Fork me on GitHub

Trending arXiv

Note: this version is tailored to @Smerity - though you can run your own! Trending arXiv may eventually be extended to multiple users ...

Papers


1 2 3 4 5 6 7 39 40

Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor

Malvina Nissim, Rik van Noord, Rob van der Goot

Analogies such as man is to king as woman is to X are often used to illustrate the amazing power of word embeddings. Concurrently, they have also exposed how strongly human biases are encoded in vector spaces built on natural language. While finding that queen is the answer to man is to king as woman is to X leaves us in awe, papers have also reported finding analogies deeply infused with human biases, like man is to computer programmer as woman is to homemaker, which instead leave us with worry and rage. In this work we show that,often unknowingly, embedding spaces have not been treated fairly. Through a series of simple experiments, we highlight practical and theoretical problems in previous works, and demonstrate that some of the most widely used biased analogies are in fact not supported by the data. We claim that rather than striving to find sensational biases, we should aim at observing the data "as is", which is biased enough. This should serve as a fair starting point to properly address the evident, serious, and compelling problem of human bias in word embeddings.

Captured tweets and retweets: 2


Multi-Sample Dropout for Accelerated Training and Better Generalization

Hiroshi Inoue

Dropout is a simple but efficient regularization technique for achieving better generalization of deep neural networks (DNNs); hence it is widely used in tasks based on DNNs. During training, dropout randomly discards a portion of the neurons to avoid overfitting. This paper presents an enhanced dropout technique, which we call multi-sample dropout, for both accelerating training and improving generalization over the original dropout. The original dropout creates a randomly selected subset (called a dropout sample) from the input in each training iteration while the multi-sample dropout creates multiple dropout samples. The loss is calculated for each sample, and then the sample losses are averaged to obtain the final loss. This technique can be easily implemented without implementing a new operator by duplicating a part of the network after the dropout layer while sharing the weights among the duplicated fully connected layers. Experimental results showed that multi-sample dropout significantly accelerates training by reducing the number of iterations until convergence for image classification tasks using the ImageNet, CIFAR-10, CIFAR-100, and SVHN datasets. Multi-sample dropout does not significantly increase computation cost per iteration because most of the computation time is consumed in the convolution layers before the dropout layer, which are not duplicated. Experiments also showed that networks trained using multi-sample dropout achieved lower error rates and losses for both the training set and validation set.

Captured tweets and retweets: 2


Learning Discrete and Continuous Factors of Data via Alternating Disentanglement

Yeonwoo Jeong, Hyun Oh Song

We address the problem of unsupervised disentanglement of discrete and continuous explanatory factors of data. We first show a simple procedure for minimizing the total correlation of the continuous latent variables without having to use a discriminator network or perform importance sampling, via cascading the information flow in the $\beta$-vae framework. Furthermore, we propose a method which avoids offloading the entire burden of jointly modeling the continuous and discrete factors to the variational encoder by employing a separate discrete inference procedure. This leads to an interesting alternating minimization problem which switches between finding the most likely discrete configuration given the continuous factors and updating the variational encoder based on the computed discrete factors. Experiments show that the proposed method clearly disentangles discrete factors and significantly outperforms current disentanglement methods based on the disentanglement score and inference network classification score. The source code is available at https://github.com/snu-mllab/DisentanglementICML19.

Captured tweets and retweets: 2


FastSpeech: Fast, Robust and Controllable Text to Speech

Yi Ren, Yangjun Ruan, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, Tie-Yan Liu

Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from text, and then synthesize speech from mel-spectrogram using vocoder such as WaveNet. Compared with traditional concatenative and statistical parametric approaches, neural network based end-to-end models suffer from slow inference speed, and the synthesized speech is usually not robust (i.e., some words are skipped or repeated) and lack of controllability (voice speed or prosody control). In this work, we propose a novel feed-forward network based on Transformer to generate mel-spectrogram in parallel for TTS. Specifically, we extract attention alignments from an encoder-decoder based teacher model for phoneme duration prediction, which is used by a length regulator to expand the source phoneme sequence to match the length of target mel-spectrogram sequence for parallel mel-spectrogram generation. Experiments on the LJSpeech dataset show that our parallel model matches autoregressive models in terms of speech quality, nearly eliminates the problem of word skipping and repeating in particularly hard cases, and can adjust voice speed smoothly. Most importantly, compared with autoregressive Transformer TTS, our model speeds up the mel-spectrogram generation by 270x and the end-to-end speech synthesis by 38x. Therefore, we call our model FastSpeech. We will release the code on Github (anonymous.url). Synthesized speech samples can be found in https://speechresearch.github.io/fastspeech/.

