检索结果-内蒙古大学图书馆

Fast Regularized Discrete Optimal Transport with Group-Sparse Regularizers

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ida, Yasutoshi Kanai, Sekitoshi Adachi, Kazuki Kumagai, Atsutoshi Fujiwara, Yasuhiro NTT Computer and Data Science Laboratories Japan NTT Communication Science Laboratories Japan

Regularized discrete optimal transport (OT) is a powerful tool to measure the distance between two discrete distributions that have been constructed from data samples on two different domains. While it has a wide range of applications in machine learning, in some cases the sampled data from only one of the domains will have class labels such as unsupervised domain adaptation. In this kind of problem setting, a group-sparse regularizer is frequently leveraged as a regularization term to handle class labels. In particular, it can preserve the label structure on the data samples by corresponding the data samples with the same class label to one group-sparse regularization term. As a result, we can measure the distance while utilizing label information by solving the regularized optimization problem with gradient-based algorithms. However, the gradient computation is expensive when the number of classes or data samples is large because the number of regularization terms and their respective sizes also turn out to be large. This paper proposes fast discrete OT with group-sparse regularizers. Our method is based on two ideas. The first is to safely skip the computations of the gradients that must be zero. The second is to efficiently extract the gradients that are expected to be nonzero. Our method is guaranteed to return the same value of the objective function as that of the original method. Experiments show that our method is up to 8.6 times faster than the original method without degrading accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Deep Quantigraphic Image Enhancement via Comparametric Equations

学校读者我要写书评

暂无评论

Deep Quantigraphic Image Enhancement via Comparametric Equat...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiaomeng Wu Yongqing Sun Akisato Kimura Communication Science Laboratories NTT Corporation Computer and Data Science Laboratories NTT Corporation

Most recent methods of deep image enhancement can be generally classified into two types: decompose-and-enhance and illumination estimation-centric. The former is usually less efficient, and the latter is constrained by a strong assumption regarding image reflectance as the desired enhancement result. To alleviate this constraint while retaining high efficiency, we propose a novel trainable module that diversifies the conversion from the low-light image and illumination map to the enhanced image. It formulates image enhancement as a comparametric equation parameterized by a camera response function and an exposure compensation ratio. By incorporating this module in an illumination estimation-centric DNN, our method improves the flexibility of deep image enhancement, limits the computational burden to illumination estimation, and allows for fully unsupervised learning adaptable to the diverse demands of different tasks.

关键词： Reflectivity Semantic segmentation Lighting Object detection Speech enhancement Signal processing Mathematical models

Meta-learning for Positive-unlabeled Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kumagai, Atsutoshi Iwata, Tomoharu Fujiwara, Yasuhiro NTT Computer and Data Science Laboratories Japan NTT Communication Science Laboratories Japan

We propose a meta-learning method for positive and unlabeled (PU) classification, which improves the performance of binary classifiers obtained from only PU data in unseen target tasks. PU learning is an important problem since PU data naturally arise in real-world applications such as outlier detection and information retrieval. Existing PU learning methods require many PU data, but sufficient data are often unavailable in practice. The proposed method minimizes the test classification risk after the model is adapted to PU data by using related tasks that consist of positive, negative, and unlabeled data. We formulate the adaptation as an estimation problem of the Bayes optimal classifier, which is an optimal classifier to minimize the classification risk. The proposed method embeds each instance into a task-specific space using neural networks. With the embedded PU data, the Bayes optimal classifier is estimated through density-ratio estimation of PU densities, whose solution is obtained as a closed-form solution. The closed-form solution enables us to efficiently and effectively minimize the test classification risk. We empirically show that the proposed method outperforms existing methods with one synthetic and three real-world datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Risk perception

TRANSFERRING LEARNING TRAJECTORIES OF NEURAL NETWORKS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chijiwa, Daiki NTT Computer and Data Science Laboratories NTT Corporation Japan

Training deep neural networks (DNNs) is computationally expensive, which is problematic especially when performing duplicated or similar training runs in model ensemble or fine-tuning pre-trained models, for example. Once we have trained one DNN on some dataset, we have its learning trajectory (i.e., a sequence of intermediate parameters during training) which may potentially contain useful information for learning the dataset. However, there has been no attempt to utilize such information of a given learning trajectory for another training. In this paper, we formulate the problem of "transferring" a given learning trajectory from one initial parameter to another one (named learning transfer problem) and derive the first algorithm to approximately solve it by matching gradients successively along the trajectory via permutation symmetry. We empirically show that the transferred parameters achieve non-trivial accuracy before any direct training, and can be trained significantly faster than training from scratch. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

Talking Face Generation for Impression Conversion Considering Speech Semantics

学校读者我要写书评

暂无评论

Talking Face Generation for Impression Conversion Considerin...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Saki Mizuno Nobukatsu Hojo Kazutoshi Shinoda Keita Suzuki Mana Ihori Hiroshi Sato Tomohiro Tanaka Naotaka Kawata Satoshi Kobashikawa Ryo Masumura NTT Computer & Data Science Laboratories NTT Corporation Japan

This study investigates the talking face generation method to convert a speaker’s video to give a target impression, such as “favorable” or “considerate”. Such an impression conversion method needs to consider the input speech semantics because they affect the impression of a speaker’s video along with the facial expression. Conventional emotional talking face generation methods utilize speech information to synchronize the lip and speech of the output video. However, they cannot consider speech semantics because the speech representations contain only phonetic information. To solve this problem, we propose a facial expression conversion model that uses a semantic vector obtained from BERT embeddings of speech recognition results of input speech. We first constructed an audio-visual dataset with impression labels assigned to each utterance. The evaluation results based on the dataset showed that the proposed method could improve the estimation accuracy of the facial expressions of the target video.

