Representation learning is an essential process in the text similarity task. The methods based on neural variational inference first learn the semantic representation of the texts, and then measure the similar degree ...
详细信息
ISBN:
(数字)9783030042219
ISBN:
(纸本)9783030042219;9783030042202
Representation learning is an essential process in the text similarity task. The methods based on neural variational inference first learn the semantic representation of the texts, and then measure the similar degree of these texts by calculating the cosine of their representations. However, it is not generally desirable that using the neural network simply to learn semantic representation as it cannot capture the rich semantic information completely. Considering that the similarity of context information reflects the similarity of text pairs in most cases, we integrate the topic information into a stacked variational autoencoder in process of text representation learning. The improved text representations are used in text similarity calculation. Experiment shows that our approach obtains the state-of-art performance.
Many improvements have been made in the field of generative modelling. State-of-the-art unsupervised models have been able to transfer the style of existing media with photo-realistic quality. However, these improveme...
详细信息
ISBN:
(数字)9783030319786
ISBN:
(纸本)9783030319786;9783030319779
Many improvements have been made in the field of generative modelling. State-of-the-art unsupervised models have been able to transfer the style of existing media with photo-realistic quality. However, these improvements have been largely limited to graphical data. Music has been proven to be more difficult to model. Magenta's MusicVAE can quite successfully generate abstract rhythms and melodies. However, MusicVAE is a large model that requires vast amounts of computing power before it starts to make realistic predictions. Moreover, its input is heavily quantized which makes it impossible to model musical variations such as swing. This paper proposes a lightweight but high-resolution variational recurrent autoencoder that can be used to transfer the style of input samples while maintaining characteristics of the original sample. This model can be trained in a few hours on small datasets and allows researchers and musicians to experiment with musical style transfer. In addition, a novel technique based on normalized compression distance is used to evaluate the model by measuring the similarity of generated samples to target classes.
Although the main structures of cortical folding are present in each human brain, the folding pattern is unique to each individual. Because of this large normal variability, the identification of abnormal patterns ass...
详细信息
ISBN:
(纸本)9783030875862;9783030875855
Although the main structures of cortical folding are present in each human brain, the folding pattern is unique to each individual. Because of this large normal variability, the identification of abnormal patterns associated to developmental disorders is a complex open challenge. In this paper, we tackle this problem as an anomaly detection task and explore the potential of deep generative models using benchmarks made up of synthetic anomalies. To focus learning on the folding geometry, brain MRI are preprocessed first to deal only with a skeleton-based negative cast of the cortex. A variational auto-encoder is trained to get a representation of the regional variability of the folding pattern of the general population. Then several synthetic benchmark datasets of abnormalities are designed. The latent space expressivity is assessed through classification experiments between control's and abnormal's latent codes. Finally, the properties encoded in the latent space are analyzed through perturbation of specific latent dimensions and observation of the resulting modification of the reconstructed images. The results have shown that the latent representation is rich enough to distinguish subtle differences like asymmetries between the right and left hemispheres.
Unsupervised anomaly detection is a challenging problem, where the aim is to detect irregular data instances. Interestingly, generative models can learn data distribution, and thus have been proposed for anomaly detec...
详细信息
ISBN:
(纸本)9781665405409
Unsupervised anomaly detection is a challenging problem, where the aim is to detect irregular data instances. Interestingly, generative models can learn data distribution, and thus have been proposed for anomaly detection. In this direction, the variational autoencoder (VAE) is popular, as it enforces an explicit probabilistic interpretation of the latent space. We note that there are other generative autoencoders (AEs) such as the denoising AE (DAE) and contractive AE (CAE), which also model data generation process without enforcing an explicit probabilistic latent space interpretation. While it is intuitively straightforward to see the benefit of a latent space with explicit probabilistic interpretation for generative tasks, it is unclear how this can be crucial for anomaly detection problems. Consequently, our exposition in this paper is to investigate the extent to which different latent space attributes of AEs impact their performances for anomaly detection tasks. We take the conventional and deterministic AE that we refer to as plain AE (PAE) as the baseline for performance comparison. Our results obtained using five different datasets reveal that an explicit probabilistic latent space is not necessary for good performance. The best results on most of the datasets are obtained using CAE, which enjoys stable latent representations.
The robustness of an anti-spoofing system is progressively more important in order to develop a reliable speaker verification system. Previous challenges and datasets mainly focus on a specific type of spoofing attack...
详细信息
The robustness of an anti-spoofing system is progressively more important in order to develop a reliable speaker verification system. Previous challenges and datasets mainly focus on a specific type of spoofing attacks. The ASVspoof 2019 edition is the first challenge to address two major spoofing types - logical and physical access. This paper presents the SJTU's submitted anti-spoofing system to the ASVspoof 2019 challenge. Log-CQT features are developed in conjunction with multi-layer convolutional neural networks for robust performance across both subtasks. CNNs with gradient linear units (GLU) activations are utilized for spoofing detection. The proposed system shows consistent performance improvement over all types of spoofing attacks. Our primary submissions achieve the 5(th) and 8(th) positions for the logical and physical access respectively. Moreover, our contrastive submission to the PA task exhibits better generalization compared to our primary submission, and achieves a comparable performance to the 3(rd) position of the challenge.