Captured tweets and retweets: 2


PaperRobot: Incremental Draft Generation of Scientific Ideas

Qingyun Wang, Lifu Huang, Zhiying Jiang, Kevin Knight, Heng Ji, Mohit Bansal, Yi Luan

We present a PaperRobot who performs as an automatic research assistant by (1) conducting deep understanding of a large collection of human-written papers in a target domain and constructing comprehensive background knowledge graphs (KGs); (2) creating new ideas by predicting links from the background KGs, by combining graph attention and contextual text attention; (3) incrementally writing some key elements of a new paper based on memory-attention networks: from the input title along with predicted related entities to generate a paper abstract, from the abstract to generate conclusion and future work, and finally from future work to generate a title for a follow-on paper. Turing Tests, where a biomedical domain expert is asked to compare a system output and a human-authored string, show PaperRobot generated abstracts, conclusion and future work sections, and new titles are chosen over human-written ones up to 30%, 24% and 12% of the time, respectively.

Captured tweets and retweets: 1


On Variational Bounds of Mutual Information

Ben Poole, Sherjil Ozair, Aaron van den Oord, Alexander A. Alemi, George Tucker

Estimating and optimizing Mutual Information (MI) is core to many problems in machine learning; however, bounding MI in high dimensions is challenging. To establish tractable and scalable objectives, recent work has turned to variational bounds parameterized by neural networks, but the relationships and tradeoffs between these bounds remains unclear. In this work, we unify these recent developments in a single framework. We find that the existing variational lower bounds degrade when the MI is large, exhibiting either high bias or high variance. To address this problem, we introduce a continuum of lower bounds that encompasses previous bounds and flexibly trades off bias and variance. On high-dimensional, controlled problems, we empirically characterize the bias and variance of the bounds and their gradients and demonstrate the effectiveness of our new bounds for estimation and representation learning.

Captured tweets and retweets: 2


Zero-Shot Voice Style Transfer with Only Autoencoder Loss

Kaizhi Qian, Yang Zhang, Shiyu Chang, Xuesong Yang, Mark Hasegawa-Johnson

Non-parallel many-to-many voice conversion, as well as zero-shot voice conversion, remain under-explored areas. Deep style transfer algorithms, such as generative adversarial networks (GAN) and conditional variational autoencoder (CVAE), are being applied as new solutions in this field. However, GAN training is sophisticated and difficult, and there is no strong evidence that its generated speech is of good perceptual quality. On the other hands, CVAE training is simple but does not come with the distribution-matching property as in GAN. In this paper, we propose a new style transfer scheme that involves only an autoencoder with a carefully designed bottleneck. We formally show that this scheme can achieve distribution-matching style transfer by training only on a self-reconstruction loss. Based on this scheme, we proposed AUTOVC, which achieves state-of-the-art results in many-to-many voice conversion with non-parallel data, and which is the first to perform zero-shot voice conversion.

Captured tweets and retweets: 2


Fast and Efficient Zero-Learning Image Fusion

Fayez Lahoud, Sabine Süsstrunk

We propose a real-time image fusion method using pre-trained neural networks. Our method generates a single image containing features from multiple sources. We first decompose images into a base layer representing large scale intensity variations, and a detail layer containing small scale changes. We use visual saliency to fuse the base layers, and deep feature maps extracted from a pre-trained neural network to fuse the detail layers. We conduct ablation studies to analyze our method's parameters such as decomposition filters, weight construction methods, and network depth and architecture. Then, we validate its effectiveness and speed on thermal, medical, and multi-focus fusion. We also apply it to multiple image inputs such as multi-exposure sequences. The experimental results demonstrate that our technique achieves state-of-the-art performance in visual quality, objective assessment, and runtime efficiency.

