scholarly journals Dynamic Residual Dense Network for Image Denoising

Sensors ◽  
2019 ◽  
Vol 19 (17) ◽  
pp. 3809 ◽  
Author(s):  
Yuda Song ◽  
Yunfang Zhu ◽  
Xin Du
Keyword(s):  
Real World ◽  
State Of The Art ◽  
Computational Cost ◽  
Dynamic Network ◽  
Input Image ◽  
Dense Network ◽  
Deep Convolutional Neural Networks ◽  
Great Performance ◽  
Image Noise Reduction ◽  
Better Than

Deep convolutional neural networks have achieved great performance on various image restoration tasks. Specifically, the residual dense network (RDN) has achieved great results on image noise reduction by cascading multiple residual dense blocks (RDBs) to make full use of the hierarchical feature. However, the RDN only performs well in denoising on a single noise level, and the computational cost of the RDN increases significantly with the increase in the number of RDBs, and this only slightly improves the effect of denoising. To overcome this, we propose the dynamic residual dense network (DRDN), a dynamic network that can selectively skip some RDBs based on the noise amount of the input image. Moreover, the DRDN allows modifying the denoising strength to manually get the best outputs, which can make the network more effective for real-world denoising. Our proposed DRDN can perform better than the RDN and reduces the computational cost by 40 – 50 % . Furthermore, we surpass the state-of-the-art CBDNet by 1.34 dB on the real-world noise benchmark.

scholarly journals Better Prediction of Mutation Score

2021 ◽  
Author(s):  
Yossi Gil ◽  
Dor Ma’ayan
Keyword(s):  
Neural Networks ◽  
Real World ◽  
State Of The Art ◽  
Future Research ◽  
World Systems ◽  
Reliable Measurement ◽  
Mutation Score ◽  
Class Level ◽  
Effectiveness Prediction ◽  
Better Than

<div><div><div><p>Mutation score is widely accepted to be a reliable measurement for the effectiveness of software tests. Recent studies, however, show that mutation analysis is extremely costly and hard to use in practice. We present a novel direct prediction model of mutation score using neural networks. Relying solely on static code features that do not require generation of mutants or execution of the tests, we predict mutation score with an accuracy better than a quintile. When we include statement coverage as a feature, our accuracy rises to about a decile. Using a similar approach, we also improve the state-of-the-art results for binary test effectiveness prediction and introduce an intuitive, easy-to-calculate set of features superior to previously studied sets. We also publish the largest dataset of test-class level mutation score and static code features data to date, for future research. Finally, we discuss how our approach could be integrated into real-world systems, IDEs, CI tools, and testing frameworks.</p></div></div></div>

scholarly journals COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning

2019 ◽  
Author(s):  
Wenxiao Wang ◽  
Cong Fu ◽  
Jishun Guo ◽  
Deng Cai ◽  
Xiaofei He
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Computational Cost ◽  
Cross Layer ◽  
Optimal Solutions ◽  
Deep Convolutional Neural Networks ◽  
Model Compression ◽  
Deep Model ◽  
Network Compression ◽  
Novel Algorithm

Neural network compression empowers the effective yet unwieldy deep convolutional neural networks (CNN) to be deployed in resource-constrained scenarios. Most state-of-the-art approaches prune the model in filter-level according to the "importance" of filters. Despite their success, we notice they suffer from at least two of the following problems: 1) The redundancy among filters is not considered because the importance is evaluated independently. 2) Cross-layer filter comparison is unachievable since the importance is defined locally within each layer. Consequently, we must manually specify layer-wise pruning ratios. 3) They are prone to generate sub-optimal solutions because they neglect the inequality between reducing parameters and reducing computational cost. Reducing the same number of parameters in different positions in the network may reduce different computational cost. To address the above problems, we develop a novel algorithm named as COP (correlation-based pruning), which can detect the redundant filters efficiently. We enable the cross-layer filter comparison through global normalization. We add parameter-quantity and computational-cost regularization terms to the importance, which enables the users to customize the compression according to their preference (smaller or faster). Extensive experiments have shown COP outperforms the others significantly. The code is released at https://github.com/ZJULearning/COP.

scholarly journals Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels with Variational Auto-Encoder

2021 ◽  
Author(s):  
Weijia Zhang
Keyword(s):  
Medical Imaging ◽  
Supervised Learning ◽  
Real World ◽  
State Of The Art ◽  
Experimental Results ◽  
Weakly Supervised Learning ◽  
Variational Autoencoder ◽  
Label Prediction ◽  
Weakly Supervised ◽  
Better Than

