scholarly journals Ultrafast Photorealistic Style Transfer via Neural Architecture Search

2020 ◽  
Vol 34 (07) ◽  
pp. 10443-10450
Author(s):  
Jie An ◽  
Haoyi Xiong ◽  
Jun Huan ◽  
Jiebo Luo
Keyword(s):  
Network Architecture ◽  
State Of The Art ◽  
Style Transfer ◽  
Network Pruning ◽  
Neural Architecture ◽  
Teacher Student ◽  
Significant Acceleration ◽  
Construction Step ◽  
Efficiency And Effectiveness ◽  
Additional Processing

The key challenge in photorealistic style transfer is that an algorithm should faithfully transfer the style of a reference photo to a content photo while the generated image should look like one captured by a camera. Although several photorealistic style transfer algorithms have been proposed, they need to rely on post- and/or pre-processing to make the generated images look photorealistic. If we disable the additional processing, these algorithms would fail to produce plausible photorealistic stylization in terms of detail preservation and photorealism. In this work, we propose an effective solution to these issues. Our method consists of a construction step (C-step) to build a photorealistic stylization network and a pruning step (P-step) for acceleration. In the C-step, we propose a dense auto-encoder named PhotoNet based on a carefully designed pre-analysis. PhotoNet integrates a feature aggregation module (BFA) and instance normalized skip links (INSL). To generate faithful stylization, we introduce multiple style transfer modules in the decoder and INSLs. PhotoNet significantly outperforms existing algorithms in terms of both efficiency and effectiveness. In the P-step, we adopt a neural architecture search method to accelerate PhotoNet. We propose an automatic network pruning framework in the manner of teacher-student learning for photorealistic stylization. The network architecture named PhotoNAS resulted from the search achieves significant acceleration over PhotoNet while keeping the stylization effects almost intact. We conduct extensive experiments on both image and video transfer. The results show that our method can produce favorable results while achieving 20-30 times acceleration in comparison with the existing state-of-the-art approaches. It is worth noting that the proposed algorithm accomplishes better performance without any pre- or post-processing.

scholarly journals A transformer-based approach to irony and sarcasm detection

2020 ◽  
Vol 32 (23) ◽  
pp. 17309-17320
Author(s):  
Rolandos Alexandros Potamias ◽  
Georgios Siolas ◽  
Andreas - Georgios Stafylopatis
Keyword(s):  
Neural Network ◽  
Language Processing ◽  
Network Architecture ◽  
Figurative Language ◽  
State Of The Art ◽  
Unresolved Issue ◽  
Discussion Forums ◽  
Large Margin ◽  
Neural Architecture ◽  
Benchmark Datasets

AbstractFigurative language (FL) seems ubiquitous in all social media discussion forums and chats, posing extra challenges to sentiment analysis endeavors. Identification of FL schemas in short texts remains largely an unresolved issue in the broader field of natural language processing, mainly due to their contradictory and metaphorical meaning content. The main FL expression forms are sarcasm, irony and metaphor. In the present paper, we employ advanced deep learning methodologies to tackle the problem of identifying the aforementioned FL forms. Significantly extending our previous work (Potamias et al., in: International conference on engineering applications of neural networks, Springer, Berlin, pp 164–175, 2019), we propose a neural network methodology that builds on a recently proposed pre-trained transformer-based network architecture which is further enhanced with the employment and devise of a recurrent convolutional neural network. With this setup, data preprocessing is kept in minimum. The performance of the devised hybrid neural architecture is tested on four benchmark datasets, and contrasted with other relevant state-of-the-art methodologies and systems. Results demonstrate that the proposed methodology achieves state-of-the-art performance under all benchmark datasets, outperforming, even by a large margin, all other methodologies and published studies.

scholarly journals TextNAS: A Neural Architecture Search Space Tailored for Text Representation

2020 ◽  
Vol 34 (05) ◽  
pp. 9242-9249
Author(s):  
Yujing Wang ◽  
Yaming Yang ◽  
Yiren Chen ◽  
Jing Bai ◽  
Ce Zhang ◽  
...  
Keyword(s):  
Text Classification ◽  
Network Architecture ◽  
State Of The Art ◽  
Search Space ◽  
Search Algorithms ◽  
Text Representation ◽  
Neural Architecture ◽  
Good Potential ◽  
Automatic Search ◽  
Public Datasets

