LIVIVO - Search results -

Search results

Result 1 - 10 of total 442

Search options

Article ; Online: TIB: Detecting Unknown Objects via Two-Stream Information Bottleneck.

Wu, Aming / Deng, Cheng

IEEE transactions on pattern analysis and machine intelligence

2023 Volume 46, Issue 1, Page(s) 611–625

Abstract: Detecting diverse objects, including ones never-seen-before during training, is critical for the safe application of object detectors. To this end, a task of unsupervised out-of-distribution object detection (OOD-OD) is proposed to detect unknown objects ...

Abstract	Detecting diverse objects, including ones never-seen-before during training, is critical for the safe application of object detectors. To this end, a task of unsupervised out-of-distribution object detection (OOD-OD) is proposed to detect unknown objects without the reliance on an auxiliary dataset. For this task, it is important to reduce the impact of lacking unknown data for supervision and leverage in-distribution (ID) data to improve the model's discrimination. In this paper, we propose a method of Two-Stream Information Bottleneck (TIB), consisting of a standard IB and a dedicated Reverse Information Bottleneck (RIB). Specifically, after extracting the features of an ID image, we first define a standard IB network to disentangle instance representations that are beneficial for localizing and recognizing objects. Meanwhile, we present RIB to obtain simulative OOD features to alleviate the impact of lacking unknown data. Different from standard IB aiming to extract task-relevant compact representations, RIB is to obtain task-irrelevant representations by reversing the optimization objective of the standard IB. Next, to further enhance the discrimination, a mixture of information bottlenecks is designed to sufficiently capture object-related information. Experimental results on OOD-OD, open-vocabulary object detection, incremental object detection, and open-set object detection show the superiorities of our method.
Language	English
Publishing date	2023-12-05
Publishing country	United States
Document type	Journal Article
ISSN	1939-3539
ISSN (online)	1939-3539
DOI	10.1109/TPAMI.2023.3323523
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Class-Incremental Unsupervised Domain Adaptation via Pseudo-Label Distillation.

Wei, Kun / Yang, Xu / Xu, Zhe / Deng, Cheng

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society

2024 Volume 33, Page(s) 1188–1198

Abstract: Class-Incremental Unsupervised Domain Adaptation (CI-UDA) requires the model can continually learn several steps containing unlabeled target domain samples, while the source-labeled dataset is available all the time. The key to tackling CI-UDA problem is ...

Abstract	Class-Incremental Unsupervised Domain Adaptation (CI-UDA) requires the model can continually learn several steps containing unlabeled target domain samples, while the source-labeled dataset is available all the time. The key to tackling CI-UDA problem is to transfer domain-invariant knowledge from the source domain to the target domain, and preserve the knowledge of the previous steps in the continual adaptation process. However, existing methods introduce much biased source knowledge for the current step, causing negative transfer and unsatisfying performance. To tackle these problems, we propose a novel CI-UDA method named Pseudo-Label Distillation Continual Adaptation (PLDCA). We design Pseudo-Label Distillation module to leverage the discriminative information of the target domain to filter the biased knowledge at the class- and instance-level. In addition, Contrastive Alignment is proposed to reduce domain discrepancy by aligning the class-level feature representation of the confident target samples and the source domain, and exploit the robust feature representation of the unconfident target samples at the instance-level. Extensive experiments demonstrate the effectiveness and superiority of PLDCA. Code is available at code.
Language	English
Publishing date	2024-02-09
Publishing country	United States
Document type	Journal Article
ISSN	1941-0042
ISSN (online)	1941-0042
DOI	10.1109/TIP.2024.3357258
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Unsupervised Out-of-Distribution Object Detection via PCA-Driven Dynamic Prototype Enhancement.

Wu, Aming / Deng, Cheng / Liu, Wei

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society

2024 Volume 33, Page(s) 2431–2446

Abstract: To promote the application of object detectors in real scenes, out-of-distribution object detection (OOD-OD) is proposed to distinguish whether detected objects belong to the ones that are unseen during training or not. One of the key challenges is that ... ...

