For user representation, we utilize a series of historical navigation to extract user preference.
In this paper, we propose a novel method for both detection and classification that explicitly incorporates spatial contextual information.
Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and imbalanced.
It is, thus, different from the recently appeared nonlinear system phase which adopts the complexification of real-valued signals using the Hilbert transform.
The layers of convolutional neural networks (CNNs) can be used to alter the resolution of their inputs, but the scaling factors are limited to integer values.
Characterization of breast parenchyma on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a challenging task owing to the complexity of underlying tissue structures.
This survey presents the most recent findings of privacy attacks and defenses appeared in cloud-based neural network services.
Next, multi-level structural constraints are used to improve the perception of lanes.
Ranked #6 on Lane Detection on CULane
In collaborative filtering (CF) algorithms, the optimal models are usually learned by globally minimizing the empirical risks averaged over all the observed data.
In this work, we present a deep learning based approach for contrast-enhanced T1 synthesis on brain tumor patients.
In the segmentation of fine-scale structures from natural and biomedical images, per-pixel accuracy is not the only metric of concern.
Label noise is frequently observed in real-world large-scale datasets.
Ranked #2 on Learning with noisy labels on ANIMAL
The information produced by beacons in multiple processes is aggregated and analyzed by the proactive scheduler to respond to the anticipated workload requirements.
Distributed, Parallel, and Cluster Computing
Stealing attack against controlled information, along with the increasing number of information leakage incidents, has become an emerging cyber security threat in recent years.
This raises the question: is the stability analysis of  tight for smooth functions, and if not, for what kind of loss functions and data distributions can the stability analysis be improved?
A federatedGAN jointly trains a centralized generator and multiple private discriminators hosted at different sites.
We provide empirical evidence that this condition holds for several loss functions, and provide theoretical evidence that the known tight SGD stability bounds for convex and non-convex loss functions can be circumvented by HC loss functions, thus partially explaining the generalization of deep neural networks.
We propose a novel GNN defense algorithm against structural attacks that maliciously modify graph topology.
Our method pushes the neural network to generate a 3D point cloud whose 2D projections match the irregular point supervision from different view angles.
Due to various challenges, a localization method is prone to spatial semantic errors, i. e., predicting multiple dots within a same person or collapsing multiple dots in a cluttered region.
To be robust against label noise, many successful methods rely on the noisy classifiers (i. e., models trained on the noisy training data) to determine whether a label is trustworthy.
Ranked #26 on Image Classification on Clothing1M
We introduce a randomized algorithm, namely RCHOL, to construct an approximate Cholesky factorization for a given Laplacian matrix (a. k. a., graph Laplacian).
Numerical Analysis Mathematical Software Numerical Analysis
It is shown that in our application, the new Automating-the-Loop method greatly reduces the labeling effort while producing comparable performance to both human-in-the-loop and complete manual labeling methods.
DeepLabv3 outperforms the other models at Binary accuracy, Mean IoU and Boundary F1 score, but is surpassed by Pix2Pix (without discriminator) and U-Net in Occluded branch recall.
Specifically, we propose a variational relaxation of instance segmentation as minimizing an optimization functional for a piecewise-constant segmentation problem, which can be used to train an FCN end-to-end.
This paper proposes a strategy named IHMs (Intermediate Searching at Heuristic Moments): each step we figure out which moment is the best to search according to a heuristic indicator, then at that moment search locations one by one in descending order of predicted appearing probabilities, until a search hits; iterate this step until we get the object's current location.
Our proposed method tackles the challenge of training GAN in the federated learning manner: How to update the generator with a flow of temporary discriminators?
To optimize 3D shape parameters, current renderers rely on pixel-wise losses between rendered images of 3D reconstructions and ground truth images from corresponding viewpoints.
Respiratory symptoms can be a caused by different underlying conditions, and are often caused by viral infections, such as Influenza-like illnesses or other emerging viruses like the Coronavirus.
To illustrate the importance of prior knowledge, the result of the algorithm without prior knowledge is also investigated.
However, training with the global image underutilizes discriminative local information, while providing extra annotations is expensive and subjective.
In this paper, we propose a data privacy-preserving and communication efficient distributed GAN learning framework named Distributed Asynchronized Discriminator GAN (AsynDGAN).
There is no existing method to rigorously attribute the inference outcomes to the contributing factors of the graphical models.
In this research, a fully neural network based visual perception framework for autonomous apple harvesting is proposed.