Learning text representation is crucial for text classification and other language related tasks. There are a diverse set of text representation networks in the literature, and how to find the optimal one is a non-trivial problem. Recently, the emerging Neural Architecture Search (NAS) techniques have demonstrated good potential to solve the problem. Nevertheless, most of the existing works of NAS focus on the search algorithms and pay little attention to the search space. In this paper, we argue that the search space is also an important human prior to the success of NAS in different applications. Thus, we propose a novel search space tailored for text representation. Through automatic search, the discovered network architecture outperforms state-of-the-art models on various public datasets on text classification and natural language inference tasks. Furthermore, some of the design principles found in the automatic network agree well with human intuition.

scholarly journals Disentangled generative adversarial network for low-dose CT

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Wenchao Du ◽  
Hu Chen ◽  
Hongyu Yang ◽  
Yi Zhang
Keyword(s):  
Network Architecture ◽  
Low Dose ◽  
Noise Suppression ◽  
State Of The Art ◽  
Visual Quality ◽  
Ct Images ◽  
Generative Adversarial Network ◽  
Low Dose Ct ◽  
Adversarial Network ◽  
Suppression Method

AbstractGenerative adversarial network (GAN) has been applied for low-dose CT images to predict normal-dose CT images. However, the undesired artifacts and details bring uncertainty to the clinical diagnosis. In order to improve the visual quality while suppressing the noise, in this paper, we mainly studied the two key components of deep learning based low-dose CT (LDCT) restoration models—network architecture and adversarial loss, and proposed a disentangled noise suppression method based on GAN (DNSGAN) for LDCT. Specifically, a generator network, which contains the noise suppression and structure recovery modules, is proposed. Furthermore, a multi-scaled relativistic adversarial loss is introduced to preserve the finer structures of generated images. Experiments on simulated and real LDCT datasets show that the proposed method can effectively remove noise while recovering finer details and provide better visual perception than other state-of-the-art methods.

scholarly journals SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

2021 ◽  
Vol 40 (3) ◽  
pp. 1-13
Author(s):  
Lumin Yang ◽  
Jiajie Zhuang ◽  
Hongbo Fu ◽  
Xiangzhi Wei ◽  
Kun Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Large Scale ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Structure Information ◽  
Graph Neural Networks ◽  
Node Labels ◽  
Point Level

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

scholarly journals Fighting Together against the Pandemic: Learning Multiple Models on Tomography Images for COVID-19 Diagnosis

AI ◽  
2021 ◽  
Vol 2 (2) ◽  
pp. 261-273
Author(s):  
Mario Manzo ◽  
Simone Pellino
Keyword(s):  
Network Architecture ◽  
State Of The Art ◽  
Ensemble Classification ◽  
Effective Vaccine ◽  
Rt Pcr ◽  
Neural Network Architecture ◽  
Experimental Phase ◽  
Different Types ◽  
Polymerase Chain ◽  
Better Than

COVID-19 has been a great challenge for humanity since the year 2020. The whole world has made a huge effort to find an effective vaccine in order to save those not yet infected. The alternative solution is early diagnosis, carried out through real-time polymerase chain reaction (RT-PCR) tests or thorax Computer Tomography (CT) scan images. Deep learning algorithms, specifically convolutional neural networks, represent a methodology for image analysis. They optimize the classification design task, which is essential for an automatic approach with different types of images, including medical. In this paper, we adopt a pretrained deep convolutional neural network architecture in order to diagnose COVID-19 disease from CT images. Our idea is inspired by what the whole of humanity is achieving, as the set of multiple contributions is better than any single one for the fight against the pandemic. First, we adapt, and subsequently retrain for our assumption, some neural architectures that have been adopted in other application domains. Secondly, we combine the knowledge extracted from images by the neural architectures in an ensemble classification context. Our experimental phase is performed on a CT image dataset, and the results obtained show the effectiveness of the proposed approach with respect to the state-of-the-art competitors.

