LIVIVO - Das Suchportal für Lebenswissenschaften

switch to English language
Zurück zur letzten Suche Suchhistorie
Erweiterte Suche

Ihre letzten Suchen

  1. AU="Yan, Junchi"
  2. AU="Matzner, R"
  3. AU="Escobedo, Víctor M"
  4. AU="Khuituan, Pissared"
  5. AU="Akiyoshi Uezu"

Suchergebnis

Treffer 1 - 10 von insgesamt 151

Suchoptionen

  1. Artikel ; Online: ScaleGCN: Efficient and Effective Graph Convolution via Channel-Wise Scale Transformation.

    Zhang, Tianqi / Wu, Qitian / Yan, Junchi / Zhao, Yunan / Han, Bing

    IEEE transactions on neural networks and learning systems

    2024  Band 35, Heft 4, Seite(n) 4478–4490

    Abstract: Graph convolutional networks (GCNs) have shown success in many graph-based applications as they can combine node features and graph topology to obtain expressive embeddings. While there exist numerous GCN variants, a typical graph convolution layer uses ... ...

    Abstract Graph convolutional networks (GCNs) have shown success in many graph-based applications as they can combine node features and graph topology to obtain expressive embeddings. While there exist numerous GCN variants, a typical graph convolution layer uses neighborhood aggregation and fully-connected (FC) layers to extract topological and node-wise features, respectively. However, when the receptive field of GCNs becomes larger, the tight coupling between the number of neighborhood aggregation and FC layers can increase the risk of over-fitting. Also, the FC layer between two successive aggregation operations will mix and pollute features in different channels, bringing noise and making node features hard to converge at each channel. In this article, we explore graph convolution without FC layers. We propose scale graph convolution, a new graph convolution using channel-wise scale transformation to extract node features. We provide empirical evidence that our new method has lower over-fitting risk and needs fewer layers to converge. We show from both theoretical and empirical perspectives that models with scale graph convolution have lower computational and memory costs than traditional GCN models. Experimental results on various datasets show that our method can achieve state-of-the-art results, in a cost-effective fashion.
    Sprache Englisch
    Erscheinungsdatum 2024-04-04
    Erscheinungsland United States
    Dokumenttyp Journal Article
    ISSN 2162-2388
    ISSN (online) 2162-2388
    DOI 10.1109/TNNLS.2022.3199390
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    Über subito bestellen

    Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  2. Artikel ; Online: Learning High-Order Graph Convolutional Networks via Adaptive Layerwise Aggregation Combination.

    Zhang, Tianqi / Wu, Qitian / Yan, Junchi

    IEEE transactions on neural networks and learning systems

    2023  Band 34, Heft 8, Seite(n) 5144–5155

    Abstract: Graph convolutional networks have attracted wide attention for their expressiveness and empirical success on graph-structured data. However, deeper graph convolutional networks with access to more information can often perform worse because their low- ... ...

    Abstract Graph convolutional networks have attracted wide attention for their expressiveness and empirical success on graph-structured data. However, deeper graph convolutional networks with access to more information can often perform worse because their low-order Chebyshev polynomial approximation cannot learn adaptive and structure-aware representations. To solve this problem, many high-order graph convolution schemes have been proposed. In this article, we study the reason why high-order schemes have the ability to learn structure-aware representations. We first prove that these high-order schemes are generalized Weisfeiler-Lehman (WL) algorithm and conduct spectral analysis on these schemes to show that they correspond to polynomial filters in the graph spectral domain. Based on our analysis, we point out twofold limitations of existing high-order models: 1) lack mechanisms to generate individual feature combinations for each node and 2) fail to properly model the relationship between information from different distances. To enable a node-specific combination scheme and capture this interdistance relationship for each node efficiently, we propose a new adaptive feature combination method inspired by the squeeze-and-excitation module that can recalibrate features from different distances by explicitly modeling interdependencies between them. Theoretical analysis shows that models with our new approach can effectively learn structure-aware representations, and extensive experimental results show that our new approach can achieve significant performance gain compared with other high-order schemes.
    Sprache Englisch
    Erscheinungsdatum 2023-08-04
    Erscheinungsland United States
    Dokumenttyp Journal Article
    ISSN 2162-2388
    ISSN (online) 2162-2388
    DOI 10.1109/TNNLS.2021.3119958
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    Über subito bestellen

    Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  3. Artikel ; Online: Learning Deep Generative Clustering via Mutual Information Maximization.

    Yang, Xiaojiang / Yan, Junchi / Cheng, Yu / Zhang, Yizhe

    IEEE transactions on neural networks and learning systems

    2023  Band 34, Heft 9, Seite(n) 6263–6275

    Abstract: Deep clustering refers to joint representation learning and clustering using deep neural networks. Existing methods can be mainly categorized into two types: discriminative and generative methods. The former learns representations for clustering with ... ...

