Pinned Repositories
AutoEncoder_HumanFace
B-lines-Detection-and-Evaluation-in-Thorax-Ultrasound-Video
Due to its convenient real time, non-invasive detection, lung ultrasound is an excellent diagnostic tool in researches related to pulmonary congestion. However, its objective assessment remains elusive. Currently, the detection and evaluation of pulmonary congestion largely rely on manual detection of B-lines by ultrasound specialists. In this paper, I propose an automatic method to detect Blines.
CV_homework
DCGAN_CATFACE
Create cat face by using DCGAN
Fast-Approximate-Spectral-Norm-Regularization-for-Enhancing-Robustness-of-DNNs
Deep neural networks (DNNs) are recently playing an important role in machine learning fields due to its outstanding performance compared with traditional approaches. However, DNNs are vulnerable to adversarial attacks and can easily be fooled by well crafted adversarial examples. Thus, DNNs will definitely bring severe security risks if deployed in fields requiring high reliability. Spectral norm regularization is a regularization method that can ensure the trained model to possess relatively low sensitivity towards the disturbance of input samples, which makes it an appealing strategy for enhancing models' robustness. However, the time cost for exact spectral norm computation is extremely expensive and impractical for large-scale networks. In this paper, we introduce a new framework for spectral norm regularization based on Fourier method and layer separation. The key insight underlying our work is it nicely combines the sparsity of weight matrix and decomposability of convolution layers. Our experimental evaluations provide persuasive evidence to show our framework is able to achieve extremely fast time efficiency and better enhanced model robustness compared with the baseline method.
Gram-Filtering-and-Sinogram-Interpolation-for-Pixel-basis-in-Parallel-beam-X-ray-CT-Reconstruction
The key aspect of parallel-beam X-ray CT is forward and back projection, but its computational burden continues to be an obstacle for applications. We propose to use pixel-basis to improve the performance of related algorithms. In addition, the detector blur effect can be included in our model efficiently. The improvements in speed and quality for back projection and iterative reconstruction are shown in our experiments on both analytical phantoms and real CT images.
Madoka
COC X Madoka
Privacy-Machine-Learning-----Adversarial-Machine-Learning
Saliency-Detection-Algorithm-via-Multi-Level-Graph-Structure-and-Accurate-Background-Queries-Select
In the field of saliency detection, many graph-based algorithms use boundary pixels as background seeds to estimate the background and foreground saliency,which leads to significant errors in some of pictures. In addition, local context with high contrast will mislead the algorithms. In this paper, we propose a novel multilevel bottom-up saliency detection approach that accurately utilizes the boundary information and takes advantage of both region-based features and local image details. To provide more accurate saliency estimations, we build a three-level graph model to capture both region-based features and local image details. By using superpixels of all four boundaries, we first roughly figure out the foreground superpixels. After calculating the RGB distances between the average of foreground superpixels and every boundary superpixel, we discard the boundary superpixels with the longest distance to get a set of accurate background boundary queries. Finally, we propose the regularized random walks ranking to formulate pixel-wise saliency maps. Experiment results on two public datasets indicate the significantly promoted accuracy and robustness of our proposed algorithm in comparison with 7 state-of-the-art saliency detection approaches.
tensorflow-vgg
VGG19 and VGG16 on Tensorflow
Flocculus's Repositories
Flocculus/Fast-Approximate-Spectral-Norm-Regularization-for-Enhancing-Robustness-of-DNNs
Deep neural networks (DNNs) are recently playing an important role in machine learning fields due to its outstanding performance compared with traditional approaches. However, DNNs are vulnerable to adversarial attacks and can easily be fooled by well crafted adversarial examples. Thus, DNNs will definitely bring severe security risks if deployed in fields requiring high reliability. Spectral norm regularization is a regularization method that can ensure the trained model to possess relatively low sensitivity towards the disturbance of input samples, which makes it an appealing strategy for enhancing models' robustness. However, the time cost for exact spectral norm computation is extremely expensive and impractical for large-scale networks. In this paper, we introduce a new framework for spectral norm regularization based on Fourier method and layer separation. The key insight underlying our work is it nicely combines the sparsity of weight matrix and decomposability of convolution layers. Our experimental evaluations provide persuasive evidence to show our framework is able to achieve extremely fast time efficiency and better enhanced model robustness compared with the baseline method.
Flocculus/Saliency-Detection-Algorithm-via-Multi-Level-Graph-Structure-and-Accurate-Background-Queries-Select
In the field of saliency detection, many graph-based algorithms use boundary pixels as background seeds to estimate the background and foreground saliency,which leads to significant errors in some of pictures. In addition, local context with high contrast will mislead the algorithms. In this paper, we propose a novel multilevel bottom-up saliency detection approach that accurately utilizes the boundary information and takes advantage of both region-based features and local image details. To provide more accurate saliency estimations, we build a three-level graph model to capture both region-based features and local image details. By using superpixels of all four boundaries, we first roughly figure out the foreground superpixels. After calculating the RGB distances between the average of foreground superpixels and every boundary superpixel, we discard the boundary superpixels with the longest distance to get a set of accurate background boundary queries. Finally, we propose the regularized random walks ranking to formulate pixel-wise saliency maps. Experiment results on two public datasets indicate the significantly promoted accuracy and robustness of our proposed algorithm in comparison with 7 state-of-the-art saliency detection approaches.
Flocculus/Gram-Filtering-and-Sinogram-Interpolation-for-Pixel-basis-in-Parallel-beam-X-ray-CT-Reconstruction
The key aspect of parallel-beam X-ray CT is forward and back projection, but its computational burden continues to be an obstacle for applications. We propose to use pixel-basis to improve the performance of related algorithms. In addition, the detector blur effect can be included in our model efficiently. The improvements in speed and quality for back projection and iterative reconstruction are shown in our experiments on both analytical phantoms and real CT images.
Flocculus/B-lines-Detection-and-Evaluation-in-Thorax-Ultrasound-Video
Due to its convenient real time, non-invasive detection, lung ultrasound is an excellent diagnostic tool in researches related to pulmonary congestion. However, its objective assessment remains elusive. Currently, the detection and evaluation of pulmonary congestion largely rely on manual detection of B-lines by ultrasound specialists. In this paper, I propose an automatic method to detect Blines.
Flocculus/CV_homework
Flocculus/Privacy-Machine-Learning-----Adversarial-Machine-Learning
Flocculus/AutoEncoder_HumanFace
Flocculus/Madoka
COC X Madoka
Flocculus/tensorflow-vgg
VGG19 and VGG16 on Tensorflow
Flocculus/DCGAN_CATFACE
Create cat face by using DCGAN
Flocculus/Exact-Gram-Filtering-and-Accurate-Back-Projection-in-3D-Parallel-beam-X-ray-CT-Reconstruction
By using the 3D pixel basis, we can dramatically improve the efficiency of 3D parallel beam reconstruction
Flocculus/FibonacciHeap
C++ implementation of Fibonacci heap
Flocculus/multi-agent-emergence-environments
Environment generation code for the paper "Emergent Tool Use From Multi-Agent Autocurricula"
Flocculus/MultiPlanarUNet
Multi-Planar UNet for autonomous segmentation of 3D medical images
Flocculus/U-Time
U-Time: A Fully Convolutional Network for Time Series Segmentation