scholarly journals Critical Aspects of Person Counting and Density Estimation

2021 ◽  
Vol 7 (2) ◽  
pp. 21
Author(s):  
Roland Perko ◽  
Manfred Klopschitz ◽  
Alexander Almer ◽  
Peter M. Roth
Keyword(s):  
Density Estimation ◽  
Network Architecture ◽  
Reference Data ◽  
State Of The Art ◽  
Limit State ◽  
Ground Truth ◽  
Data Sets ◽  
Ground Truth Generation ◽  
Baseline Approach ◽  
Critical Aspects

Many scientific studies deal with person counting and density estimation from single images. Recently, convolutional neural networks (CNNs) have been applied for these tasks. Even though often better results are reported, it is often not clear where the improvements are resulting from, and if the proposed approaches would generalize. Thus, the main goal of this paper was to identify the critical aspects of these tasks and to show how these limit state-of-the-art approaches. Based on these findings, we show how to mitigate these limitations. To this end, we implemented a CNN-based baseline approach, which we extended to deal with identified problems. These include the discovery of bias in the reference data sets, ambiguity in ground truth generation, and mismatching of evaluation metrics w.r.t. the training loss function. The experimental results show that our modifications allow for significantly outperforming the baseline in terms of the accuracy of person counts and density estimation. In this way, we get a deeper understanding of CNN-based person density estimation beyond the network architecture. Furthermore, our insights would allow to advance the field of person density estimation in general by highlighting current limitations in the evaluation protocols.

scholarly journals Hybrid Graph Neural Networks for Crowd Counting

2020 ◽  
Vol 34 (07) ◽  
pp. 11693-11700 ◽  
Author(s):  
Ao Luo ◽  
Fan Yang ◽  
Xin Li ◽  
Dong Nie ◽  
Zhicheng Jiao ◽  
...  
Keyword(s):  
Network Architecture ◽  
Message Passing ◽  
Large Scale ◽  
State Of The Art ◽  
Density Variation ◽  
Feature Maps ◽  
Crowd Counting ◽  
Multi Scale ◽  
Crowd Density ◽  
Graph Neural Networks

Crowd counting is an important yet challenging task due to the large scale and density variation. Recent investigations have shown that distilling rich relations among multi-scale features and exploiting useful information from the auxiliary task, i.e., localization, are vital for this task. Nevertheless, how to comprehensively leverage these relations within a unified network architecture is still a challenging problem. In this paper, we present a novel network structure called Hybrid Graph Neural Network (HyGnn) which targets to relieve the problem by interweaving the multi-scale features for crowd density as well as its auxiliary task (localization) together and performing joint reasoning over a graph. Specifically, HyGnn integrates a hybrid graph to jointly represent the task-specific feature maps of different scales as nodes, and two types of relations as edges: (i) multi-scale relations capturing the feature dependencies across scales and (ii) mutual beneficial relations building bridges for the cooperation between counting and localization. Thus, through message passing, HyGnn can capture and distill richer relations between nodes to obtain more powerful representations, providing robust and accurate results. Our HyGnn performs significantly well on four challenging datasets: ShanghaiTech Part A, ShanghaiTech Part B, UCF_CC_50 and UCF_QNRF, outperforming the state-of-the-art algorithms by a large margin.

scholarly journals Translucent Answer Predictions in Multi-Hop Reading Comprehension

2020 ◽  
Vol 34 (05) ◽  
pp. 7700-7707
Author(s):  
G P Shrivatsa Bhargav ◽  
Michael Glass ◽  
Dinesh Garg ◽  
Shirish Shevade ◽  
Saswati Dana ◽  
...  
Keyword(s):  
Reading Comprehension ◽  
Question Answering ◽  
State Of The Art ◽  
Local Context ◽  
The Novel ◽  
Loose Coupling ◽  
Loosely Coupled ◽  
Neural Architecture ◽  
Coupled Networks ◽  
Novel Design