    Abstract Deep clustering refers to joint representation learning and clustering using deep neural networks. Existing methods can be mainly categorized into two types: discriminative and generative methods. The former learns representations for clustering with discriminative mechanisms directly, and the latter estimate the latent distribution of each cluster for generating data points and then infers cluster assignments. Although generative methods have the advantage of estimating the latent distributions of clusters, their performances still significantly fall behind discriminative methods. In this work, we argue that this performance gap might be partly due to the overlap of data distribution of different clusters. In fact, there is little guarantee of generative methods to separate the distributions of different clusters in the data space. To tackle these problems, we theoretically prove that mutual information maximization promotes the separation of different clusters in the data space, which provides a theoretical justification for deep generative clustering with mutual information maximization. Our theoretical analysis directly leads to a model which integrates a hierarchical generative adversarial network and mutual information maximization. Moreover, we further propose three techniques and empirically show their effects to stabilize and enhance the model. The proposed approach notably outperforms other generative models for deep clustering on public benchmarks.
    Sprache Englisch
    Erscheinungsdatum 2023-09-01
    Erscheinungsland United States
    Dokumenttyp Journal Article
    ISSN 2162-2388
    ISSN (online) 2162-2388
    DOI 10.1109/TNNLS.2021.3135375
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    Über subito bestellen

    Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  4. Artikel ; Online: Unsupervised Learning of Graph Matching With Mixture of Modes via Discrepancy Minimization.

    Wang, Runzhong / Yan, Junchi / Yang, Xiaokang

    IEEE transactions on pattern analysis and machine intelligence

    2023  Band 45, Heft 8, Seite(n) 10500–10518

    Abstract: Graph matching (GM) has been a long-standing combinatorial problem due to its NP-hard nature. Recently (deep) learning-based approaches have shown their superiority over the traditional solvers while the methods are almost based on supervised learning ... ...

    Abstract Graph matching (GM) has been a long-standing combinatorial problem due to its NP-hard nature. Recently (deep) learning-based approaches have shown their superiority over the traditional solvers while the methods are almost based on supervised learning which can be expensive or even impractical. We develop a unified unsupervised framework from matching two graphs to multiple graphs, without correspondence ground truth for training. Specifically, a Siamese-style unsupervised learning framework is devised and trained by minimizing the discrepancy of a second-order classic solver and a first-order (differentiable) Sinkhorn net as two branches for matching prediction. The two branches share the same CNN backbone for visual graph matching. Our framework further allows unsupervised learning with graphs from a mixture of modes which is ubiquitous in reality. Specifically, we develop and unify the graduated assignment (GA) strategy for matching two-graph, multi-graph, and graphs from a mixture of modes, whereby two-way constraint and clustering confidence (for mixture case) are modulated by two separate annealing parameters, respectively. Moreover, for partial and outlier matching, an adaptive reweighting technique is developed to suppress the overmatching issue. Experimental results on real-world benchmarks including natural image matching show our unsupervised method performs comparatively and even better against two-graph based supervised approaches.
    Mesh-Begriff(e) Algorithms ; Unsupervised Machine Learning ; Cluster Analysis
    Sprache Englisch
    Erscheinungsdatum 2023-06-30
    Erscheinungsland United States
    Dokumenttyp Journal Article
    ISSN 1939-3539
    ISSN (online) 1939-3539
    DOI 10.1109/TPAMI.2023.3257830
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    Über subito bestellen

    Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  5. Artikel ; Online: Combinatorial Learning of Robust Deep Graph Matching: An Embedding Based Approach.

    Wang, Runzhong / Yan, Junchi / Yang, Xiaokang

    IEEE transactions on pattern analysis and machine intelligence

    2023  Band 45, Heft 6, Seite(n) 6984–7000

    Abstract: Graph matching aims to establish node correspondence between two graphs, which has been a fundamental problem for its NP-hard nature. One practical consideration is the effective modeling of the affinity function in the presence of noise, such that the ... ...

    Abstract Graph matching aims to establish node correspondence between two graphs, which has been a fundamental problem for its NP-hard nature. One practical consideration is the effective modeling of the affinity function in the presence of noise, such that the mathematically optimal matching result is also physically meaningful. This paper resorts to deep neural networks to learn the node and edge feature, as well as the affinity model for graph matching in an end-to-end fashion. The learning is supervised by combinatorial permutation loss over nodes. Specifically, the parameters belong to convolutional neural networks for image feature extraction, graph neural networks for node embedding that convert the structural (beyond second-order) information into node-wise features that leads to a linear assignment problem, as well as the affinity kernel between two graphs. Our approach enjoys flexibility in that the permutation loss is agnostic to the number of nodes, and the embedding model is shared among nodes such that the network can deal with varying numbers of nodes for both training and inference. Moreover, our network is class-agnostic. Experimental results on extensive benchmarks show its state-of-the-art performance. It bears some generalization capability across categories and datasets, and is capable for robust matching against outliers.
    Sprache Englisch
    Erscheinungsdatum 2023-05-05
    Erscheinungsland United States
    Dokumenttyp Journal Article
    ISSN 1939-3539
    ISSN (online) 1939-3539
    DOI 10.1109/TPAMI.2020.3005590
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    Über subito bestellen

    Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  6. Buch ; Online: Leveraging Angular Information Between Feature and Classifier for Long-tailed Learning

    Wang, Haoxuan / Yan, Junchi

    A Prediction Reformulation Approach

    2022  

    Abstract: Deep neural networks still struggle on long-tailed image datasets, and one of the reasons is that the imbalance of training data across categories leads to the imbalance of trained model parameters. Motivated by the empirical findings that trained ... ...

    Abstract Deep neural networks still struggle on long-tailed image datasets, and one of the reasons is that the imbalance of training data across categories leads to the imbalance of trained model parameters. Motivated by the empirical findings that trained classifiers yield larger weight norms in head classes, we propose to reformulate the recognition probabilities through included angles without re-balancing the classifier weights. Specifically, we calculate the angles between the data feature and the class-wise classifier weights to obtain angle-based prediction results. Inspired by the performance improvement of the predictive form reformulation and the outstanding performance of the widely used two-stage learning framework, we explore the different properties of this angular prediction and propose novel modules to improve the performance of different components in the framework. Our method is able to obtain the best performance among peer methods without pretraining on CIFAR10/100-LT and ImageNet-LT. Source code will be made publicly available.
    Schlagwörter Computer Science - Computer Vision and Pattern Recognition
    Thema/Rubrik (Code) 006
    Erscheinungsdatum 2022-12-03
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  7. Artikel ; Online: DIY Your EasyNAS for Vision: Convolution Operation Merging, Map Channel Reducing, and Search Space to Supernet Conversion Tooling.

    Wang, Xiaoxing / Lian, Zhirui / Lin, Jiale / Xue, Chao / Yan, Junchi

    IEEE transactions on pattern analysis and machine intelligence

    2023  Band 45, Heft 11, Seite(n) 13974–13990

    Abstract: Despite its popularity as a one-shot Neural Architecture Search (NAS) approach, the applicability of differentiable architecture search (DARTS) on complex vision tasks is still limited by the high computation and memory costs incurred by the over- ... ...

    Abstract Despite its popularity as a one-shot Neural Architecture Search (NAS) approach, the applicability of differentiable architecture search (DARTS) on complex vision tasks is still limited by the high computation and memory costs incurred by the over-parameterized supernet. We propose a new architecture search method called EasyNAS, whose memory and computational efficiency is achieved via our devised operator merging technique which shares and merges the weights of candidate convolution operations into a single convolution, and a dynamic channel refinement strategy. We also introduce a configurable search space-to-supernet conversion tool, leveraging the concept of atomic search components, to enable its application from classification to more complex vision tasks: detection and semantic segmentation. In classification, EasyNAS achieves state-of-the-art performance on the NAS-Bench-201 benchmark, attaining an impressive 76.2% accuracy on ImageNet. For detection, it achieves a mean average precision (mAP) of 40.1 with 120 frames per second (FPS) on MS-COCO test-dev. Additionally, we transfer the discovered architecture to the rotation detection task, where EasyNAS achieves a remarkable 77.05 mAP
    Sprache Englisch
    Erscheinungsdatum 2023-10-03
    Erscheinungsland United States
    Dokumenttyp Journal Article
    ISSN 1939-3539
    ISSN (online) 1939-3539
    DOI 10.1109/TPAMI.2023.3298296
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    Über subito bestellen

    Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  8. Artikel ; Online: Robust Mesh Representation Learning via Efficient Local Structure-Aware Anisotropic Convolution.

    Gao, Zhongpai / Yan, Junchi / Zhai, Guangtao / Zhang, Juyong / Yang, Xiaokang

    IEEE transactions on neural networks and learning systems

    2023  Band 34, Heft 11, Seite(n) 8566–8578

    Abstract: Mesh is a type of data structure commonly used for 3-D shapes. Representation learning for 3-D meshes is essential in many computer vision and graphics applications. The recent success of convolutional neural networks (CNNs) for structured data (e.g., ... ...