Captured tweets and retweets: 2


PPGNet: Learning Point-Pair Graph for Line Segment Detection

Ziheng Zhang, Zhengxin Li, Ning Bi, Jia Zheng, Jinlei Wang, Kun Huang, Weixin Luo, Yanyu Xu, Shenghua Gao

In this paper, we present a novel framework to detect line segments in man-made environments. Specifically, we propose to describe junctions, line segments and relationships between them with a simple graph, which is more structured and informative than end-point representation used in existing line segment detection methods. In order to extract a line segment graph from an image, we further introduce the PPGNet, a convolutional neural network that directly infers a graph from an image. We evaluate our method on published benchmarks including York Urban and Wireframe datasets. The results demonstrate that our method achieves satisfactory performance and generalizes well on all the benchmarks. The source code of our work is available at \url{https://github.com/svip-lab/PPGNet}.

Captured tweets and retweets: 2


Universal Sound Separation

Ilya Kavalerov, Scott Wisdom, Hakan Erdogan, Brian Patton, Kevin Wilson, Jonathan Le Roux, John R. Hershey

Recent deep learning approaches have achieved impressive performance on speech enhancement and separation tasks. However, these approaches have not been investigated for separating mixtures of arbitrary sounds of different types, a task we refer to as universal sound separation, and it is unknown whether performance on speech tasks carries over to non-speech tasks. To study this question, we develop a universal dataset of mixtures containing arbitrary sounds, and use it to investigate the space of mask-based separation architectures, varying both the overall network architecture and the framewise analysis-synthesis basis for signal transformations. These network architectures include convolutional long short-term memory networks and time-dilated convolution stacks inspired by the recent success of time-domain enhancement networks like ConvTasNet. For the latter architecture, we also propose novel modifications that further improve separation performance. In terms of the framewise analysis-synthesis basis, we explore using either a short-time Fourier transform (STFT) or a learnable basis, as used in ConvTasNet, and for both of these bases, we examine the effect of window size. In particular, for STFTs, we find that longer windows (25-50 ms) work best for speech/non-speech separation, while shorter windows (2.5 ms) work best for arbitrary sounds. For learnable bases, shorter windows (2.5 ms) work best on all tasks. Surprisingly, for universal sound separation, STFTs outperform learnable bases. Our best methods produce an improvement in scale-invariant signal-to-distortion ratio of over 13 dB for speech/non-speech separation and close to 10 dB for universal sound separation.

Captured tweets and retweets: 2


MixMatch: A Holistic Approach to Semi-Supervised Learning

David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, Colin Raffel

Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets. In this work, we unify the current dominant approaches for semi-supervised learning to produce a new algorithm, MixMatch, that works by guessing low-entropy labels for data-augmented unlabeled examples and mixing labeled and unlabeled data using MixUp. We show that MixMatch obtains state-of-the-art results by a large margin across many datasets and labeled data amounts. For example, on CIFAR-10 with 250 labels, we reduce error rate by a factor of 4 (from 38% to 11%) and by a factor of 2 on STL-10. We also demonstrate how MixMatch can help achieve a dramatically better accuracy-privacy trade-off for differential privacy. Finally, we perform an ablation study to tease apart which components of MixMatch are most important for its success.

Captured tweets and retweets: 2


SinGAN: Learning a Generative Model from a Single Natural Image

Tamar Rott Shaham, Tali Dekel, Tomer Michaeli

We introduce SinGAN, an unconditional generative model that can be learned from a single natural image. Our model is trained to capture the internal distribution of patches within the image, and is then able to generate high quality, diverse samples that carry the same visual content as the image. SinGAN contains a pyramid of fully convolutional GANs, each responsible for learning the patch distribution at a different scale of the image. This allows generating new samples of arbitrary size and aspect ratio, that have significant variability, yet maintain both the global structure and the fine textures of the training image. In contrast to previous single image GAN schemes, our approach is not limited to texture images, and is not conditional (i.e. it generates samples from noise). User studies confirm that the generated samples are commonly confused to be real images. We illustrate the utility of SinGAN in a wide range of image manipulation tasks.

Captured tweets and retweets: 2


High quality, lightweight and adaptable TTS using LPCNet

Zvi Kons, Slava Shechtman, Alex Sorin, Carmel Rabinovitz, Ron Hoory

We present a lightweight adaptable neural TTS system with high quality output. The system is composed of three separate neural network blocks: prosody prediction, acoustic feature prediction and Linear Prediction Coding Net as a neural vocoder. This system can synthesize speech with close to natural quality while running 3 times faster than real-time on a standard CPU. The modular setup of the system allows for simple adaptation to new voices with a small amount of data. We first demonstrate the ability of the system to produce high quality speech when trained on large, high quality datasets. Following that, we demonstrate its adaptability by mimicking unseen voices using 5 to 20 minutes long datasets with lower recording quality. Large scale Mean Opinion Score quality and similarity tests are presented, showing that the system can adapt to unseen voices with quality gap of 0.12 and similarity gap of 3% compared to natural speech for male voices and quality gap of 0.35 and similarity of gap of 9 % for female voices.

