Search Results for author:
Found 10 papers, 6 papers with code
Binarized Weight Error Networks With a Transition Regularization Term
In addition, a novel regularization term is introduced that is suitable for all threshold-based binary precision networks.
Spectral Unmixing With Multinomial Mixture Kernel and Wasserstein Generative Adversarial Loss
This study proposes a novel framework for spectral unmixing by using 1D convolution kernels and spectral uncertainty.
Cross-Domain Segmentation with Adversarial Loss and Covariate Shift for Biomedical Imaging
Despite the widespread use of deep learning methods for semantic segmentation of images that are acquired from a single source, clinicians often use multi-domain data for a detailed analysis.
Automatic Liver Segmentation with Adversarial Loss and Convolutional Neural Network
Automatic segmentation of medical images is among most demanded works in the medical information field since it saves time of the experts in the field and avoids human error factors.
Improved Deep Spectral Convolution Network For Hyperspectral Unmixing With Multinomial Mixture Kernel and Endmember Uncertainty
The results validate that the proposed method obtains state-of-the-art hyperspectral unmixing performance particularly on the real datasets compared to the baseline techniques.
Exploiting Local Indexing and Deep Feature Confidence Scores for Fast Image-to-Video Search
The cost-effective visual representation and fast query-by-example search are two challenging goals that should be maintained for web-scale visual retrieval tasks on moderate hardware.
Convolutional Neural Networks Analyzed via Inverse Problem Theory and Sparse Representations
We discuss the necessity of mutual coherence between CNN layer elements in order for a network to converge to the optimum solution.
Deep Spectral Convolution Network for HyperSpectral Unmixing
In this paper, we propose a novel hyperspectral unmixing technique based on deep spectral convolution networks (DSCN).
Relaxed Spatio-Temporal Deep Feature Aggregation for Real-Fake Expression Prediction
Frame-level visual features are generally aggregated in time with the techniques such as LSTM, Fisher Vectors, NetVLAD etc.
EndNet: Sparse AutoEncoder Network for Endmember Extraction and Hyperspectral Unmixing
Data acquired from multi-channel sensors is a highly valuable asset to interpret the environment for a variety of remote sensing applications.