    Abstract Mesh is a type of data structure commonly used for 3-D shapes. Representation learning for 3-D meshes is essential in many computer vision and graphics applications. The recent success of convolutional neural networks (CNNs) for structured data (e.g., images) suggests the value of adapting insights from CNN for 3-D shapes. However, 3-D shape data are irregular since each node's neighbors are unordered. Various graph neural networks for 3-D shapes have been developed with isotropic filters or predefined local coordinate systems to overcome the node inconsistency on graphs. However, isotropic filters or predefined local coordinate systems limit the representation power. In this article, we propose a local structure-aware anisotropic convolutional operation (LSA-Conv) that learns adaptive weighting matrices for each template's node according to its neighboring structure and performs shared anisotropic filters. In fact, the learnable weighting matrix is similar to the attention matrix in the random synthesizer-a new Transformer model for natural language processing (NLP). Since the learnable weighting matrices require large amounts of parameters for high-resolution 3-D shapes, we introduce a matrix factorization technique to notably reduce the parameter size, denoted as LSA-small. Furthermore, a residual connection with a linear transformation is introduced to improve the performance of our LSA-Conv. Comprehensive experiments demonstrate that our model produces significant improvement in 3-D shape reconstruction compared to state-of-the-art methods.
    Sprache Englisch
    Erscheinungsdatum 2023-10-27
    Erscheinungsland United States
    Dokumenttyp Journal Article
    ISSN 2162-2388
    ISSN (online) 2162-2388
    DOI 10.1109/TNNLS.2022.3151609
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    Über subito bestellen

    Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  9. Buch ; Online: ViTree

    Lao, Danning / Liu, Qi / Bu, Jiazi / Yan, Junchi / Shen, Wei

    Single-path Neural Tree for Step-wise Interpretable Fine-grained Visual Categorization

    2024  

    Abstract: As computer vision continues to advance and finds widespread applications across various domains, the need for interpretability in deep learning models becomes paramount. Existing methods often resort to post-hoc techniques or prototypes to explain the ... ...

    Abstract As computer vision continues to advance and finds widespread applications across various domains, the need for interpretability in deep learning models becomes paramount. Existing methods often resort to post-hoc techniques or prototypes to explain the decision-making process, which can be indirect and lack intrinsic illustration. In this research, we introduce ViTree, a novel approach for fine-grained visual categorization that combines the popular vision transformer as a feature extraction backbone with neural decision trees. By traversing the tree paths, ViTree effectively selects patches from transformer-processed features to highlight informative local regions, thereby refining representations in a step-wise manner. Unlike previous tree-based models that rely on soft distributions or ensembles of paths, ViTree selects a single tree path, offering a clearer and simpler decision-making process. This patch and path selectivity enhances model interpretability of ViTree, enabling better insights into the model's inner workings. Remarkably, extensive experimentation validates that this streamlined approach surpasses various strong competitors and achieves state-of-the-art performance while maintaining exceptional interpretability which is proved by multi-perspective methods. Code can be found at https://github.com/SJTU-DeepVisionLab/ViTree.
    Schlagwörter Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Artificial Intelligence
    Thema/Rubrik (Code) 006
    Erscheinungsdatum 2024-01-30
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  10. Artikel ; Online: Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem With Extension to Hypergraph and Multiple-Graph Matching.

    Wang, Runzhong / Yan, Junchi / Yang, Xiaokang

    IEEE transactions on pattern analysis and machine intelligence

    2022  Band 44, Heft 9, Seite(n) 5261–5279

    Abstract: Graph matching involves combinatorial optimization based on edge-to-edge affinity matrix, which can be generally formulated as Lawler's quadratic assignment problem (QAP). This paper presents a QAP network directly learning with the affinity matrix ( ... ...

    Abstract Graph matching involves combinatorial optimization based on edge-to-edge affinity matrix, which can be generally formulated as Lawler's quadratic assignment problem (QAP). This paper presents a QAP network directly learning with the affinity matrix (equivalently the association graph) whereby the matching problem is translated into a constrained vertex classification task. The association graph is learned by an embedding network for vertex classification, followed by Sinkhorn normalization and a cross-entropy loss for end-to-end learning. We further improve the embedding model on association graph by introducing Sinkhorn based matching-aware constraint, as well as dummy nodes to deal with unequal sizes of graphs. To our best knowledge, this is one of the first network to directly learn with the general Lawler's QAP. In contrast, recent deep matching methods focus on the learning of node/edge features in two graphs respectively. We also show how to extend our network to hypergraph matching, and matching of multiple graphs. Experimental results on both synthetic graphs and real-world images show its effectiveness. For pure QAP tasks on synthetic data and QAPLIB benchmark, our method can perform competitively and even surpass state-of-the-art graph matching and QAP solvers with notable less time cost. We provide a project homepage at http://thinklab.sjtu.edu.cn/project/NGM/index.html.
    Sprache Englisch
    Erscheinungsdatum 2022-08-04
    Erscheinungsland United States
    Dokumenttyp Journal Article
    ISSN 1939-3539
    ISSN (online) 1939-3539
    DOI 10.1109/TPAMI.2021.3078053
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    Über subito bestellen

    Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Zum Seitenanfang