Research on the task of Reading Comprehension style Question Answering (RCQA) has gained momentum in recent years due to the emergence of human annotated datasets and associated leaderboards, for example CoQA, HotpotQA, SQuAD, TriviaQA, etc. While state-of-the-art has advanced considerably, there is still ample opportunity to advance it further on some important variants of the RCQA task. In this paper, we propose a novel deep neural architecture, called TAP (Translucent Answer Prediction), to identify answers and evidence (in the form of supporting facts) in an RCQA task requiring multi-hop reasoning. TAP comprises two loosely coupled networks – Local and Global Interaction eXtractor (LoGIX) and Answer Predictor (AP). LoGIX predicts supporting facts, whereas AP consumes these predicted supporting facts to predict the answer span. The novel design of LoGIX is inspired by two key design desiderata – local context and global interaction– that we identified by analyzing examples of multi-hop RCQA task. The loose coupling between LoGIX and the AP reveals the set of sentences used by the AP in predicting an answer. Therefore, answer predictions of TAP can be interpreted in a translucent manner. TAP offers state-of-the-art performance on the HotpotQA (Yang et al. 2018) dataset – an apt dataset for multi-hop RCQA task – as it occupies Rank-1 on its leaderboard (https://hotpotqa.github.io/) at the time of submission.

scholarly journals One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search

2021 ◽  
Vol 5 (3) ◽  
pp. 1-34
Author(s):  
Bingqian Lu ◽  
Jianyi Yang ◽  
Weiwen Jiang ◽  
Yiyu Shi ◽  
Shaolei Ren
Keyword(s):  
State Of The Art ◽  
Autonomous Driving ◽  
Pareto Optimal ◽  
Video Content ◽  
Fast Evaluation ◽  
Video Content Analysis ◽  
Search Spaces ◽  
Neural Architecture ◽  
Real World Applications ◽  
Prohibitive Cost

Convolutional neural networks (CNNs) are used in numerous real-world applications such as vision-based autonomous driving and video content analysis. To run CNN inference on various target devices, hardware-aware neural architecture search (NAS) is crucial. A key requirement of efficient hardware-aware NAS is the fast evaluation of inference latencies in order to rank different architectures. While building a latency predictor for each target device has been commonly used in state of the art, this is a very time-consuming process, lacking scalability in the presence of extremely diverse devices. In this work, we address the scalability challenge by exploiting latency monotonicity --- the architecture latency rankings on different devices are often correlated. When strong latency monotonicity exists, we can re-use architectures searched for one proxy device on new target devices, without losing optimality. In the absence of strong latency monotonicity, we propose an efficient proxy adaptation technique to significantly boost the latency monotonicity. Finally, we validate our approach and conduct experiments with devices of different platforms on multiple mainstream search spaces, including MobileNet-V2, MobileNet-V3, NAS-Bench-201, ProxylessNAS and FBNet. Our results highlight that, by using just one proxy device, we can find almost the same Pareto-optimal architectures as the existing per-device NAS, while avoiding the prohibitive cost of building a latency predictor for each device.

scholarly journals Crafting Efficient Neural Graph of Large Entropy

2019 ◽  
Author(s):  
Minjing Dong ◽  
Hanting Chen ◽  
Yunhe Wang ◽  
Chang Xu
Keyword(s):  
Information Flow ◽  
Network Architecture ◽  
High Performance ◽  
Global Information ◽  
High Quality ◽  
Network Pruning ◽  
Initial Network ◽  
Trade Offs ◽  
Graph Properties ◽  
Deep Cnn

Network pruning is widely applied to deep CNN models due to their heavy computation costs and achieves high performance by keeping important weights while removing the redundancy. Pruning redundant weights directly may hurt global information flow, which suggests that an efficient sparse network should take graph properties into account. Thus, instead of paying more attention to preserving important weight, we focus on the pruned architecture itself. We propose to use graph entropy as the measurement, which shows useful properties to craft high-quality neural graphs and enables us to propose efficient algorithm to construct them as the initial network architecture. Our algorithm can be easily implemented and deployed to different popular CNN models and achieve better trade-offs.

Sign in / Sign up

Export Citation Format

Share Document