that learn from billions of words, our corpus size is only 12 million words; an order of magnitude smaller. The memory footprint of our learnt model for inference and prediction is also an order of magnitude smaller than the conventional language model based text decoders. We report baseline performance for neural keyboard decoders in such limited domain. Our models achieve a word level accuracy of $90\%$ and a character error rate CER of $2.4\%$ over the Twitter typo dataset. We present a novel dataset of noisy to corrected mappings by inducing the noise distribution from the Twitter data over the OpenSubtitles 2009 dataset; on which our model predicts with a word level accuracy of $98\%$ and sequence accuracy of $68.9\%$. In our user study, our model achieved an average CER of $2.6\%$ with the state-of-the-art non-neural touch-screen keyboard decoder at CER of $1.6\%$.

arXiv:1709.05631

Unwritten Languages Demand Attention Too! Word Discovery with Encoder-Decoder Models

Word discovery is the task of extracting words from unsegmented text. In this paper we examine to what extent neural networks can be applied to this task in a realistic unwritten language scenario, where only small corpora and limited annotations are available. We investigate two scenarios: one with no supervision and another with limited supervision with access to the most frequent words. Obtained results show that it is possible to retrieve at least 27% of the gold standard vocabulary by training an encoder-decoder neural machine translation system with only 5,157 sentences. This result is close to those obtained with a task-specific Bayesian nonparametric model. Moreover, our approach has the advantage of generating translation alignments, which could be used to create a bilingual lexicon. As a future perspective, this approach is also well suited to work directly from speech.

arXiv:1703.10553

Learning Convolutional Networks for Content-weighted Image Compression

Lossy image compression is generally formulated as a joint rate-distortion optimization to learn encoder, quantizer, and decoder. However, the quantizer is non-differentiable, and discrete entropy estimation usually is required for rate control. These make it very challenging to develop a convolutional network (CNN)-based image compression system. In this paper, motivated by that the local information content is spatially variant in an image, we suggest that the bit rate of the different parts of the image should be adapted to local content. And the content aware bit rate is allocated under the guidance of a content-weighted importance map. Thus, the sum of the importance map can serve as a continuous alternative of discrete entropy estimation to control compression rate. And binarizer is adopted to quantize the output of encoder due to the binarization scheme is also directly defined by the importance map. Furthermore, a proxy function is introduced for binary operation in backward propagation to make it differentiable. Therefore, the encoder, decoder, binarizer and importance map can be jointly optimized in an end-to-end manner by using a subset of the ImageNet database. In low bit rate image compression, experiments show that our system significantly outperforms JPEG and JPEG 2000 by structural similarity (SSIM) index, and can produce the much better visual result with sharp edges, rich textures, and fewer artifacts.

arXiv:1709.07814

Attention-based Wav2Text with Feature Transfer Learning

Conventional automatic speech recognition (ASR) typically performs multi-level pattern recognition tasks that map the acoustic speech waveform into a hierarchy of speech units. But, it is widely known that information loss in the earlier stage can propagate through the later stages. After the resurgence of deep learning, interest has emerged in the possibility of developing a purely end-to-end ASR system from the raw waveform to the transcription without any predefined alignments and hand-engineered models. However, the successful attempts in end-to-end architecture still used spectral-based features, while the successful attempts in using raw waveform were still based on the hybrid deep neural network - Hidden Markov model (DNN-HMM) framework. In this paper, we construct the first end-to-end attention-based encoder-decoder model to process directly from raw speech waveform to the text transcription. We called the model as "Attention-based Wav2Text". To assist the training process of the end-to-end model, we propose to utilize a feature transfer learning. Experimental results also reveal that the proposed Attention-based Wav2Text model directly with raw waveform could achieve a better result in comparison with the attentional encoder-decoder model trained on standard front-end filterbank features.

arXiv:1709.07599

High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference

We propose a data-driven method for recovering miss-ing parts of 3D shapes. Our method is based on a new deep learning architecture consisting of two sub-networks: a global structure inference network and a local geometry refinement network. The global structure inference network incorporates a long short-term memorized context fusion module (LSTM-CF) that infers the global structure of the shape based on multi-view depth information provided as part of the input. It also includes a 3D fully convolutional (3DFCN) module that further enriches the global structure representation according to volumetric information in the input. Under the guidance of the global structure network, the local geometry refinement network takes as input lo-cal 3D patches around missing regions, and progressively produces a high-resolution, complete surface through a volumetric encoder-decoder architecture. Our method jointly trains the global structure inference and local geometry refinement networks in an end-to-end manner. We perform qualitative and quantitative evaluations on six object categories, demonstrating that our method outperforms existing state-of-the-art work on shape completion.