Abstract	To promote the application of object detectors in real scenes, out-of-distribution object detection (OOD-OD) is proposed to distinguish whether detected objects belong to the ones that are unseen during training or not. One of the key challenges is that detectors lack unknown data for supervision, and as a result, can produce overconfident detection results on OOD data. Thus, this task requires to synthesize OOD data for training, which achieves the goal of enhancing the ability of localizing and discriminating OOD objects. In this paper, we propose a novel method, i.e., PCA-Driven dynamic prototype enhancement, to explore exploiting Principal Component Analysis (PCA) to extract simulative OOD data for training and obtain dynamic prototypes that are related to the current input and are helpful for boosting the discrimination ability. Concretely, the last few principal components of the backbone features are utilized to calculate an OOD map that involves plentiful information that deviates from the correlation distribution of the input. The OOD map is further used to extract simulative OOD data for training, which alleviates the impact of lacking unknown data. Besides, for in-distribution (ID) data, the category-level semantic information of objects between the backbone features and the high-level features should be kept consistent. To this end, we utilize the residual principal components to extract dynamic prototypes that reflect the semantic information of the current backbone features. Next, we define a contrastive loss to leverage these prototypes to enlarge the semantic gap between the simulative OOD data and the features from the residual principal components, which improves the ability of discriminating OOD objects. In the experiments, we separately verify our method on OOD-OD and incremental object detection. The significant performance gains demonstrate the superiorities of our method.
Language	English
Publishing date	2024-03-29
Publishing country	United States
Document type	Journal Article
ISSN	1941-0042
ISSN (online)	1941-0042
DOI	10.1109/TIP.2024.3378464
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Causality-Invariant Interactive Mining for Cross-Modal Similarity Learning.

Yan, Jiexi / Deng, Cheng / Huang, Heng / Liu, Wei

IEEE transactions on pattern analysis and machine intelligence

2024 Volume PP

Abstract: In the real world, how to effectively learn consistent similarity measurement across different modalities is essential. Most of the existing similarity learning methods cannot deal well with cross-modal data due to the modality gap and have obvious ... ...

Abstract	In the real world, how to effectively learn consistent similarity measurement across different modalities is essential. Most of the existing similarity learning methods cannot deal well with cross-modal data due to the modality gap and have obvious performance degeneration when applied to cross-modal data. To tackle this problem, we propose a novel cross-modal similarity learning method, called Causality-Invariant Interactive Mining (CIIM), that can effectively capture informative relationships among different samples and modalities to derive the modality-consistent feature embeddings in the unified metric space. Our CIIM tackles the modality gap from two aspects, i.e., sample-wise and feature-wise. Specifically, we start from the sample-wise view and learn the single-modality and hybrid-modality proxies for exploring the cross-modal similarity with the elaborate metric losses. In this way, sample-to-sample and sample-to-proxy correlations are both taken into consideration. Furthermore, we conduct the causal intervention to eliminate the modality bias and reconstruct the invariant causal embedding in the feature-wise aspect. To this end, we force the learned embeddings to satisfy the specific properties of our causal mechanism and derive the causality-invariant feature embeddings in the unified metric space. Extensive experiments on two cross-modality tasks demonstrate the superiority of our proposed method over the state-of-the-art methods.
Language	English
Publishing date	2024-03-21
Publishing country	United States
Document type	Journal Article
ISSN	1939-3539
ISSN (online)	1939-3539
DOI	10.1109/TPAMI.2024.3379752
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Asynchronous Parallel Large-Scale Gaussian Process Regression.

Dang, Zhiyuan / Gu, Bin / Deng, Cheng / Huang, Heng

IEEE transactions on neural networks and learning systems

2024 Volume PP

Abstract: Gaussian process regression (GPR) is an important nonparametric learning method in machine learning research with many real-world applications. It is well known that training large-scale GPR is a challenging task due to the required heavy computational ... ...

Abstract	Gaussian process regression (GPR) is an important nonparametric learning method in machine learning research with many real-world applications. It is well known that training large-scale GPR is a challenging task due to the required heavy computational cost and large volume memory. To address this challenging problem, in this article, we propose an asynchronous doubly stochastic gradient algorithm to handle the large-scale training of GPR. We formulate the GPR to a convex optimization problem, i.e., kernel ridge regression. After that, in order to efficiently solve this convex kernel problem, we first use the random feature mapping method to approximate the kernel model and then utilize two unbiased stochastic approximations, i.e., stochastic variance reduced gradient and stochastic coordinate descent, to update the solution asynchronously and in parallel. In this way, our algorithm scales well in both sample size and dimensionality, and speeds up the training computation. More importantly, we prove that our algorithm has a global linear convergence rate. Our experimental results on eight large-scale benchmark datasets with both regression and classification tasks show that the proposed algorithm outperforms the existing state-of-the-art GPR methods.
Language	English
Publishing date	2024-04-08
Publishing country	United States
Document type	Journal Article
ISSN	2162-2388
ISSN (online)	2162-2388
DOI	10.1109/TNNLS.2022.3200602
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Multi-Relational Deep Hashing for Cross-Modal Search.