Captured tweets and retweets: 2


Style Transfer by Relaxed Optimal Transport and Self-Similarity

Nicholas Kolkin, Jason Salavon, Greg Shakhnarovich

Style transfer algorithms strive to render the content of one image using the style of another. We propose Style Transfer by Relaxed Optimal Transport and Self-Similarity (STROTSS), a new optimization-based style transfer algorithm. We extend our method to allow user-specified point-to-point or region-to-region control over visual similarity between the style image and the output. Such guidance can be used to either achieve a particular visual effect or correct errors made by unconstrained style transfer. In order to quantitatively compare our method to prior work, we conduct a large-scale user study designed to assess the style-content tradeoff across settings in style transfer algorithms. Our results indicate that for any desired level of content preservation, our method provides higher quality stylization than prior work. Code is available at https://github.com/nkolkin13/STROTSS

Captured tweets and retweets: 2


Neural source-filter waveform models for statistical parametric speech synthesis

Xin Wang, Shinji Takaki, Junichi Yamagishi

Neural waveform models such as WaveNet have demonstrated better performance than conventional vocoders for statistical parametric speech synthesis. As an autoregressive (AR) model, WaveNet is limited by a slow sequential waveform generation process. Some new models that use the inverse-autoregressive flow (IAF) can generate a whole waveform in a one-shot manner. However, these IAF-based models require sequential transformation during training, which severely slows down the training speed. Other models such as Parallel WaveNet and ClariNet bring together the benefits of AR and IAF-based models and train an IAF model by transferring the knowledge from a pre-trained AR teacher to an IAF student without any sequential transformation. However, both models require additional training criteria, and their implementation is prohibitively complicated. We propose a framework for neural source-filter (NSF) waveform modeling without AR nor IAF-based approaches. This framework requires only three components for waveform generation: a source module that generates a sine-based signal as excitation, a non-AR dilated-convolution-based filter module that transforms the excitation into a waveform, and a conditional module that pre-processes the acoustic features for the source and filer modules. This framework minimizes spectral-amplitude distances for model training, which can be efficiently implemented by using short-time Fourier transform routines. Under this framework, we designed three NSF models and compared them with WaveNet. It was demonstrated that the NSF models generated waveforms at least 100 times faster than WaveNet, and the quality of the synthetic speech from the best NSF model was better than or equally good as that from WaveNet.

Captured tweets and retweets: 4


A Distributed Method for Fitting Laplacian Regularized Stratified Models

Jonathan Tuck, Shane Barratt, Stephen Boyd

Stratified models are models that depend in an arbitrary way on a set of selected categorical features, and depend linearly on the other features. In a basic and traditional formulation a separate model is fit for each value of the categorical feature, using only the data that has the specific categorical value. To this formulation we add Laplacian regularization, which encourages the model parameters for neighboring categorical values to be similar. Laplacian regularization allows us to specify one or more weighted graphs on the stratification feature values. For example, stratifying over the days of the week, we can specify that the Sunday model parameter should be close to the Saturday and Monday model parameters. The regularization improves the performance of the model over the traditional stratified model, since the model for each value of the categorical `borrows strength' from its neighbors. In particular, it produces a model even for categorical values that did not appear in the training data set. We propose an efficient distributed method for fitting stratified models, based on the alternating direction method of multipliers (ADMM). When the fitting loss functions are convex, the stratified model fitting problem is convex, and our method computes the global minimizer of the loss plus regularization; in other cases it computes a local minimizer. The method is very efficient, and naturally scales to large data sets or numbers of stratified feature values. We illustrate our method with a variety of examples.

