Search Results for author:
Found 27 papers, 15 papers with code
BALANCE: Bayesian Linear Attribution for Root Cause Localization
In particular, we propose BALANCE (BAyesian Linear AttributioN for root CausE localization), which formulates the problem of RCA through the lens of attribution in XAI and seeks to explain the anomalies in the target KPIs by the behavior of the candidate root causes.
Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting
In this paper, we propose Regularized Graph Structure Learning (RGSL) model to incorporate both explicit prior structure and implicit structure together, and learn the forecasting deep networks along with the graph structure.
A Meta Reinforcement Learning Approach for Predictive Autoscaling in the Cloud
Predictive autoscaling (autoscaling with workload forecasting) is an important mechanism that supports autonomous adjustment of computing resources in accordance with fluctuating workload demands in the Cloud.
Heterogeneous Ultra-Dense Networks with Traffic Hotspots: A Unified Handover Analysis
By combining the PCP and MRWP model, the distributions of distances from a typical terminal to the BSs in different tiers are derived.
Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting
Accurate prediction of the future given the past based on time series data is of paramount importance, since it opens the door for decision making and risk management ahead of time.
Variational Pedestrian Detection
Pedestrian detection in a crowd is a challenging task due to a high number of mutually-occluding human instances, which brings ambiguity and optimization difficulties to the current IoU-based ground truth assignment procedure in classical object detection methods.
Extreme Value Preserving Networks
Recent evidence shows that convolutional neural networks (CNNs) are biased towards textures so that CNNs are non-robust to adversarial perturbations over textures, while traditional robust visual features like SIFT (scale-invariant feature transforms) are designed to be robust across a substantial range of affine distortion, addition of noise, etc with the mimic of human perception nature.
AP-Loss for Accurate One-Stage Object Detection
This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the Average-Precision loss (AP-loss) for the ranking problem.
Extreme Values are Accurate and Robust in Deep Networks
Recent evidence shows that convolutional neural networks (CNNs) are biased towards textures so that CNNs are non-robust to adversarial perturbations over textures, while traditional robust visual features like SIFT (scale-invariant feature transforms) are designed to be robust across a substantial range of affine distortion, addition of noise, etc with the mimic of human perception nature.
ATRW: A Benchmark for Amur Tiger Re-identification in the Wild
This paper tries to fill the gap by introducing a novel large-scale dataset, the Amur Tiger Re-identification in the Wild (ATRW) dataset.
Towards Accurate One-Stage Object Detection with AP-Loss
For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks.
Few Sample Knowledge Distillation for Efficient Network Compression
Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high.
Composite Binary Decomposition Networks
Binary neural networks have great resource and computing efficiency, while suffer from long training procedure and non-negligible accuracy drops, when comparing to the full-precision counterparts.
Knowledge Distillation from Few Samples
Taking the assumption that both "teacher" and "student" have the same feature map sizes at each corresponding block, we add a $1\times 1$ conv-layer at the end of each block in the student-net, and align the block-level outputs between "teacher" and "student" by estimating the parameters of the added layer with limited samples.
Object Detection from Scratch with Deep Supervision
Thus, a better solution to handle these critical problems is to train object detectors from scratch, which motivates our proposed method.
Network Decoupling: From Regular to Depthwise Separable Convolutions
Depthwise separable convolution has shown great efficiency in network design, but requires time-consuming training procedure with full training-set available.
Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
Based on the deeply supervised object detection (DSOD) framework, we propose Tiny-DSOD dedicating to resource-restricted usages.
Learning Visual Knowledge Memory Networks for Visual Question Answering
Second is the mechanism for handling multiple knowledge facts expanding from question and answer pairs.
Boosting Adversarial Attacks with Momentum
To further improve the success rates for black-box attacks, we apply momentum iterative algorithms to an ensemble of models, and show that the adversarially trained models with a strong defense ability are also vulnerable to our black-box attacks.
BodyFusion: Real-Time Capture of Human Motion and Surface Geometry Using a Single Depth Camera
To reduce the ambiguities of the non-rigid deformation parameterization on the surface graph nodes, we take advantage of the internal articulated motion prior for human performance and contribute a skeleton-embedded surface fusion (SSF) method.
Learning Efficient Convolutional Networks through Network Slimming
For VGGNet, a multi-pass version of network slimming gives a 20x reduction in model size and a 5x reduction in computing operations.
Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization
This procedure can greatly compensate the quantization error and thus yield better accuracy for low-bit DNNs.
DSOD: Learning Deeply Supervised Object Detectors from Scratch
State-of-the-art object objectors rely heavily on the off-the-shelf networks pre-trained on large-scale classification datasets like ImageNet, which incurs learning bias due to the difference on both the loss functions and the category distributions between classification and detection tasks.
Weakly Supervised Dense Video Captioning
This paper focuses on a novel and challenging vision task, dense video captioning, which aims to automatically describe a video clip with multiple informative and diverse caption sentences.
Deep Attributes from Context-Aware Regional Neural Codes
Results show that deep attribute approaches achieve state-of-the-art results, and outperforms existing peer methods with a significant margin, even though some benchmarks have little overlap of concepts with the pre-trained CNN models.
Large-scale Supervised Hierarchical Feature Learning for Face Recognition
Second, the face image is further represented by patches of picked channels, and we search from the over-complete patch pool to activate only those most discriminant patches.
Learning SURF Cascade for Fast and Accurate Object Detection
Third, we adopt AUC as a single criterion for the convergence test during cascade training rather than the two trade-off criteria (false-positive-rate and hit-rate) in the VJ framework.