Liang, Xiao / Yang, Erkun / Yang, Yanhua / Deng, Cheng

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society

2024 Volume 33, Page(s) 3009–3020

Abstract: Deep cross-modal hashing retrieval has recently made significant progress. However, existing methods generally learn hash functions with pairwise or triplet supervisions, which involves learning the relevant information by splicing partial similarity ... ...

Abstract	Deep cross-modal hashing retrieval has recently made significant progress. However, existing methods generally learn hash functions with pairwise or triplet supervisions, which involves learning the relevant information by splicing partial similarity between data pairs; notably, this approach only captures the data similarity locally and incompletely, resulting in sub-optimal retrieval performance. In this paper, we propose a novel Multi-Relational Deep Hashing (MRDH) approach, which can fully bridge the modality gap by comprehensively modeling the similarity relationship between data in different modalities. In more detail, to investigate the inter-modal relationships, we constrain the consistency of cross-modal pairwise similarities to maintain the semantic similarity across modalities. Moreover, to further capture complete similarity information, we design a new similarity metric, which we term cross-modal global similarity, by encouraging hash codes of similar data pairs from different modalities to approach a common center and hash codes for dissimilar pairs to converge to different centers. Adopting this approach enables our model to generate more discriminative hash codes. Extensive experiments on three benchmark datasets demonstrate the superiority of our method on cross-modal hashing retrieval.
Language	English
Publishing date	2024-04-25
Publishing country	United States
Document type	Journal Article
ISSN	1941-0042
ISSN (online)	1941-0042
DOI	10.1109/TIP.2024.3385656
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Global Model Selection via Solution Paths for Robust Support Vector Machine.

Zhai, Zhou / Gu, Bin / Deng, Cheng / Huang, Heng

IEEE transactions on pattern analysis and machine intelligence

2023 Volume PP

Abstract: Robust support vector machine (RSVM) using ramp loss provides a better generalization performance than traditional support vector machine (SVM) using hinge loss. However, the good performance of RSVM heavily depends on the proper values of regularization ...

Abstract	Robust support vector machine (RSVM) using ramp loss provides a better generalization performance than traditional support vector machine (SVM) using hinge loss. However, the good performance of RSVM heavily depends on the proper values of regularization parameter and ramp parameter. Traditional model selection technique with gird search has extremely high computational cost especially for fine-grained search. To address this challenging problem, in this paper, we first propose solution paths of RSVM (SPRSVM) based on the concave-convex procedure (CCCP) which can track the solutions of the non-convex RSVM with respect to regularization parameter and ramp parameter respectively. Specifically, we use incremental and decremental learning algorithms to deal with the Karush-Khun-Tucker violating samples in the process of tracking the solutions. Based on the solution paths of RSVM and the piecewise linearity of model function, we can compute the error paths of RSVM and find the values of regularization parameter and ramp parameter, respectively, which corresponds to the minimum cross validation error. We prove the finite convergence of SPRSVM and analyze the computational complexity of SPRSVM. Experimental results on a variety of benchmark datasets not only verify that our SPRSVM can globally search the regularization and ramp parameters respectively, but also show a huge reduction of computational time compared with the grid search approach.
Language	English
Publishing date	2023-12-25
Publishing country	United States
Document type	Journal Article
ISSN	1939-3539
ISSN (online)	1939-3539
DOI	10.1109/TPAMI.2023.3346765
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Deep Multiview Collaborative Clustering.

Yang, Xu / Deng, Cheng / Dang, Zhiyuan / Tao, Dacheng

IEEE transactions on neural networks and learning systems

2023 Volume 34, Issue 1, Page(s) 516–526

Abstract: The clustering methods have absorbed even-increasing attention in machine learning and computer vision communities in recent years. In this article, we focus on the real-world applications where a sample can be represented by multiple views. Traditional ... ...