High-Level Synthesis (HLS) Design Space Exploration (DSE) is a widely accepted approach for efficiently exploring Pareto-optimal and optimal hardware solutions during the HLS process. Several HLS benchmarks and datase...
详细信息
ISBN:
(纸本)9798400706059
High-Level Synthesis (HLS) Design Space Exploration (DSE) is a widely accepted approach for efficiently exploring Pareto-optimal and optimal hardware solutions during the HLS process. Several HLS benchmarks and datasets are available for the research community to evaluate their methodologies. Unfortunately, these resources are limited and may not be sufficient for complex, multi-component system-level explorations. Generating new data using existing HLS benchmarks can be cumbersome, given the expertise and time required to effectively generate data for different HLS designs and directives. As a result, synthetic data has been used in prior work to evaluate system-level HLS DSE. However, the fidelity of the synthetic data to real data is often unclear, leading to uncertainty about the quality of system-level HLS DSE. This paper proposes a novel approach, called Vaegan, that employs generative machine learning to generate synthetic data that is robust enough to support complex system-level HLS DSE experiments that would be unattainable with only the currently available data. We explore and adapt a variational autoencoder (VAE) and Generative Adversarial Network (GAN) for this task and evaluate our approach using state-of-the-art datasets and metrics. We compare our approach to prior works and show that Vaegan effectively generates synthetic HLS data that closely mirrors the ground truth's distribution.
Generalized zero-shot learning is a method that can classify seen and unseen samples by learning training samples' visual and semantic modal information. Visual modal information is generally extracted by feature ...
详细信息
ISBN:
(数字)9781665460569
ISBN:
(纸本)9781665460569
Generalized zero-shot learning is a method that can classify seen and unseen samples by learning training samples' visual and semantic modal information. Visual modal information is generally extracted by feature extraction networks pre-trained with a large-scale data set, and semantic modal information is typically represented by class attributes. Different categories have shared semantic information, therefore, through learning the mapping between two modal information, the transferable knowledge can be used to classify testing samples. However, most methods align the two modal information of the per-sample rather than considering the alignment of the distribution of multiple instances in the two modalities. We utilize variational autoencoders mapping two modalities' information to a shared latent space, then align the samples' manifold structure of them to promote the accuracy of model classification. We evaluate the proposed method on several benchmark datasets (CUB, SUN, and AWA2), and the significant improvements have proved the method's effectiveness.
Transfer Learning (TL) plays a vital role in image classification systems based on Deep Convolutional Neural Networks (DCNNs). Systems employing such technique may be susceptible to distortions on images, motivating t...
详细信息
ISBN:
(数字)9781665483568
ISBN:
(纸本)9781665483568
Transfer Learning (TL) plays a vital role in image classification systems based on Deep Convolutional Neural Networks (DCNNs). Systems employing such technique may be susceptible to distortions on images, motivating the development of robust DCNNs capable of facing these problems. Unfortunately, changes in the architecture of DCNNs are sometimes specific to a kind of distortion and result in models that need to be retrained from scratch. This work proposes the use of autoencoders as intermediaries between pre-trained DCNNs and classifiers, delegating the denoising task to this architecture trained to encode feature maps. The classifiers are then trained to map the inputs from the autoencoder latent spaces to their respective classes. Models employing this approach achieved 3% to 4% increase in accuracy and 50% to 70% reduction in loss on the CIFAR10 and CIFAR100 datasets. The results also showed an up to 80% reduction in loss and up to 15% increase in accuracy for images with unseen distortions compared to the classical TL approach. This work improves classification results and increases robustness to distortions in a straightforward manner.
variational autoencoders (VAEs) are the state-of-the-art model for recommendation with implicit feedback signals. Unfortunately, implicit feedback suffers from selection bias, e.g., popularity bias, position bias, etc...
详细信息
ISBN:
(纸本)9798400700736
variational autoencoders (VAEs) are the state-of-the-art model for recommendation with implicit feedback signals. Unfortunately, implicit feedback suffers from selection bias, e.g., popularity bias, position bias, etc., and as a result, training from such signals produces biased recommendation models. Existing methods for debiasing the learning process have not been applied in a generative setting. We address this gap by introducing an inverse propensity scoring (IPS) based method for training VAEs from implicit feedback data in an unbiased way. Our IPS-based estimator for the VAE training objective, VAE-IPS, is provably unbiased w.r.t. selection bias. Our experimental results show that the proposed VAE-IPS model reaches significantly higher performance than existing baselines. Our contributions enable practitioners to combine state-of-the-art VAE recommendation techniques with the advantages of bias mitigation for implicit feedback.
This paper proposes a novel learning classifier system (LCS) framework named ELSDeCS (Encoding, Learning, Sampling, and Decoding Classifier System) which can employ any dimensionality reduction method as pre-processin...
详细信息
ISBN:
(纸本)9781728121536
This paper proposes a novel learning classifier system (LCS) framework named ELSDeCS (Encoding, Learning, Sampling, and Decoding Classifier System) which can employ any dimensionality reduction method as pre-processing of learning and has its own components for extracting interpretable rule representations. We also propose two LCSs as examples of ELSDeCS. The first is DCAXCSR2, which is a revised version of the conventional system, and the second is VAEXCSR, which employs a deep generative model for dimensionality reduction. The experimental results on a classification task of handwritten digits show that only VAEXCSR can extract useful rule representations thanks to its robustness of decoding newly generated samples.
暂无评论