Search Results for author:
Found 18 papers, 5 papers with code
Single-Image Super-Resolution Reconstruction based on the Differences of Neighboring Pixels
The deep learning technique was used to increase the performance of single image super-resolution (SISR).
Pixel Relationships-based Regularizer for Retinal Vessel Image Segmentation
Using pixel-wise loss neglected the pixel neighbor relationships in the network learning process.
Attention-effective multiple instance learning on weakly stem cell colony segmentation
It is designed in a single model to produce weak segmentation and classification of colonies without using finely labeled samples.
Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN
The proposed approach intends to show the usefulness of every layer termed as global-local attention in 3D CNN via visual attribution, weakly-supervised action localization, and action recognition.
q-SNE: Visualizing Data using q-Gaussian Distributed Stochastic Neighbor Embedding
As the one technique of dimensionality reduction, a stochastic neighbor embedding (SNE) was introduced.
Channel Planting for Deep Neural Networks using Knowledge Distillation
Our planting can search the optimal network architecture with smaller number of parameters for improving the network performance by augmenting channels incrementally to layers of the initial networks while keeping the earlier trained parameters fixed.
Filter Pruning using Hierarchical Group Sparse Regularization for Deep Convolutional Neural Networks
It is shown that the proposed method can reduce more than 50% parameters of ResNet for CIFAR-10 with only 0. 3% decrease in the accuracy of test samples.
Transfer Learning by Cascaded Network to identify and classify lung nodules for cancer detection
The experimental results showed that the classification accuracy of 97. 96\% of our proposed architecture outperformed other simple and complex architectures in classifying lung nodules for lung cancer detection.
U-Net with Graph Based Smoothing Regularizer for Small Vessel Segmentation on Fundus Image
The detection of retinal blood vessels, especially the changes of small vessel condition is the most important indicator to identify the vascular network of the human body.
Triplet Loss for Knowledge Distillation
The functionality of the metric learning to reduce the differences between similar outputs can be used for the knowledge distillation to reduce the differences between the outputs of the teacher model and the student model.
Adaptive Neuron-wise Discriminant Criterion and Adaptive Center Loss at Hidden Layer for Deep Convolutional Neural Network
The neuron-wise discriminant criterion makes the input feature of each neuron in the output layer discriminative by introducing the discriminant criterion to each of the features.
Hierarchical Group Sparse Regularization for Deep Convolutional Neural Networks
As a result, we can prune the weights more adequately depending on the structure of the network and the number of channels keeping high performance.
On-line non-overlapping camera calibration net
First, successive images are fed to a PoseNet-based network to obtain ego-motion of cameras between frames.
Mixup of Feature Maps in a Hidden Layer for Training of Convolutional Neural Network
However, the recognition accuracy of the trained deep CNN drastically decreases for the samples which are obtained from the outside regions of the training samples.
Correlation Net: Spatiotemporal multimodal deep learning for action recognition
The existing fusion approach averages the two streams.
Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network
A combination of Deep CNNs and Skip connection layers is used as a feature extractor for image features on both local and global area.
Ranked #20 on
Image Super-Resolution
on Set14 - 2x upscaling
Mixture of Counting CNNs: Adaptive Integration of CNNs Specialized to Specific Appearance for Crowd Counting
In this paper, we propose to predict the number of targets using multiple CNNs specialized to a specific appearance, and those CNNs are adaptively selected according to the appearance of a test image.
Domain Adaptation with L2 constraints for classifying images from different endoscope systems
This paper proposes a method for domain adaptation that extends the maximum margin domain transfer (MMDT) proposed by Hoffman et al., by introducing L2 distance constraints between samples of different domains; thus, our method is denoted as MMDTL2.