This paper develops a framework of visual perception and modelling for robotic harvesting of fruits in the orchard environments.
In particular, our proposed HoMM can perform arbitrary-order moment tensor matching, we show that the first-order HoMM is equivalent to Maximum Mean Discrepancy (MMD) and the second-order HoMM is equivalent to Correlation Alignment (CORAL).
The robustness and efficiency of the DaSNet-V2 in detection and segmentation are validated by the experiments in the real-environment of apple orchard.
The spatial layout of the beams is regular, and this allows the beam features to be further fed into an efficient 2D convolutional neural network (CNN) for hierarchical feature aggregation.
In this paper, we propose a novel Semi-supervised Self-pace Adversarial Hashing method, named SSAH to solve the above problems in a unified framework.
In this paper, we propose a system framework consisting of UEs clustering, UAV-BS placement, UEs trajectories prediction, and UAV-BS reposition matching scheme, to serve the UEs seamlessly as well as minimize the energy cost of UAV-BSs' reposition trajectories.
A generic model for CrowdMining is further proposed based on a set of existing studies.
Specifically, ShapeCaptioner aggregates the parts detected in multiple colored views using our novel part class specific aggregation to represent a 3D shape, and then, employs a sequence to sequence model to generate the caption.
This allows for a much larger training set, that reflects visual variability across multiple cancer types and thus training of a single network which can be automatically applied to each cancer type without human adjustment.
In this paper, we pursue very efficient neural network modules which can significantly boost the learning power of deep convolutional neural networks with negligible extra computational cost.
Current neural networks for 3D object recognition are vulnerable to 3D rotation.
However, since the domain shift between source and target domains, only using the deep features for sample selection is defective.
Ranked #4 on Partial Domain Adaptation on Office-31
Most work on automated deception detection (ADD) in video has two restrictions: (i) it focuses on a video of one person, and (ii) it focuses on a single act of deception in a one or two minute video.
no code implementations • 3 May 2019 • Xiong Deng, Chao Chen, Deyang Chen, Xiangbin Cai, Xiaozhe Yin, Chao Xu, Fei Sun, Caiwen Li, Yan Li, Han Xu, Mao Ye, Guo Tian, Zhen Fan, Zhipeng Hou, Minghui Qin, Yu Chen, Zhenlin Luo, Xubing Lu, Guofu Zhou, Lang Chen, Ning Wang, Ye Zhu, Xingsen Gao, Jun-Ming Liu
The limitation of commercially available single-crystal substrates and the lack of continuous strain tunability preclude the ability to take full advantage of strain engineering for further exploring novel properties and exhaustively studying fundamental physics in complex oxides.
Recent advances in unsupervised domain adaptation mainly focus on learning shared representations by global distribution alignment without considering class information across domains.
We introduce a parallel method that provably requires $O(N)$ operations to reduce the computation cost.
We evaluate the algorithm on some large problems show it exhibits near-linear scaling.
Three-dimensional object recognition has recently achieved great progress thanks to the development of effective point cloud-based learning frameworks, such as PointNet and its extensions.
Change detection has been a challenging visual task due to the dynamic nature of real-world scenes.
Collaborative filtering (CF) is a popular technique in today's recommender systems, and matrix approximation-based CF methods have achieved great success in both rating prediction and top-N recommendation tasks.
Unlike the existing parameter transfer approaches, which incorporate the source model information into the target by regularizing the di erence between the source and target domain parameters, an intuitively appealing projective-model is proposed to bridge the source and target model parameters.
Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities.
In particular, our measurement of topological complexity incorporates the importance of topological features (e. g., connected components, handles, and so on) in a meaningful manner, and provides a direct control over spurious topological structures.
In this study, we propose an approximate estimation of the weights uncertainty using Ensemble Kalman Filter, which is easily scalable to a large number of weights.
However, our studies show that submatrices with different ranks could coexist in the same user-item rating matrix, so that approximations with fixed ranks cannot perfectly describe the internal structures of the rating matrix, therefore leading to inferior recommendation accuracy.
Ranked #4 on Recommendation Systems on MovieLens 10M
The Multiple Instance Hybrid Estimator for discriminative target characterization from imprecisely labeled hyperspectral data is presented.
Though the mode finding problem is generally intractable in high dimensions, this paper unveils that, if the distribution can be approximated well by a tree graphical model, mode characterization is significantly easier.