关键词：

Open-Set Recognition for Facial-Expression Recognition

学校读者我要写书评

暂无评论

Open-Set Recognition for Facial-Expression Recognition

IEEE International Conference on Image Processing

作者： Mihiro Uchida Shota Orihashi Akihiko Takashima Yoshihiro Yamazaki Ryo Masumura NTT Computer and Data Science Laboratories NTT Corporation Japan

We address distinguishing whether an input is a facial image by learning only a facial-expression recognition (FER) dataset. To avoid misclassification in FER, it is necessary to distinguish whether the input is a facial image. Unfortunately, collecting exhaustive non-face images is costly. Therefore, distinguishing whether the input is a facial image by learning only an FER dataset is important. A representative method for this task is learning reconstruction of only facial images and determining high-error samples between input images and reconstructed images as non-face images. However, reconstruction is difficult on facial images because such images contain detailed features. Our key idea to tackle the task without reconstruction is assuming that facial images will match several emotions, whereas non-face images will not match any emotion. Therefore, we propose a method for training a discriminator that determines whether the inputs and emotions match using counter-factual pairs in an FER dataset. A metric for the task is then obtained by taking into account each emotion in the posterior probability that inputs and emotions match, estimated by the discriminator. Experiments on the RAF-DB dataset vs. the Stanford Dogs dataset and AffectNet datasets showed the effectiveness of our method.

关键词：

Audio Visual Scene-Aware Dialog Generation with Transformer-based Video Representations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yamazaki, Yoshihiro Orihashi, Shota Masumura, Ryo Uchida, Mihiro Takashima, Akihiko NTT Computer and Data Science Laboratories NTT Corporation Japan

There have been many attempts to build multimodal dialog systems that can respond to a question about given audiovisual information, and the representative task for such systems is the Audio Visual Scene-Aware Dialog (AVSD). Most conventional AVSD models adopt the Convolutional Neural Network (CNN)-based video feature extractor to understand visual information. While a CNN tends to obtain both temporally and spatially local information, global information is also crucial for boosting video understanding because AVSD requires long-term temporal visual dependency and whole visual information. In this study, we apply the Transformer-based video feature that can capture both temporally and spatially global representations more efficiently than the CNN-based feature. Our AVSD model with its Transformer-based feature attains higher objective performance scores for answer generation. In addition, our model achieves a subjective score close to that of human answers in DSTC10. We observed that the Transformer-based visual feature is beneficial for the AVSD task because our model tends to correctly answer the questions that need a temporally and spatially broad range of visual information. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolutional neural networks

Utilizing resource-rich language datasets for end-to-end scene text recognition in resource-poor languages

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Orihashi, Shota Yamazaki, Yoshihiro Makishima, Naoki Ihori, Mana Takashima, Akihiko Tanaka, Tomohiro Masumura, Ryo NTT Computer and Data Science Laboratories NTT Corporation Japan

This paper presents a novel training method for end-to-end scene text recognition. End-to-end scene text recognition offers high recognition accuracy, especially when using the encoder-decoder model based on Transformer. To train a highly accurate end-to-end model, we need to prepare a large image-to-text paired dataset for the target language. However, it is difficult to collect this data, especially for resource-poor languages. To overcome this difficulty, our proposed method utilizes well-prepared large datasets in resource-rich languages such as English, to train the resource-poor encoder-decoder model. Our key idea is to build a model in which the encoder reflects knowledge of multiple languages while the decoder specializes in knowledge of just the resource-poor language. To this end, the proposed method pre-trains the encoder by using a multilingual dataset that combines the resource-poor language's dataset and the resource-rich language's dataset to learn language-invariant knowledge for scene text recognition. The proposed method also pre-trains the decoder by using the resource-poor language's dataset to make the decoder better suited to the resource-poor language. Experiments on Japanese scene text recognition using a small, publicly available dataset demonstrate the effectiveness of the proposed method. Copyright © 2021, The Authors. All rights reserved.

关键词： Signal encoding

End-to-End Joint Target and Non-Target Speakers ASR

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Masumura, Ryo Makishima, Naoki Yamane, Taiga Yamazaki, Yoshihiko Mizuno, Saki Ihori, Mana Uchida, Mihiro Suzuki, Keita Sato, Hiroshi Tanaka, Tomohiro Takashima, Akihiko Suzuki, Satoshi Moriya, Takafumi Hojo, Nobukatsu Ando, Atsushi NTT Computer and Data Science Laboratories NTT Corporation Japan

This paper proposes a novel automatic speech recognition (ASR) system that can transcribe individual speaker’s speech while identifying whether they are target or non-target speakers from multi-talker overlapped speech. Target-speaker ASR systems are a promising way to only transcribe a target speaker’s speech by enrolling the target speaker’s information. However, in conversational ASR applications, transcribing both the target speaker’s speech and non-target speakers’ ones is often required to understand interactive information. To naturally consider both target and non-target speakers in a single ASR model, our idea is to extend autoregressive modeling-based multi-talker ASR systems to utilize the enrollment speech of the target speaker. Our proposed ASR is performed by recursively generating both textual tokens and tokens that represent target or non-target speakers. Our experiments demonstrate the effectiveness of our proposed method. © 2023, CC BY.

关键词： Speech recognition