Search

Galaxies that cause the strong gravitational lensing of background galaxies provide us crucial information about the distribution of matter around them. Traditional modelling methods that analyse such strong lenses are both time and resource consuming, require sophisticated lensing codes and modelling expertise. To study the large lens population expected from imaging surveys such as LSST, we need fast and automated analysis methods. In this work, we build and train a simple convolutional neural network with an aim to rapidly predict model parameters of gravitational lenses. We focus on the most important lens mass model parameters, namely, the Einstein radius, the axis ratio and the position angle of the major axis of the mass distribution. The network is trained on a variety of simulated data with an increasing degree of realism and shows satisfactory performance on simulated test data. The trained network is then applied to the real sample of galaxy-scale candidate lenses from the Subaru HSC, a precursor survey to LSST. Unlike the simulated lenses, we do not have the ground truth for the real lenses. Therefore, we have compared our predictions with those from YattaLens, a lens modelling pipeline. Additionally, we also compare the parameter predictions for 10 HSC lenses that were also studied by other conventional modelling methods. These comparisons show a fair quantitative agreement on the Einstein radius, although the axis ratio and the position angle from the network as well as the individual modelling methods, seem to have systematic uncertainties beyond the quoted errors., Comment: 10 pages, 9 figures

Unsupervised intrinsic image decomposition (IID) is the process of separating a natural image into albedo and shade without these ground truths. A recent model employing light detection and ranging (LiDAR) intensity demonstrated impressive performance, though the necessity of LiDAR intensity during inference restricts its practicality. Thus, IID models employing only a single image during inference while keeping as high IID quality as the one with an image plus LiDAR intensity are highly desired. To address this challenge, we propose a novel approach that utilizes only an image during inference while utilizing an image and LiDAR intensity during training. Specifically, we introduce a partially-shared model that accepts an image and LiDAR intensity individually using a different specific encoder but processes them together in specific components to learn shared representations. In addition, to enhance IID quality, we propose albedo-alignment loss and image-LiDAR conversion (ILC) paths. Albedo-alignment loss aligns the gray-scale albedo from an image to that inferred from LiDAR intensity, thereby reducing cast shadows in albedo from an image due to the absence of cast shadows in LiDAR intensity. Furthermore, to translate the input image into albedo and shade style while keeping the image contents, the input image is separated into style code and content code by encoders. The ILC path mutually translates the image and LiDAR intensity, which share content but differ in style, contributing to the distinct differentiation of style from content. Consequently, LIET achieves comparable IID quality to the existing model with LiDAR intensity, while utilizing only an image without LiDAR intensity during inference.

Similarity measures for time series are important problems for time series classification. To handle the nonlinear time distortions, Dynamic Time Warping (DTW) has been widely used. However, DTW is not learnable and suffers from a trade-off between robustness against time distortion and discriminative power. In this paper, we propose a neural network model for task-adaptive time warping. Specifically, we use the attention model, called the bipartite attention model, to develop an explicit time warping mechanism with greater distortion invariance. Unlike other learnable models using DTW for warping, our model predicts all local correspondences between two time series and is trained based on metric learning, which enables it to learn the optimal data-dependent warping for the target task. We also propose to induce pre-training of our model by DTW to improve the discriminative power. Extensive experiments demonstrate the superior effectiveness of our model over DTW and its state-of-the-art performance in online signature verification., Comment: Accepted at Pattern Recognition

A major approach for defending against adversarial attacks aims at controlling only image classifiers to be more resilient, and it does not care about visual objects, such as pandas and cars, in images. This means that visual objects themselves cannot take any defensive actions, and they are still vulnerable to adversarial attacks. In contrast, letters are artificial symbols, and we can freely control their appearance unless losing their readability. In other words, we can make the letters more defensive to the attacks. This paper poses three research questions related to the adversarial vulnerability of letter images: (1) How defensive are the letters against adversarial attacks? (2) Can we estimate how defensive a given letter image is before attacks? (3) Can we control the letter images to be more defensive against adversarial attacks? For answering the first and second questions, we measure the defensibility of letters by employing Iterative Fast Gradient Sign Method (I-FGSM) and then build a deep regression model for estimating the defensibility of each letter image. We also propose a two-step method based on a generative adversarial network (GAN) for generating character images with higher defensibility, which solves the third research question., Comment: 14 pages, 8 figures, accepted at ACPR 2023

Scene text removal (STR) is the image transformation task to remove text regions in scene images. The conventional STR methods remove all scene text. This means that the existing methods cannot select text to be removed. In this paper, we propose a novel task setting named selective scene text removal (SSTR) that removes only target words specified by the user. Although SSTR is a more complex task than STR, the proposed multi-module structure enables efficient training for SSTR. Experimental results show that the proposed method can remove target words as expected., Comment: 12 pages, 8 figures, Accepted at the 34th British Machine Vision Conference, code:https://github.com/mitanihayato/Selective-Scene-Text-Removal

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., Comment: Published in ICASSP 2023. For GitHub code, see https://github.com/nttcslab/cone

Despite recent advances in image enhancement, it remains difficult for existing approaches to adaptively improve the brightness and contrast for both low-light and normal-light images. To solve this problem, we propose a novel 2D histogram equalization approach. It assumes intensity occurrence and co-occurrence to be dependent on each other and derives the distribution of intensity occurrence (1D histogram) by marginalizing over the distribution of intensity co-occurrence (2D histogram). This scheme improves global contrast more effectively and reduces noise amplification. The 2D histogram is defined by incorporating the local pixel value differences in image reflectance into the density estimation to alleviate the adverse effects of dark lighting conditions. Over 500 images were used for evaluation, demonstrating the superiority of our approach over existing studies. It can sufficiently improve the brightness of low-light images while avoiding over-enhancement in normal-light images., Comment: Published in ICASSP 2021. For GitHub code, see https://github.com/nttcslab/rope

We propose a novel framework for target speech extraction based on semantic information, called ConceptBeam. Target speech extraction means extracting the speech of a target speaker in a mixture. Typical approaches have been exploiting properties of audio signals, such as harmonic structure and direction of arrival. In contrast, ConceptBeam tackles the problem with semantic clues. Specifically, we extract the speech of speakers speaking about a concept, i.e., a topic of interest, using a concept specifier such as an image or speech. Solving this novel problem would open the door to innovative applications such as listening systems that focus on a particular topic discussed in a conversation. Unlike keywords, concepts are abstract notions, making it challenging to directly represent a target concept. In our scheme, a concept is encoded as a semantic embedding by mapping the concept specifier to a shared embedding space. This modality-independent space can be built by means of deep metric learning using paired data consisting of images and their spoken captions. We use it to bridge modality-dependent information, i.e., the speech segments in the mixture, and the specified, modality-independent concept. As a proof of our scheme, we performed experiments using a set of images associated with spoken captions. That is, we generated speech mixtures from these spoken captions and used the images or speech signals as the concept specifiers. We then extracted the target speech using the acoustic characteristics of the identified segments. We compare ConceptBeam with two methods: one based on keywords obtained from recognition systems and another based on sound source separation. We show that ConceptBeam clearly outperforms the baseline methods and effectively extracts speech based on the semantic representation., Comment: Accepted to ACM Multimedia 2022

Our goal is to generate fonts with specific impressions, by training a generative adversarial network with a font dataset with impression labels. The main difficulty is that font impression is ambiguous and the absence of an impression label does not always mean that the font does not have the impression. This paper proposes a font generation model that is robust against missing impression labels. The key ideas of the proposed method are (1)a co-occurrence-based missing label estimator and (2)an impression label space compressor. The first is to interpolate missing impression labels based on the co-occurrence of labels in the dataset and use them for training the model as completed label conditions. The second is an encoder-decoder module to compress the high-dimensional impression space into low-dimensional. We proved that the proposed model generates high-quality font images using multi-label data with missing labels through qualitative and quantitative evaluations., Comment: Accepted ICPR2022

Different fonts have different impressions, such as elegant, scary, and cool. This paper tackles part-based shape-impression analysis based on the Transformer architecture, which is able to handle the correlation among local parts by its self-attention mechanism. This ability will reveal how combinations of local parts realize a specific impression of a font. The versatility of Transformer allows us to realize two very different approaches for the analysis, i.e., multi-label classification and translation. A quantitative evaluation shows that our Transformer-based approaches estimate the font impressions from a set of local parts more accurately than other approaches. A qualitative evaluation then indicates the important local parts for a specific impression., Comment: Accepted at DAS 2022

Deep time series metric learning is challenging due to the difficult trade-off between temporal invariance to nonlinear distortion and discriminative power in identifying non-matching sequences. This paper proposes a novel neural network-based approach for robust yet discriminative time series classification and verification. This approach adapts a parameterized attention model to time warping for greater and more adaptive temporal invariance. It is robust against not only local but also large global distortions, so that even matching pairs that do not satisfy the monotonicity, continuity, and boundary conditions can still be successfully identified. Learning of this model is further guided by dynamic time warping to impose temporal constraints for stabilized training and higher discriminative power. It can learn to augment the inter-class variation through warping, so that similar but different classes can be effectively distinguished. We experimentally demonstrate the superiority of the proposed approach over previous non-parametric and deep models by combining it with a deep online signature verification framework, after confirming its promising behavior in single-letter handwriting classification on the Unipen dataset., Comment: Accepted at ICDAR2021

Various fonts give different impressions, such as legible, rough, and comic-text.This paper aims to analyze the correlation between the local shapes, or parts, and the impression of fonts. By focusing on local shapes instead of the whole letter shape, we can realize letter-shape independent and more general analysis. The analysis is performed by newly combining SIFT and DeepSets, to extract an arbitrary number of essential parts from a particular font and aggregate them to infer the font impressions by nonlinear regression. Our qualitative and quantitative analyses prove that (1)fonts with similar parts have similar impressions, (2)many impressions, such as legible and rough, largely depend on specific parts, (3)several impressions are very irrelevant to parts., Comment: Accepted at ICDAR 2021

Styles of typefaces or fonts are often associated with specific impressions, such as heavy, contemporary, or elegant. This indicates that there are certain correlations between font shapes and their impressions. To understand the correlations, this paper realizes a shared latent space where a font and its impressions are embedded nearby. The difficulty is that the impression words attached to a font are often very noisy. This is because impression words are very subjective and diverse. More importantly, some impression words have no direct relevance to the font shapes and will disturb the realization of the shared latent space. We, therefore, use DeepSets for enhancing shape-relevant words and suppressing shape irrelevant words automatically while training the shared latent space. Quantitative and qualitative experimental results with a large-scale font-impression dataset demonstrate that the shared latent space by the proposed method describes the correlation appropriately, especially for the shape-relevant impression words., Comment: accepted at MMM2022

Various fonts give us various impressions, which are often represented by words. This paper proposes Impressions2Font (Imp2Font) that generates font images with specific impressions. Imp2Font is an extended version of conditional generative adversarial networks (GANs). More precisely, Imp2Font accepts an arbitrary number of impression words as the condition to generate the font images. These impression words are converted into a soft-constraint vector by an impression embedding module built on a word embedding technique. Qualitative and quantitative evaluations prove that Imp2Font generates font images with higher quality than comparative methods by providing multiple impression words or even unlearned words., Comment: accepted at ICDAR2021

The advancement of technology has resulted in a rapid increase in supernova (SN) discoveries. The Subaru/Hyper Suprime-Cam (HSC) transient survey, conducted from fall 2016 through spring 2017, yielded 1824 SN candidates. This gave rise to the need for fast type classification for spectroscopic follow-up and prompted us to develop a machine learning algorithm using a deep neural network (DNN) with highway layers. This machine is trained by actual observed cadence and filter combinations such that we can directly input the observed data array into the machine without any interpretation. We tested our model with a dataset from the LSST classification challenge (Deep Drilling Field). Our classifier scores an area under the curve (AUC) of 0.996 for binary classification (SN Ia or non-SN Ia) and 95.3% accuracy for three-class classification (SN Ia, SN Ibc, or SN II). Application of our binary classification to HSC transient data yields an AUC score of 0.925. With two weeks of HSC data since the first detection, this classifier achieves 78.1% accuracy for binary classification, and the accuracy increases to 84.2% with the full dataset. This paper discusses the potential use of machine learning for SN type classification purposes., Comment: 23 pages, 18 figures, accepted for publication in PASJ

We present an overview of a deep transient survey of the COSMOS field with the Subaru Hyper Suprime-Cam (HSC). The survey was performed for the 1.77 deg$^2$ ultra-deep layer and 5.78 deg$^2$ deep layer in the Subaru Strategic Program over 6- and 4-month periods from 2016 to 2017, respectively. The ultra-deep layer shows a median depth per epoch of 26.4, 26.3, 26.0, 25.6, and 24.6 mag in $g$, $r$, $i$, $z$, and $y$ bands, respectively; the deep layer is $\sim0.6$ mag shallower. In total, 1,824 supernova candidates were identified. Based on light curve fitting and derived light curve shape parameter, we classified 433 objects as Type Ia supernovae (SNe); among these candidates, 129 objects have spectroscopic or COSMOS2015 photometric redshifts and 58 objects are located at $z > 1$. Our unique dataset doubles the number of Type Ia SNe at $z > 1$ and enables various time-domain analyses of Type II SNe, high redshift superluminous SNe, variable stars, and active galactic nuclei., Comment: 17 pages, 17 figures, accepted for publication in PASJ

The current state-of-the-art in feature learning relies on the supervised learning of large-scale datasets consisting of target content items and their respective category labels. However, constructing such large-scale fully-labeled datasets generally requires painstaking manual effort. One possible solution to this problem is to employ community contributed text tags as weak labels, however, the concepts underlying a single text tag strongly depends on the users. We instead present a new paradigm for learning discriminative features by making full use of the human curation process on social networking services (SNSs). During the process of content curation, SNS users collect content items manually from various sources and group them by context, all for their own benefit. Due to the nature of this process, we can assume that (1) content items in the same group share the same semantic concept and (2) groups sharing the same images might have related semantic concepts. Through these insights, we can define human curated groups as weak labels from which our proposed framework can learn discriminative features as a representation in the space of semantic concepts the users intended when creating the groups. We show that this feature learning can be formulated as a problem of link prediction for a bipartite graph whose nodes corresponds to content items and human curated groups, and propose a novel method for feature learning based on sparse coding or network fine-tuning., Comment: Published in the Proceedings of AAAI Conferenrence on Artificial Intelligence (AAAI2018)

In this paper, we propose a simple but effective method for training neural networks with a limited amount of training data. Our approach inherits the idea of knowledge distillation that transfers knowledge from a deep or wide reference model to a shallow or narrow target model. The proposed method employs this idea to mimic predictions of reference estimators that are more robust against overfitting than the network we want to train. Different from almost all the previous work for knowledge distillation that requires a large amount of labeled training data, the proposed method requires only a small amount of training data. Instead, we introduce pseudo training examples that are optimized as a part of model parameters. Experimental results for several benchmark datasets demonstrate that the proposed method outperformed all the other baselines, such as naive training of the target model and standard knowledge distillation., Comment: 14 pages, 2 figures, will be presented at BMVC2018

Supernovae Type-Ia (SNeIa) play a significant role in exploring the history of the expansion of the Universe, since they are the best-known standard candles with which we can accurately measure the distance to the objects. Finding large samples of SNeIa and investigating their detailed characteristics have become an important issue in cosmology and astronomy. Existing methods relied on a photometric approach that first measures the luminance of supernova candidates precisely and then fits the results to a parametric function of temporal changes in luminance. However, it inevitably requires multi-epoch observations and complex luminance measurements. In this work, we present a novel method for classifying SNeIa simply from single-epoch observation images without any complex measurements, by effectively integrating the state-of-the-art computer vision methodology into the standard photometric approach. Our method first builds a convolutional neural network for estimating the luminance of supernovae from telescope images, and then constructs another neural network for the classification, where the estimated luminance and observation dates are used as features for classification. Both of the neural networks are integrated into a single deep neural network to classify SNeIa directly from observation images. Experimental results show the effectiveness of the proposed method and reveal classification performance comparable to existing photometric methods with multi-epoch observations., Comment: 7 pages, published as a workshop paper in ICDCS2017, in June 2017

This paper proposes a novel type of random forests called a denoising random forests that are robust against noises contained in test samples. Such noise-corrupted samples cause serious damage to the estimation performances of random forests, since unexpected child nodes are often selected and the leaf nodes that the input sample reaches are sometimes far from those for a clean sample. Our main idea for tackling this problem originates from a binary indicator vector that encodes a traversal path of a sample in the forest. Our proposed method effectively employs this vector by introducing denoising autoencoders into random forests. A denoising autoencoder can be trained with indicator vectors produced from clean and noisy input samples, and non-leaf nodes where incorrect decisions are made can be identified by comparing the input and output of the trained denoising autoencoder. Multiple traversal paths with respect to the nodes with incorrect decisions caused by the noises can then be considered for the estimation., Comment: 20 pages, 10 figures, submitted to Pattern Recognition

This paper provides a generic framework of component analysis (CA) methods introducing a new expression for scatter matrices and Gram matrices, called Generalized Pairwise Expression (GPE). This expression is quite compact but highly powerful: The framework includes not only (1) the standard CA methods but also (2) several regularization techniques, (3) weighted extensions, (4) some clustering methods, and (5) their semi-supervised extensions. This paper also presents quite a simple methodology for designing a desired CA method from the proposed framework: Adopting the known GPEs as templates, and generating a new method by combining these templates appropriately., Comment: Accepted to IAPR International Conference on Pattern Recognition, submitted to IPSJ Transactions on Mathematical Modeling and its Applications (TOM). Just only one-page abstract for new due to novelty violation for journal submission. The details will be disclosed in late September

Automatic video segmentation plays an important role in a wide range of computer vision and image processing applications. Recently, various methods have been proposed for this purpose. The problem is that most of these methods are far from real-time processing even for low-resolution videos due to the complex procedures. To this end, we propose a new and quite fast method for automatic video segmentation with the help of 1) efficient optimization of Markov random fields with polynomial time of number of pixels by introducing graph cuts, 2) automatic, computationally efficient but stable derivation of segmentation priors using visual saliency and sequential update mechanism, and 3) an implementation strategy in the principle of stream processing with graphics processor units (GPUs). Test results indicates that our method extracts appropriate regions from videos as precisely as and much faster than previous semi-automatic methods even though any supervisions have not been incorporated., Comment: submitted to Special Issue on High Performance Computation on Hardware Accelerators, the Computer Journal

A multiterminal lossy coding problem, which includes various problems such as the Wyner-Ziv problem and the complementary delivery problem as special cases, is considered. It is shown that any point in the achievable rate-distortion region can be attained even if the source statistics are not known., Comment: 9 pages, 4 figures

Recent studies in the field of human vision science suggest that the human responses to the stimuli on a visual display are non-deterministic. People may attend to different locations on the same visual input at the same time. Based on this knowledge, we propose a new stochastic model of visual attention by introducing a dynamic Bayesian network to predict the likelihood of where humans typically focus on a video scene. The proposed model is composed of a dynamic Bayesian network with 4 layers. Our model provides a framework that simulates and combines the visual saliency response and the cognitive state of a person to estimate the most probable attended regions. Sample-based inference with Markov chain Monte-Carlo based particle filter and stream processing with multi-core processors enable us to estimate human visual attention in near real time. Experimental results have demonstrated that our model performs significantly better in predicting human visual attention compared to the previous deterministic models., Comment: 24 pages, single-column, 13 figures excluding portlaits, submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence.

A coding problem for correlated information sources is investigated. Messages emitted from two correlated sources are jointly encoded, and delivered to two decoders. Each decoder has access to one of the two messages to enable it to reproduce the other message. The rate-distortion function for the coding problem and its interesting properties are clarified., Comment: 13 pages in double-column format, 1 figure, submitted to IEICE Transactions on Fundamentals

This paper deals with a coding problem called complementary delivery, where messages from two correlated sources are jointly encoded and each decoder reproduces one of two messages using the other message as the side information. Both lossless and lossy universal complementary delivery coding schemes are investigated. In the lossless case, it is demonstrated that a universal complementary delivery code can be constructed by only combining two Slepian-Wolf codes. Especially, it is shown that a universal lossless complementary delivery code, for which error probability is exponentially tight, can be constructed from two linear Slepian-Wolf codes. In the lossy case, a universal complementary delivery coding scheme based on Wyner-Ziv codes is proposed. While the proposed scheme cannot attain the optimal rate-distortion trade-off in general, the rate-loss is upper bounded by a universal constant under some mild conditions. The proposed schemes allows us to apply any Slepian-Wolf and Wyner-Ziv codes to complementary delivery coding., Comment: 20 pages, one column, submitted to IEEE Transactions on Information Theory

This paper deals with a universal coding problem for a certain kind of multiterminal source coding network called a generalized complementary delivery network. In this network, messages from multiple correlated sources are jointly encoded, and each decoder has access to some of the messages to enable it to reproduce the other messages. Both fixed-to-fixed length and fixed-to-variable length lossless coding schemes are considered. Explicit constructions of universal codes and the bounds of the error probabilities are clarified by using methods of types and graph-theoretical analysis., Comment: 18 pages, one column, submitted to IEEE Transactions on Information Theory, presented at a recent result session in ISIT2007

This paper deals with a universal coding problem for a certain kind of multiterminal source coding system that we call the complementary delivery coding system. In this system, messages from two correlated sources are jointly encoded, and each decoder has access to one of the two messages to enable it to reproduce the other message. Both fixed-to-fixed length and fixed-to-variable length lossless coding schemes are considered. Explicit constructions of universal codes and bounds of the error probabilities are clarified via type-theoretical and graph-theoretical analyses. [[Keywords]] multiterminal source coding, complementary delivery, universal coding, types of sequences, bipartite graphs, Comment: 18 pages, some of the material in this manuscript has been already published in IEICE Transactions on Fundamentals, September 2007. Several additional results are also included

This paper presents a new method for a quick similarity-based search through long unlabeled audio streams to detect and locate audio clips provided by users. The method involves feature-dimension reduction based on a piecewise linear representation of a sequential feature trajectory extracted from a long audio stream. Two techniques enable us to obtain a piecewise linear representation: the dynamic segmentation of feature trajectories and the segment-based Karhunen-L\'{o}eve (KL) transform. The proposed search method guarantees the same search results as the search method without the proposed feature-dimension reduction method in principle. Experiment results indicate significant improvements in search speed. For example the proposed method reduced the total search time to approximately 1/12 that of previous methods and detected queries in approximately 0.3 seconds from a 200-hour audio database., Comment: 20 pages, to appear in IEEE Transactions on Audio, Speech and Language Processing