This is achieved from a strategy that relies on auxiliary tasks based on distribution alignment and domain classification, in addition to a residual feature fusion procedure.
Next, we distill the knowledge from the teacher TVUS POD obliteration detector to train the student MRI model by minimizing a regression loss that approximates the output of the student to the teacher using unpaired TVUS and MRI data.
In this work, we propose a new strategy to build cost-effective and relatively unbiased audio-visual semantic segmentation benchmarks.
When analysing screening mammograms, radiologists can naturally process information across two ipsilateral views of each breast, namely the cranio-caudal (CC) and mediolateral-oblique (MLO) views.
To achieve this, we propose Multi-modal Models Membership Inference (M^4I) with two attack methods to infer the membership status, named metric-based (MB) M^4I and feature-based (FB) M^4I, respectively.
One effective way is to encode document positional information to assist models in capturing cross-document relations.
Recently, with the rise of high dynamic range (HDR) display devices, there is a great demand to transfer traditional low dynamic range (LDR) images into HDR versions.
Multi-modal learning focuses on training models by equally combining multiple input data modalities during the prediction process.
Deep learning methods have shown outstanding classification accuracy in medical imaging problems, which is largely attributed to the availability of large-scale datasets manually annotated with clean labels.
We design a system for risk-analyzing and pricing portfolios of non-performing consumer credit loans.
In this work, we develop a neural network based model which leverages dependency parsing to capture cross-positional dependencies and grammatical structures.
The advancement of secure communication and identity verification fields has significantly increased through the use of deep learning techniques for data hiding.
With this key observation, we protect data privacy and allow the disclosure of feature meaning by concealing decision paths and adapt a communication-efficient secure computation method for inference outputs.
Current deep image super-resolution (SR) approaches attempt to restore high-resolution images from down-sampled images or by assuming degradation from simple Gaussian kernels and additive noises.
Deep Neural Networks have achieved unprecedented success in the field of face recognition such that any individual can crawl the data of others from the Internet without their explicit permission for the purpose of training high-precision face recognition models, creating a serious violation of privacy.
Therefore, a purify-trained classifier is designed to obtain the distribution and generate the calibrated rewards.
To address these issues, in this work we carefully design our settings and propose a new dataset including both synthetic and real traffic data in more complex scenarios.
With the rising popularity of intelligent mobile devices, it is of great practical significance to develop accurate, realtime and energy-efficient image Super-Resolution (SR) inference methods.
In deep data hiding models, to maximize the encoding capacity, each pixel of the cover image ought to be treated differently since they have different sensitivities w. r. t.
Multi-document summarization (MDS) is an effective tool for information aggregation that generates an informative and concise summary from a cluster of topic-related documents.
The experimental results on synthetic data and real-world data show the ROCP algorithm is able to cope with CP decomposition for large-scale tensors with arbitrary number of dimensions.
Automated disease classification of radiology images has been emerging as a promising technique to support clinical diagnosis and treatment planning.
In this paper, we introduce a Soft Expert Reward Learning (SERL) model to overcome the reward engineering designing and generalisation problems of the VLN task.
To enable unsupervised learning on those domains, in this work we propose to learn features without using any labelled data by training neural networks to predict data distances in a randomly projected space.
To achieve the aim of searching the feasible solutions accurately, an adaptive population size method and an adaptive mutation strategy are proposed in the paper.
In such a framework, a reconstruction neural network (ReConNN) model designed for simulation-based physical field's reconstruction is proposed.
The complexity of neural networks can be reduced since long-term dependencies are not modeled with neural connections, and thus the amount of data needed to optimize the neural networks can be reduced.
In order to evaluate the proposed CNN metamodel for hundreds-dimensional and strong nonlinear problems, CNN is compared with other metamodeling techniques.