Multi-instance learning is a type of weakly supervised learning. It deals with tasks where the data is a set of bags and each bag is a set of instances. Only the bag labels are observed whereas the labels for the instances are unknown. An important advantage of multi-instance learning is that by representing objects as a bag of instances, it is able to preserve the inherent dependencies among parts of the objects. Unfortunately, most existing algorithms assume all instances to be identically and independently distributed, which violates real-world scenarios since the instances within a bag are rarely independent. In this work, we propose the Multi-Instance Variational Autoencoder (MIVAE) algorithm which explicitly models the dependencies among the instances for predicting both bag labels and instance labels. Experimental results on several multi-instance benchmarks and end-to-end medical imaging datasets demonstrate that MIVAE performs better than state-of-the-art algorithms for both instance label and bag label prediction tasks.

scholarly journals Compressive closeness in networks

2019 ◽  
Vol 4 (1) ◽  
Author(s):  
Hamidreza Mahyar ◽  
Rouzbeh Hasheminezhad ◽  
H Eugene Stanley
Keyword(s):  
Computational Complexity ◽  
Compressive Sensing ◽  
Distributed Algorithms ◽  
Real World ◽  
Topological Structure ◽  
Network Science ◽  
State Of The Art ◽  
Closeness Centrality ◽  
Local Interactions ◽  
Better Than

Abstract Distributed algorithms for network science applications are of great importance due to today’s large real-world networks. In such algorithms, a node is allowed only to have local interactions with its immediate neighbors; because the whole network topological structure is often unknown to each node. Recently, distributed detection of central nodes, concerning different notions of importance, within a network has received much attention. Closeness centrality is a prominent measure to evaluate the importance (influence) of nodes, based on their accessibility, in a given network. In this paper, first, we introduce a local (ego-centric) metric that correlates well with the global closeness centrality; however, it has very low computational complexity. Second, we propose a compressive sensing (CS)-based framework to accurately recover high closeness centrality nodes in the network utilizing the proposed local metric. Both ego-centric metric computation and its aggregation via CS are efficient and distributed, using only local interactions between neighboring nodes. Finally, we evaluate the performance of the proposed method through extensive experiments on various synthetic and real-world networks. The results show that the proposed local metric correlates with the global closeness centrality, better than the current local metrics. Moreover, the results demonstrate that the proposed CS-based method outperforms state-of-the-art methods with notable improvement.

scholarly journals EHANet: An Effective Hierarchical Aggregation Network for Face Parsing

2020 ◽  
Vol 10 (9) ◽  
pp. 3135 ◽  
Author(s):  
Ling Luo ◽  
Dingyu Xue ◽  
Xinglong Feng
Keyword(s):  
Neural Networks ◽  
Real World ◽  
State Of The Art ◽  
Contextual Information ◽  
Semantic Gap ◽  
Deep Convolutional Neural Networks ◽  
Multi Scale ◽  
Hierarchical Aggregation ◽  
Real World Applications ◽  
Weighted Boundary

In recent years, benefiting from deep convolutional neural networks (DCNNs), face parsing has developed rapidly. However, it still has the following problems: (1) Existing state-of-the-art frameworks usually do not satisfy real-time while pursuing performance; (2) similar appearances cause incorrect pixel label assignments, especially in the boundary; (3) to promote multi-scale prediction, deep features and shallow features are used for fusion without considering the semantic gap between them. To overcome these drawbacks, we propose an effective and efficient hierarchical aggregation network called EHANet for fast and accurate face parsing. More specifically, we first propose a stage contextual attention mechanism (SCAM), which uses higher-level contextual information to re-encode the channel according to its importance. Secondly, a semantic gap compensation block (SGCB) is presented to ensure the effective aggregation of hierarchical information. Thirdly, the advantages of weighted boundary-aware loss effectively make up for the ambiguity of boundary semantics. Without any bells and whistles, combined with a lightweight backbone, we achieve outstanding results on both CelebAMask-HQ (78.19% mIoU) and Helen datasets (90.7% F1-score). Furthermore, our model can achieve 55 FPS on a single GTX 1080Ti card with 640 × 640 input and further reach over 300 FPS with a resolution of 256 × 256, which is suitable for real-world applications.

scholarly journals An Input-aware Factorization Machine for Sparse Prediction

2019 ◽  
Author(s):  
Yantao Yu ◽  
Zhen Wang ◽  
Bo Yuan
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Real World ◽  
State Of The Art ◽  
Overall Performance ◽  
Factorization Machine ◽  
The Impact ◽  
Novel Model ◽  
Individual Input ◽  
Better Than

Factorization machines (FMs) are a class of general predictors working effectively with sparse data, which represents features using factorized parameters and weights. However, the accuracy of FMs can be adversely affected by the fixed representation trained for each feature, as the same feature is usually not equally predictive and useful in different instances. In fact, the inaccurate representation of features may even introduce noise and degrade the overall performance. In this work, we improve FMs by explicitly considering the impact of individual input upon the representation of features. We propose a novel model named \textit{Input-aware Factorization Machine} (IFM), which learns a unique input-aware factor for the same feature in different instances via a neural network. Comprehensive experiments on three real-world recommendation datasets are used to demonstrate the effectiveness and mechanism of IFM. Empirical results indicate that IFM is significantly better than the standard FM model and consistently outperforms four state-of-the-art deep learning based methods.