Abstract	The clustering methods have absorbed even-increasing attention in machine learning and computer vision communities in recent years. In this article, we focus on the real-world applications where a sample can be represented by multiple views. Traditional methods learn a common latent space for multiview samples without considering the diversity of multiview representations and use K -means to obtain the final results, which are time and space consuming. On the contrary, we propose a novel end-to-end deep multiview clustering model with collaborative learning to predict the clustering results directly. Specifically, multiple autoencoder networks are utilized to embed multi-view data into various latent spaces and a heterogeneous graph learning module is employed to fuse the latent representations adaptively, which can learn specific weights for different views of each sample. In addition, intraview collaborative learning is framed to optimize each single-view clustering task and provide more discriminative latent representations. Simultaneously, interview collaborative learning is employed to obtain complementary information and promote consistent cluster structure for a better clustering solution. Experimental results on several datasets show that our method significantly outperforms several state-of-the-art clustering approaches.
Language	English
Publishing date	2023-01-05
Publishing country	United States
Document type	Journal Article
ISSN	2162-2388
ISSN (online)	2162-2388
DOI	10.1109/TNNLS.2021.3097748
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article: Intermittent spontaneous ovulation in patients with premature ovarian failure: Three case reports and review of literature.

Zhang, Wan-Yu / Wang, Han-Bi / Deng, Cheng-Yan

World journal of clinical cases

2023 Volume 11, Issue 31, Page(s) 7647–7655

Abstract: Background: Premature ovarian failure (POF) is the end-stage of a decline in ovarian function prior to the age of 40 years that involves symptoms associated with low estradiol (E: Case summary: Here, we report three cases (29, 22, and 33 years-of-age) ...

Abstract	Background: Premature ovarian failure (POF) is the end-stage of a decline in ovarian function prior to the age of 40 years that involves symptoms associated with low estradiol (E Case summary: Here, we report three cases (29, 22, and 33 years-of-age) diagnosed with POF after experiencing secondary amenorrhea for more than one year, serum levels of follicle-stimulating hormone (FSH) > 40 IU/L on two occasions with an interval of more than 4 wk, and negative progesterone withdrawal tests. All three patients were intermittently administered with drugs to create an artificial cycle. During the subsequent discontinuation period, the patients experienced intermittent follicular growth and spontaneous ovulation. One patient experienced two natural pregnancies (both with embryo arrest). Conclusion: Our findings suggest that young patients with POF can experience unpredictable and intermittent spontaneous follicular development, ovulation, and even natural pregnancy. Clinicians should provide appropriate medical guidance and individualized treatments according to fertility requirements, genetic risks and hypoestrogenic symptoms as soon as possible.
Language	English
Publishing date	2023-11-23
Publishing country	United States
Document type	Case Reports
ISSN	2307-8960
ISSN	2307-8960
DOI	10.12998/wjcc.v11.i31.7647
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Group Contrastive Self-Supervised Learning on Graphs.

Xu, Xinyi / Deng, Cheng / Xie, Yaochen / Ji, Shuiwang

IEEE transactions on pattern analysis and machine intelligence

2023 Volume 45, Issue 3, Page(s) 3169–3180

Abstract: We study self-supervised learning on graphs using contrastive methods. A general scheme of prior methods is to optimize two-view representations of input graphs. In many studies, a single graph-level representation is computed as one of the contrastive ... ...

Abstract	We study self-supervised learning on graphs using contrastive methods. A general scheme of prior methods is to optimize two-view representations of input graphs. In many studies, a single graph-level representation is computed as one of the contrastive objectives, capturing limited characteristics of graphs. We argue that contrasting graphs in multiple subspaces enables graph encoders to capture more abundant characteristics. To this end, we propose a group contrastive learning framework in this work. Our framework embeds the given graph into multiple subspaces, of which each representation is prompted to encode specific characteristics of graphs. To learn diverse and informative representations, we develop principled objectives that enable us to capture the relations among both intra-space and inter-space representations in groups. Under the proposed framework, we further develop an attention-based group generator to compute representations that capture different substructures of a given graph. Built upon our framework, we extend two current methods into GroupCL and GroupIG, equipped with the proposed objective. Comprehensive experimental results show our framework achieves a promising boost in performance on a variety of datasets. In addition, our qualitative results show that features generated from our representor successfully capture various specific characteristics of graphs.
Language	English
Publishing date	2023-02-03
Publishing country	United States
Document type	Journal Article
ISSN	1939-3539
ISSN (online)	1939-3539
DOI	10.1109/TPAMI.2022.3177295
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED