Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleMay 2024
Flow factorized representation learning
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsArticle No.: 2166, Pages 49761–49782A prominent goal of representation learning research is to achieve representations which are factorized in a useful manner with respect to the ground truth factors of variation. The fields of disentangled and equivariant representation learning have ...
- research-articleFebruary 2024
High-precision target ranging in complex orchard scenes by utilizing semantic segmentation results and binocular vision
Computers and Electronics in Agriculture (COEA), Volume 215, Issue Chttps://doi.org/10.1016/j.compag.2023.108440Highlights- Constructing a high-quality dataset for complex orchard scenes.
- Proposing a multi-scale feature fusion Segformer semantic segmentation network.
- Introducing a novel method to obtain accurate depth information of the targets.
- ...
The automation of orchard production is increasingly relying on robotics, driven by the advancements in artificial intelligence technology. However, accurately comprehending semantic information and precisely locating various targets within ...
- ArticleJanuary 2024
Small-Sample Coal-Rock Recognition Model Based on MFSC and Siamese Neural Network
AbstractGiven the advantages of deep learning in feature extraction and learning ability, it has been used in coal-rock recognition. Deep learning techniques rely on a large number of independent identically distributed samples. However, the complexity ...
- research-articleJuly 2023
Latent traversals in generative models as potential flows
ICML'23: Proceedings of the 40th International Conference on Machine LearningArticle No.: 1338, Pages 32288–32303Despite the significant recent progress in deep generative models, the underlying structure of their latent spaces is still poorly understood, thereby making the task of performing semantically meaningful latent traversals an open research challenge. Most ...
- research-articleJuly 2023
Orthogonal SVD Covariance Conditioning and Latent Disentanglement
IEEE Transactions on Pattern Analysis and Machine Intelligence (ITPM), Volume 45, Issue 7Pages 8773–8786https://doi.org/10.1109/TPAMI.2022.3228979Inserting an SVD meta-layer into neural networks is prone to make the covariance ill-conditioned, which could harm the model in the training stability and generalization abilities. In this article, we systematically study how to improve the covariance ...
-
- research-articleJune 2023
Fast Differentiable Matrix Square Root and Inverse Square Root
IEEE Transactions on Pattern Analysis and Machine Intelligence (ITPM), Volume 45, Issue 6Pages 7367–7380https://doi.org/10.1109/TPAMI.2022.3216339Computing the matrix square root and its inverse in a differentiable manner is important in a variety of computer vision tasks. Previous methods either adopt the Singular Value Decomposition (SVD) to explicitly factorize the matrix or use the Newton-...
- research-articleJanuary 2023
Disentangle Saliency Detection into Cascaded Detail Modeling and Body Filling
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Volume 19, Issue 1Article No.: 7, Pages 1–15https://doi.org/10.1145/3513134Salient object detection has been long studied to identify the most visually attractive objects in images/videos. Recently, a growing amount of approaches have been proposed, all of which rely on the contour/edge information to improve detection ...
- research-articleDecember 2022
Automatic gear shift strategy for manual transmission of mine truck based on Bi-LSTM network
Expert Systems with Applications: An International Journal (EXWA), Volume 209, Issue Chttps://doi.org/10.1016/j.eswa.2022.118197Highlights- Gear shift strategy.
- Mine truck.
As mine trucks face severe and changeable driving conditions in mining area, it is important to formulate a general automatic gear shift strategy for reducing the intensity and difficulty of the work. Therefore, gear shift strategy ...
- research-articleApril 2024
GBA: a tuning-free approach to switch between synchronous and asynchronous training for recommendation models
- Wenbo Su,
- Yuanxing Zhang,
- Yufeng Cai,
- Kaixu Ren,
- Pengjie Wang,
- Huimin Yi,
- Yue Song,
- Jing Chen,
- Hongbo Deng,
- Jian Xu,
- Lin Qu,
- Bo Zheng
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsArticle No.: 2141, Pages 29525–29537High-concurrency asynchronous training upon parameter server (PS) architecture and high-performance synchronous training upon all-reduce (AR) architecture are the most commonly deployed distributed training modes for recommendation models. Although ...
- research-articleApril 2024
RankFeat: rank-1 feature removal for out-of-distribution detection
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsArticle No.: 1300, Pages 17885–17898The task of out-of-distribution (OOD) detection is crucial for deploying machine learning models in real-world settings. In this paper, we observe that the singular value distributions of the in-distribution (ID) and OOD features are quite different: the ...
- ArticleOctober 2022
Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality
AbstractInserting an SVD meta-layer into neural networks is prone to make the covariance ill-conditioned, which could harm the model in the training stability and generalization abilities. In this paper, we systematically study how to improve the ...
- ArticleOctober 2022
- research-articleMay 2022
Anomaly Detection in Spacecraft Telemetry Data using Graph Convolution Networks
2022 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)Pages 1–6https://doi.org/10.1109/I2MTC48687.2022.9806645Telemetry data anomaly detection is of great significance to guarantee the safe operation of spacecraft. However, the high dimensionality of telemetry variables and the strong correlation between variables pose a great challenge to multivariate anomaly ...
- research-articleApril 2022
Kernel-based fuzzy local information clustering algorithm self-integrating non-local information
AbstractThe application of fuzzy clustering in image segmentation is a research hotspot nowadays. Existing robust fuzzy clustering have some problems such as the inability to adaptively select spatial constraint parameters, the inability to ...
- research-articleApril 2022
A novel self-learning weighted fuzzy local information clustering algorithm integrating local and non-local spatial information for noise image segmentation
Applied Intelligence (KLU-APIN), Volume 52, Issue 6Pages 6376–6397https://doi.org/10.1007/s10489-021-02722-7AbstractFuzzy clustering algorithm (FCM) can be directly used to segment images, it takes no account of the neighborhood information of the current pixel and does not have a robust segmentation noise suppression. Fuzzy Local Information C-means Clustering ...
- research-articleJanuary 2022
Analysis of Topological Aspects for Metal-Insulator Transition Superlattice Network
In this research work, we have explored the physical and topological properties of the crystal structure of metal-insulator transition superlattice (GST-SL). In recent times, two-dimensional substantial have enamored comprehensive considerations owing to ...
- research-articleJanuary 2022
Distributed Sliding Mode Fault-Tolerant LFC for Multiarea Interconnected Power Systems under Sensor Fault
This paper focuses on the problem of load frequency control and sensor fault-tolerant control in the multiarea power grid. To solve these problems, a sliding mode control strategy based on an interval observer is designed. First, an interval observer is ...
- research-articleJanuary 2022
Event-Based State Estimation for Networked Singularly Perturbed Complex Networks
This paper deals with the multievent-triggering-based state estimation for a class of discrete-time networked singularly perturbed complex networks (SPCNs). A small singularly perturbed scalar is adopted to establish a discrete-time SPCNs model. To reduce ...
- review-articleJanuary 2022
Self-Organization in Network Sociotechnical Systems
We can observe self-organization properties in various systems. However, modern networked dynamical sociotechnical systems have some features that allow for realizing the benefits of self-organization in a wide range of systems in economic and social ...
- research-articleJanuary 2022
Distance-Based Topological Descriptors on Ternary Hypertree Networks
- Yue Song,
- Yun Yu,
- D. Antony Xavier,
- Eddith Sarah Varghese,
- Deepa Mathew,
- Muhammad Kamran Siddiqui,
- Samuel Asefa Fufa
Topological indices are numeric parameters which portray the topology of a subatomic structure. In QSAR/QSPR analysis, topological descriptors play a vital role to examine the topology of a network. An interconnection network is a structure whose ...