arXiv:1709.08553

Attribute Recognition by Joint Recurrent Learning of Context and Correlation

Recognising semantic pedestrian attributes in surveillance images is a challenging task for computer vision, particularly when the imaging quality is poor with complex background clutter and uncontrolled viewing conditions, and the number of labelled training data is small. In this work, we formulate a Joint Recurrent Learning (JRL) model for exploring attribute context and correlation in order to improve attribute recognition given small sized training data with poor quality images. The JRL model learns jointly pedestrian attribute correlations in a pedestrian image and in particular their sequential ordering dependencies (latent high-order correlation) in an end-to-end encoder/decoder recurrent network. We demonstrate the performance advantage and robustness of the JRL model over a wide range of state-of-the-art deep models for pedestrian attribute recognition, multi-label image classification, and multi-person image annotation on two largest pedestrian attribute benchmarks PETA and RAP.

arXiv:1709.09578공식 코드 · Papers with Code

Neural networks for topology optimization

In this research, we propose a deep learning based approach for speeding up the topology optimization methods. The problem we seek to solve is the layout problem. The main novelty of this work is to state the problem as an image segmentation task. We leverage the power of deep learning methods as the efficient pixel-wise image labeling technique to perform the topology optimization. We introduce convolutional encoder-decoder architecture and the overall approach of solving the above-described problem with high performance. The conducted experiments demonstrate the significant acceleration of the optimization process. The proposed approach has excellent generalization properties. We demonstrate the ability of the application of the proposed model to other problems. The successful results, as well as the drawbacks of the current method, are discussed.

arXiv:1707.06375

3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks

We propose a method for reconstructing 3D shapes from 2D sketches in the form of line drawings. Our method takes as input a single sketch, or multiple sketches, and outputs a dense point cloud representing a 3D reconstruction of the input sketch(es). The point cloud is then converted into a polygon mesh. At the heart of our method lies a deep, encoder-decoder network. The encoder converts the sketch into a compact representation encoding shape information. The decoder converts this representation into depth and normal maps capturing the underlying surface from several output viewpoints. The multi-view maps are then consolidated into a 3D point cloud by solving an optimization problem that fuses depth and normals across all viewpoints. Based on our experiments, compared to other methods, such as volumetric networks, our architecture offers several advantages, including more faithful reconstruction, higher output surface resolution, better preservation of topology and shape structure.

arXiv:1710.00489

SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control

In this work, we present an approach to deep visuomotor control using structured deep dynamics models. Our deep dynamics model, a variant of SE3-Nets, learns a low-dimensional pose embedding for visuomotor control via an encoder-decoder structure. Unlike prior work, our dynamics model is structured: given an input scene, our network explicitly learns to segment salient parts and predict their pose-embedding along with their motion modeled as a change in the pose space due to the applied actions. We train our model using a pair of point clouds separated by an action and show that given supervision only in the form of point-wise data associations between the frames our network is able to learn a meaningful segmentation of the scene along with consistent poses. We further show that our model can be used for closed-loop control directly in the learned low-dimensional pose space, where the actions are computed by minimizing error in the pose space using gradient-based methods, similar to traditional model-based control. We present results on controlling a Baxter robot from raw depth data in simulation and in the real world and compare against two baseline deep networks. Our method runs in real-time, achieves good prediction of scene dynamics and outperforms the baseline methods on multiple control runs. Video results can be found at: https://rse-lab.cs.washington.edu/se3-structured-deep-ctrl/

arXiv:1710.00290

Translating Videos to Commands for Robotic Manipulation with Deep Recurrent Neural Networks

We present a new method to translate videos to commands for robotic manipulation using Deep Recurrent Neural Networks (RNN). Our framework first extracts deep features from the input video frames with a deep Convolutional Neural Networks (CNN). Two RNN layers with an encoder-decoder architecture are then used to encode the visual features and sequentially generate the output words as the command. We demonstrate that the translation accuracy can be improved by allowing a smooth transaction between two RNN layers and using the state-of-the-art feature extractor. The experimental results on our new challenging dataset show that our approach outperforms recent methods by a fair margin. Furthermore, we combine the proposed translation module with the vision and planning system to let a robot perform various manipulation tasks. Finally, we demonstrate the effectiveness of our framework on a full-size humanoid robot WALK-MAN.

arXiv:1710.00126

3DOF Pedestrian Trajectory Prediction Learned from Long-Term Autonomous Mobile Robot Deployment Data

This paper presents a novel 3DOF pedestrian trajectory prediction approach for autonomous mobile service robots. While most previously reported methods are based on learning of 2D positions in monocular camera images, our approach uses range-finder sensors to learn and predict 3DOF pose trajectories (i.e. 2D position plus 1D rotation within the world coordinate system). Our approach, T-Pose-LSTM (Temporal 3DOF-Pose Long-Short-Term Memory), is trained using long-term data from real-world robot deployments and aims to learn context-dependent (environment- and time-specific) human activities. Our approach incorporates long-term temporal information (i.e. date and time) with short-term pose observations as input. A sequence-to-sequence LSTM encoder-decoder is trained, which encodes observations into LSTM and then decodes as predictions. For deployment, it can perform on-the-fly prediction in real-time. Instead of using manually annotated data, we rely on a robust human detection, tracking and SLAM system, providing us with examples in a global coordinate system. We validate the approach using more than 15K pedestrian trajectories recorded in a care home environment over a period of three months. The experiment shows that the proposed T-Pose-LSTM model advances the state-of-the-art 2D-based method for human trajectory prediction in long-term mobile robot deployments.

arXiv:1710.02318공식 코드 · Papers with Code

A Semantic Relevance Based Neural Network for Text Summarization and Text Simplification

Text summarization and text simplification are two major ways to simplify the text for poor readers, including children, non-native speakers, and the functionally illiterate. Text summarization is to produce a brief summary of the main ideas of the text, while text simplification aims to reduce the linguistic complexity of the text and retain the original meaning. Recently, most approaches for text summarization and text simplification are based on the sequence-to-sequence model, which achieves much success in many text generation tasks. However, although the generated simplified texts are similar to source texts literally, they have low semantic relevance. In this work, our goal is to improve semantic relevance between source texts and simplified texts for text summarization and text simplification. We introduce a Semantic Relevance Based neural model to encourage high semantic similarity between texts and summaries. In our model, the source text is represented by a gated attention encoder, while the summary representation is produced by a decoder. Besides, the similarity score between the representations is maximized during training. Our experiments show that the proposed model outperforms the state-of-the-art systems on two benchmark corpus.

arXiv:1710.02280

Generating Nontrivial Melodies for Music as a Service

We present a hybrid neural network and rule-based system that generates pop music. Music produced by pure rule-based systems often sounds mechanical. Music produced by machine learning sounds better, but still lacks hierarchical temporal structure. We restore temporal hierarchy by augmenting machine learning with a temporal production grammar, which generates the music's overall structure and chord progressions. A compatible melody is then generated by a conditional variational recurrent autoencoder. The autoencoder is trained with eight-measure segments from a corpus of 10,000 MIDI files, each of which has had its melody track and chord progressions identified heuristically. The autoencoder maps melody into a multi-dimensional feature space, conditioned by the underlying chord progression. A melody is then generated by feeding a random sample from that space to the autoencoder's decoder, along with the chord progression generated by the grammar. The autoencoder can make musically plausible variations on an existing melody, suitable for recurring motifs. It can also reharmonize a melody to a new chord progression, keeping the rhythm and contour. The generated music compares favorably with that generated by other academic and commercial software designed for the music-as-a-service industry.

arXiv:1710.03255

Multitask training with unlabeled data for end-to-end sign language fingerspelling recognition

We address the problem of automatic American Sign Language fingerspelling recognition from video. Prior work has largely relied on frame-level labels, hand-crafted features, or other constraints, and has been hampered by the scarcity of data for this task. We introduce a model for fingerspelling recognition that addresses these issues. The model consists of an auto-encoder-based feature extractor and an attention-based neural encoder-decoder, which are trained jointly. The model receives a sequence of image frames and outputs the fingerspelled word, without relying on any frame-level training labels or hand-crafted features. In addition, the auto-encoder subcomponent makes it possible to leverage unlabeled data to improve the feature learning. The model achieves 11.6% and 4.4% absolute letter accuracy improvement respectively in signer-independent and signer-adapted fingerspelling recognition over previous approaches that required frame-level training labels.

arXiv:1709.02554공식 코드 · Papers with Code

Learning to Segment Breast Biopsy Whole Slide Images

We trained and applied an encoder-decoder model to semantically segment breast biopsy images into biologically meaningful tissue labels. Since conventional encoder-decoder networks cannot be applied directly on large biopsy images and the different sized structures in biopsies present novel challenges, we propose four modifications: (1) an input-aware encoding block to compensate for information loss, (2) a new dense connection pattern between encoder and decoder, (3) dense and sparse decoders to combine multi-level features, (4) a multi-resolution network that fuses the results of encoder-decoders run on different resolutions. Our model outperforms a feature-based approach and conventional encoder-decoders from the literature. We use semantic segmentations produced with our model in an automated diagnosis task and obtain higher accuracies than a baseline approach that employs an SVM for feature-based segmentation, both using the same segmentation-based diagnostic features.

arXiv:1708.08487

On denoising autoencoders trained to minimise binary cross-entropy

Denoising autoencoders (DAEs) are powerful deep learning models used for feature extraction, data generation and network pre-training. DAEs consist of an encoder and decoder which may be trained simultaneously to minimise a loss (function) between an input and the reconstruction of a corrupted version of the input. There are two common loss functions used for training autoencoders, these include the mean-squared error (MSE) and the binary cross-entropy (BCE). When training autoencoders on image data a natural choice of loss function is BCE, since pixel values may be normalised to take values in [0,1] and the decoder model may be designed to generate samples that take values in (0,1). We show theoretically that DAEs trained to minimise BCE may be used to take gradient steps in the data space towards regions of high probability under the data-generating distribution. Previously this had only been shown for DAEs trained using MSE. As a consequence of the theory, iterative application of a trained DAE moves a data sample from regions of low probability to regions of higher probability under the data-generating distribution. Firstly, we validate the theory by showing that novel data samples, consistent with the training data, may be synthesised when the initial data samples are random noise. Secondly, we motivate the theory by showing that initial data samples synthesised via other methods may be improved via iterative application of a trained DAE to those initial samples.