Search Results for author:
Found 20 papers, 4 papers with code
PFGE: Parsimonious Fast Geometric Ensembling of DNNs
Ensemble methods have been widely used to improve the performance of machine learning methods in terms of generalization, while they are hard to use in deep learning systems, as training an ensemble of deep neural networks (DNNs) incurs an extremely higher computational overhead of model training.
Stochastic Weight Averaging Revisited
Based on our experimental findings, we raise a hypothesis that there are global scale geometric structures in the DNN loss landscape that can be discovered by an SGD agent at the early stage of its working period, and such global geometric structures can be exploited by the WA operation.
Fully Attentional Network for Semantic Segmentation
Recent non-local self-attention methods have proven to be effective in capturing long-range dependencies for semantic segmentation.
Denoised Non-Local Neural Network for Semantic Segmentation
Without any external training data, our proposed Denoised NL can achieve the state-of-the-art performance of 83. 5\% and 46. 69\% mIoU on Cityscapes and ADE20K, respectively.
LSENet: Location and Seasonality Enhanced Network for Multi-Class Ocean Front Detection
Ocean fronts can cause the accumulation of nutrients and affect the propagation of underwater sound, so high-precision ocean front detection is of great significance to the marine fishery and national defense fields.
Long-Tailed Multi-Label Visual Recognition by Collaborative Training on Uniform and Re-Balanced Samplings
While re-balanced data sampling can improve the performance on tail classes, it may also hurt the performance on head classes in training due to label co-occurrence.
Multi-modal Entity Alignment in Hyperbolic Space
To mitigate this problem, a viable approach is to integrate complementary knowledge from other MMKGs.
Multi-Level Attentive Convoluntional Neural Network for Crowd Counting
Recently the crowd counting has received more and more attention.
DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation
We further design a re-weighting strategy to handle the inaccuracy caused by misalignment between day-night image pairs and wrong predictions of daytime images, as well as boost the prediction accuracy of small objects.
Ranked #2 on
Semantic Segmentation
on Nighttime Driving
Continuous Prediction of Lower-Limb Kinematics From Multi-Modal Biomedical Signals
Challenges of exoskeletons motor intent decoding schemes remain in making a continuous prediction to compensate for the hysteretic response caused by mechanical transmission.
Generating Informative CVE Description From ExploitDB Posts by Extractive Summarization
The extracted aspects from an ExploitDB post are then composed into a CVE description according to the suggested CVE description templates, which is must-provided information for requesting new CVEs.
Predictor Antenna: A Technique to Boost the Performance of Moving Relays
In future wireless systems, a large number of users may access the networks via moving relays (MRs) installed on top of vehicles.
Information Theory Signal Processing Information Theory
Predictor Antennas for Moving Relays: Finite Block-length Analysis
We use the fundamental results on the achievable rate of finite block-length codes to study the system throughput and error probability in the presence of short packets.
Information Theory Signal Processing Information Theory
A Hierarchical User Intention-Habit Extract Network for Credit Loan Overdue Risk Detection
In this paper, we propose a model named HUIHEN (Hierarchical User Intention-Habit Extract Network) that leverages the users' behavior information in mobile banking APP.
Thermostatistics of a q-deformed Relativistic Ideal Fermi Gas
In this paper, we formulate a q-deformed many-body theory for the relativistic Fermi gas and discuss the effects of the deformation parameter q on physical properties of such systems.
High Energy Physics - Theory High Energy Physics - Phenomenology
Deep Poisoning: Towards Robust Image Data Sharing against Visual Disclosure
Due to respectively limited training data, different entities addressing the same vision task based on certain sensitive images may not train a robust deep network.
Visual Attention Consistency Under Image Transforms for Multi-Label Image Classification
In this paper, we further propose the assumption of perceptual consistency of visual attention regions for classification under such transforms, i. e., the attention region for a classification follows the same transform if the input image is spatially transformed.
Automatic Identification of Indicators of Compromise using Neural-Based Sequence Labelling
In this paper, we propose using a neural-based sequence labelling model to identify IOCs automatically from reports on cybersecurity without expert knowledge of cybersecurity.
Object Detection with Mask-based Feature Encoding
In particular, we design a Mask Weight Network (MWN) to learn a set of masks and then apply channel-wise masking operations to ROI feature map, followed by a global pooling and a cheap fully-connected layer.
Learning View-Invariant Features for Person Identification in Temporally Synchronized Videos Taken by Wearable Cameras
In this paper, we attempt to utilize 3D human-skeleton sequences to learn a model that can extract view-invariant motion features from optical flows in different views.
