Multimodal embedding is a crucial research topic for cross-modal understanding, data mining, and translation. Many studies have attempted to extract representations from given entities and align them ...in a shared embedding space. However, because entities in different modalities exhibit different abstraction levels and modality-specific information, it is insufficient to embed related entities close to each other. In this study, we propose the Target-Oriented Deformation Network (TOD-Net), a novel module that continuously deforms the embedding space into a new space under a given condition, thereby providing conditional similarities between entities. Unlike methods based on cross-modal attention applied to words and cropped images, TOD-Net is a post-process applied to the embedding space learned by existing embedding systems and improves their performances of retrieval. In particular, when combined with cutting-edge models, TOD-Net gains the state-of-the-art image-caption retrieval model associated with the MS COCO and Flickr30k datasets. Qualitative analysis reveals that TOD-Net successfully emphasizes entity-specific concepts and retrieves diverse targets via handling higher levels of diversity than existing models.
A new ungulinid bivalve species, Transkeia sagaensis n. sp., is described from the uppermost Eocene-lowest Oligocene Kishima Formation in Kyūshū, southwestern Japan. The present new species is the ...oldest member in the genus Transkeia Huber, 2015. In the previous molluscan studies of the formation, no ungulinid species have been recognized. This is probably due to misidentification as the venerid Cyclinella? compressa (Nagao, 1928b).
Modeling and implementation approaches for the reproduction of input-output relationships in biological nervous tissues contribute to the development of engineering and clinical applications. ...However, because of high nonlinearity, the traditional modeling and implementation approaches encounter difficulties in terms of generalization ability (i.e., performance when reproducing an unknown data set) and computational resources (i.e., computation time and circuit elements). To overcome these difficulties, asynchronous cellular automaton-based neuron (ACAN) models, which are described as special kinds of cellular automata that can be implemented as small asynchronous sequential logic circuits have been proposed. This paper presents a novel type of such ACAN and a theoretical analysis of its excitability. This paper also presents a novel network of such neurons, which can mimic input-output relationships of biological and nonlinear ordinary differential equation model neural networks. Numerical analyses confirm that the presented network has a higher generalization ability than other major modeling and implementation approaches. In addition, Field-Programmable Gate Array-implementations confirm that the presented network requires lower computational resources.
The diffusion model has achieved success in generating and editing high-quality images because of its ability to produce fine details. Its superior generation ability has the potential to facilitate ...more detailed segmentation. This study presents a novel approach to segmentation tasks using an inverse heat dissipation model, a kind of diffusion-based models. The proposed method involves generating a mask that gradually shrinks to fit the shape of the desired segmentation region. We comprehensively evaluated the proposed method using multiple datasets under varying conditions. The results show that the proposed method outperforms existing methods and provides a more detailed segmentation.
The combination of neural networks and numerical integration can provide highly accurate models of continuous-time dynamical systems and probabilistic distributions. However, if a neural network is ...used <inline-formula> <tex-math notation="LaTeX">\bm{n}</tex-math> </inline-formula> times during numerical integration, the whole computation graph can be considered as a network <inline-formula> <tex-math notation="LaTeX">\bm{n}</tex-math> </inline-formula> times deeper than the original. The backpropagation algorithm consumes memory in proportion to the number of uses times of the network size, causing practical difficulties. This is true even if a checkpointing scheme divides the computation graph into subgraphs. Alternatively, the adjoint method obtains a gradient by a numerical integration backward in time; although this method consumes memory only for single-network use, the computational cost of suppressing numerical errors is high. The symplectic adjoint method proposed in this study, an adjoint method solved by a symplectic integrator, obtains the exact gradient (up to rounding error) with memory proportional to the number of uses plus the network size. The theoretical analysis shows that it consumes much less memory than the naive backpropagation algorithm and checkpointing schemes. The experiments verify the theory, and they also demonstrate that the symplectic adjoint method is faster than the adjoint method and is more robust to rounding errors.
Topology-Aware Flow-Based Point Cloud Generation Kimura, Takumi; Matsubara, Takashi; Uehara, Kuniaki
IEEE transactions on circuits and systems for video technology,
11/2022, Volume:
32, Issue:
11
Journal Article
Peer reviewed
Point clouds have attracted attention as a representation of an object's surface. Deep generative models have typically used a continuous map from a dense set in a latent space to express their ...variations. However, a continuous map cannot adequately express the varying numbers of holes. That is, previous approaches disregarded the topological structure of point clouds. Furthermore, a point cloud comprises several subparts, making it difficult to express it using a continuous map. This paper proposes ChartPointFlow, a flow-based deep generative model that forms a map conditioned on a label. Similar to a manifold chart, a map conditioned on a label is assigned to a continuous subset of a point cloud. Thus, ChartPointFlow is able to maintain the topological structure with clear boundaries and holes, whereas previous approaches generated blurry point clouds with fuzzy holes. The experimental results show that ChartPointFlow achieves state-of-the-art performance in various tasks, including generation, reconstruction, upsampling, and segmentation.