A Neural Network for Image Anomaly Detection with Deep Pyramidal Representations and Dynamic Routing

2020 ◽  
Vol 30 (10) ◽  
pp. 2050060
Author(s):  
Pankaj Mishra ◽  
Claudio Piciarelli ◽  
Gian Luca Foresti
Keyword(s):  
Neural Network ◽  
Anomaly Detection ◽  
State Of The Art ◽  
Structural Similarity ◽  
Input Image ◽  
Image Features ◽  
Anomalous Data ◽  
Scale Levels ◽  
Anomaly Detector ◽  
Better Than

Image anomaly detection is an application-driven problem where the aim is to identify novel samples, which differ significantly from the normal ones. We here propose Pyramidal Image Anomaly DEtector (PIADE), a deep reconstruction-based pyramidal approach, in which image features are extracted at different scale levels to better catch the peculiarities that could help to discriminate between normal and anomalous data. The features are dynamically routed to a reconstruction layer and anomalies can be identified by comparing the input image with its reconstruction. Unlike similar approaches, the comparison is done by using structural similarity and perceptual loss rather than trivial pixel-by-pixel comparison. The proposed method performed at par or better than the state-of-the-art methods when tested on publicly available datasets such as CIFAR10, COIL-100 and MVTec.

scholarly journals Better Prediction of Mutation Score

2021 ◽  
Author(s):  
Yossi Gil ◽  
Dor Ma’ayan
Keyword(s):  
Neural Networks ◽  
Real World ◽  
State Of The Art ◽  
Future Research ◽  
World Systems ◽  
Reliable Measurement ◽  
Mutation Score ◽  
Class Level ◽  
Effectiveness Prediction ◽  
Better Than

<div><div><div><p>Mutation score is widely accepted to be a reliable measurement for the effectiveness of software tests. Recent studies, however, show that mutation analysis is extremely costly and hard to use in practice. We present a novel direct prediction model of mutation score using neural networks. Relying solely on static code features that do not require generation of mutants or execution of the tests, we predict mutation score with an accuracy better than a quintile. When we include statement coverage as a feature, our accuracy rises to about a decile. Using a similar approach, we also improve the state-of-the-art results for binary test effectiveness prediction and introduce an intuitive, easy-to-calculate set of features superior to previously studied sets. We also publish the largest dataset of test-class level mutation score and static code features data to date, for future research. Finally, we discuss how our approach could be integrated into real-world systems, IDEs, CI tools, and testing frameworks.</p></div></div></div>

Fusion of Underwater Image Enhancement and Restoration

2019 ◽  
Vol 34 (03) ◽  
pp. 2054007 ◽  
Author(s):  
Rajni Sethi ◽  
Sreedevi Indu
Keyword(s):  
Image Enhancement ◽  
State Of The Art ◽  
Input Image ◽  
Laplacian Pyramid ◽  
Novel Technique ◽  
Underwater Image ◽  
Single Input ◽  
Color Cast ◽  
Better Than

Optical properties of water distort the quality of underwater images. Underwater images are characterized by poor contrast, color cast, noise and haze. These images need to be pre-processed so as to get some information. In this paper, a novel technique named Fusion of Underwater Image Enhancement and Restoration (FUIER) has been proposed which enhances as well as restores underwater images with a target to act on all major issues in underwater images, i.e. color cast removal, contrast enhancement and dehazing. It generates two versions of the single input image and these two versions are fused using Laplacian pyramid-based fusion to get the enhanced image. The proposed method works efficiently for all types of underwater images captured in different conditions (turbidity, depth, salinity, etc.). Results obtained using the proposed method are better than those for state-of-the-art methods.

Smart Animation Tools

2018 ◽  
pp. 52-66
Author(s):  
Benjamin Kenwright
Keyword(s):  
Machine Learning ◽  
Parallel Processing ◽  
Real World ◽  
State Of The Art ◽  
Computational Cost ◽  
Massively Parallel ◽  
Learning Models ◽  
Processing Power ◽  
Massively Parallel Processing ◽  
Self Learning

This chapter discusses the inherent limitations in conventional animation techniques and possible solutions through optimisation and machine learning paradigms. For example, going beyond pre–recorded animation libraries towards more intelligent self-learning models. These models present a range of difficulties in real-world solutions, such as, computational cost, flexibility, and most importantly, artistic control. However, as we discuss in this chapter, advancements in massively parallel processing power and hybrid models provides a transitional medium for these solutions (best of both worlds). We review trends and state of the art techniques and their viability in industry. A particular area of active animation is self–driven characters (i.e., agents mimic the real-world through physics-based models). We discuss and debate each techniques practicality in solving and overcoming current and future limitations.

Sign in / Sign up

Export Citation Format

Share Document