Captured tweets and retweets: 2


Adaptive Transform Domain Image Super-resolution Via Orthogonally Regularized Deep Networks

Tiantong Guo, Hojjat S. Mousavi, Vishal Monga

Deep learning methods, in particular, trained Convolutional Neural Networks (CNN) have recently been shown to produce compelling results for single image Super-Resolution (SR). Invariably, a CNN is learned to map the Low Resolution (LR) image to its corresponding High Resolution (HR) version in the spatial domain. We propose a novel network structure for learning the SR mapping function in an image transform domain, specifically the Discrete Cosine Transform (DCT). As the first contribution, we show that DCT can be integrated into the network structure as a Convolutional DCT (CDCT) layer. With the CDCT layer, we construct the DCT Deep SR (DCT-DSR) network. We further extend the DCT-DSR to allow the CDCT layer to become trainable (i.e., optimizable). Because this layer represents an image transform, we enforce pairwise orthogonality constraints and newly formulated complexity order constraints on the individual basis functions/filters. This Orthogonally Regularized Deep SR network (ORDSR) simplifies the SR task by taking advantage of image transform domain while adapting the design of transform basis to the training image set. Experimental results show ORDSR achieves state-of-the-art SR image quality with fewer parameters than most of the deep CNN methods. A particular success of ORDSR is in overcoming the artifacts introduced by bicubic interpolation. A key burden of deep SR has been identified as the requirement of generous training LR and HR image pairs; ORSDR exhibits a much more graceful degradation as training size is reduced with significant benefits in the regime of limited training. Analysis of memory and computation requirements confirms that ORDSR can allow for a more efficient network with faster inference.

Captured tweets and retweets: 2


Mining Rules Incrementally over Large Knowledge Bases

Xiaofeng Zhou, Ali Sadeghian, Daisy Zhe Wang

Multiple web-scale Knowledge Bases, e.g., Freebase, YAGO, NELL, have been constructed using semi-supervised or unsupervised information extraction techniques and many of them, despite their large sizes, are continuously growing. Much research effort has been put into mining inference rules from knowledge bases. To address the task of rule mining over evolving web-scale knowledge bases, we propose a parallel incremental rule mining framework. Our approach is able to efficiently mine rules based on the relational model and apply updates to large knowledge bases; we propose an alternative metric that reduces computation complexity without compromising quality; we apply multiple optimization techniques that reduce runtime by more than 2 orders of magnitude. Experiments show that our approach efficiently scales to web-scale knowledge bases and saves over 90% time compared to the state-of-the-art batch rule mining system. We also apply our optimization techniques to the batch rule mining algorithm, reducing runtime by more than half compared to the state-of-the-art. To the best of our knowledge, our incremental rule mining system is the first that handles updates to web-scale knowledge bases.

Captured tweets and retweets: 2


A Novel BiLevel Paradigm for Image-to-Image Translation

Liqian Ma, Qianru Sun, Bernt Schiele, Luc Van Gool

Image-to-image (I2I) translation is a pixel-level mapping that requires a large number of paired training data and often suffers from the problems of high diversity and strong category bias in image scenes. In order to tackle these problems, we propose a novel BiLevel (BiL) learning paradigm that alternates the learning of two models, respectively at an instance-specific (IS) and a general-purpose (GP) level. In each scene, the IS model learns to maintain the specific scene attributes. It is initialized by the GP model that learns from all the scenes to obtain the generalizable translation knowledge. This GP initialization gives the IS model an efficient starting point, thus enabling its fast adaptation to the new scene with scarce training data. We conduct extensive I2I translation experiments on human face and street view datasets. Quantitative results validate that our approach can significantly boost the performance of classical I2I translation models, such as PG2 and Pix2Pix. Our visualization results show both higher image quality and more appropriate instance-specific details, e.g., the translated image of a person looks more like that person in terms of identity.

Captured tweets and retweets: 2


Effective Estimation of Deep Generative Language Models

Tom Pelsmaeker, Wilker Aziz

Advances in variational inference enable parameterisation of probabilistic models by deep neural networks. This combines the statistical transparency of the probabilistic modelling framework with the representational power of deep learning. Yet, it seems difficult to effectively estimate such models in the context of language modelling. Even models based on rather simple generative stories struggle to make use of additional structure due to a problem known as posterior collapse. We concentrate on one such model, namely, a variational auto-encoder, which we argue is an important building block in hierarchical probabilistic models of language. This paper contributes a sober view of the problem, a survey of techniques to address it, novel techniques, and extensions to the model. Our experiments on modelling written English text support a number of recommendations that should help researchers interested in this exciting field.

Captured tweets and retweets: 2


1 2 3 4 5 6 7 39 40