The knowledge graphs are structured data utilized for information retrieval purposes. Entity alignment using multi-modal supplementary information plays an important role in knowledge graph ...integration. However, if the supplementary information is missing or incorrect, it can negatively impact the retrieval of information. If we can quantify the usefulness of the information for retrieval as a degree of importance, the influence of unimportant supplementary information can be reduced. In this study, we proposed a method that quantifies the importance of each piece of information by using a probability distribution. Our proposed method improves an existing method by 7.7% and 7.3% in H@1 on two datasets (FB15K-DB15K, FB15K-YAGO15K). Qualitative experiments also showed that the importance of information quantified by uncertainty successfully captured data that was not useful for information retrieval. Our qualitative experiments also show that the importance of information, quantified by uncertainty, effectively captures data that is not beneficial for information retrieval.
The traditional method of measuring nitrogen content in plants is a time-consuming and labor-intensive task. Spectral vegetation indices extracted from unmanned aerial vehicle (UAV) images and ...machine learning algorithms have been proved effective in assisting nutritional analysis in plants. Still, this analysis has not considered the combination of spectral indices and machine learning algorithms to predict nitrogen in tree-canopy structures. This paper proposes a new framework to infer the nitrogen content in citrus-tree at a canopy-level using spectral vegetation indices processed with the random forest algorithm. A total of 33 spectral indices were estimated from multispectral images acquired with a UAV-based sensor. Leaf samples were gathered from different planting-fields and the leaf nitrogen content (LNC) was measured in the laboratory, and later converted into the canopy nitrogen content (CNC). To evaluate the robustness of the proposed framework, we compared it with other machine learning algorithms. We used 33,600 citrus trees to evaluate the performance of the machine learning models. The random forest algorithm had higher performance in predicting CNC than all models tested, reaching an R2 of 0.90, MAE of 0.341 g·kg−1 and MSE of 0.307 g·kg−1. We demonstrated that our approach is able to reduce the need for chemical analysis of the leaf tissue and optimizes citrus orchard CNC monitoring.
Intraductal papillary neoplasms of the bile duct (IPNB) shows favorable prognosis and is regarded as a biliary counterpart of intraductal papillary mucinous neoplasm (IPMN) of the pancreas. Although ...activating point mutations of GNAS at codon 201 have been detected in approximately two thirds of IPMNs of the pancreas, there have been few studies on GNAS mutations in IPNBs. This study investigates the status of GNAS and KRAS mutations and their association with clinicopathological factors in IPNBs. We examined the status of GNAS mutation at codon 201 and KRAS mutation at codon 12&13, degree of mucin production and immunohistochemical expressions of MUC mucin core proteins in 29 patients (M/F = 15/14) with IPNB in intrahepatic and perihilar bile ducts (perihilar IPNB) and 6 patients (M/F = 5/1) with IPNB in distal bile ducts (distal IPNB). GNAS mutations and KRAS mutations were detected in 50% and 46.2% of IPNBs, respectively. There was no significant correlation between the status of GNAS mutation and clinicopathological factors in IPNBs, whereas, the status of KRAS mutation was significantly inversely correlated with the degree of MUC2 expression in IPNBs (p<0.05). All IPNBs with GNAS mutation only showed high-mucin production. Degree of mucin production was significantly higher in perihilar IPNBs than distal IPNBs (p<0.05). MUC2 and MUC5AC expression was significantly higher in IPNBs with high-mucin production than those with low-mucin production (p<0.01 and p<0.05, respectively). In conclusions, this study firstly disclosed frequent GNAS mutations in IPNBs, similarly to IPMNs. This may suggest a common histopathogenesis of IPNBs and IPMNs. The status of KRAS mutations was inversely correlated to MUC2 expression and this may suggest heterogeneous properties of IPNBs. IPNBs with high-mucin production are characterized by perihilar location and high expression of MUC2 and MUC5AC, irrespective of the status of GNAS and KRAS mutations.
There exists a great demand for automatic anomaly detection in industrial world. The anomaly has been defined as a group of samples that rarely or never appears. Given a type of products, one has to ...collect numerous samples and train an anomaly detector. When one diverts a model trained with old types of products with sufficient inventory to the new type, one can detect anomalies of the new type before a production line is established. However, because of the definition of the anomaly, a typical anomaly detector considers the new type of products anomalous even if it is consistent with the standard. Given the above practical demand, this study propose a novel problem setting, few-shot anomaly detection, where an anomaly detector trained in source domains is adapted to a small set of target samples without full retraining. Then, we tackle this problem using a hierarchical probabilistic model based on deep learning. Our empirical results on toy and real-world datasets demonstrate that the proposed model detects anomalies in a small set of target samples successfully.