Paper Group ANR 317
PhaseStain: Digital staining of label-free quantitative phase microscopy images using deep learning. Transcribing Lyrics From Commercial Song Audio: The First Step Towards Singing Content Processing. Segmentation of Liver Lesions with Reduced Complexity Deep Models. Environments for Lifelong Reinforcement Learning. A Deep Learning Architecture for …
PhaseStain: Digital staining of label-free quantitative phase microscopy images using deep learning
Title | PhaseStain: Digital staining of label-free quantitative phase microscopy images using deep learning |
Authors | Yair Rivenson, Tairan Liu, Zhensong Wei, Yibo Zhang, Aydogan Ozcan |
Abstract | Using a deep neural network, we demonstrate a digital staining technique, which we term PhaseStain, to transform quantitative phase images (QPI) of labelfree tissue sections into images that are equivalent to brightfield microscopy images of the same samples that are histochemically stained. Through pairs of image data (QPI and the corresponding brightfield images, acquired after staining) we train a generative adversarial network (GAN) and demonstrate the effectiveness of this virtual staining approach using sections of human skin, kidney and liver tissue, matching the brightfield microscopy images of the same samples stained with Hematoxylin and Eosin, Jones’ stain, and Masson’s trichrome stain, respectively. This digital staining framework might further strengthen various uses of labelfree QPI techniques in pathology applications and biomedical research in general, by eliminating the need for chemical staining, reducing sample preparation related costs and saving time. Our results provide a powerful example of some of the unique opportunities created by data driven image transformations enabled by deep learning. |
Tasks | |
Published | 2018-07-20 |
URL | http://arxiv.org/abs/1807.07701v1 |
http://arxiv.org/pdf/1807.07701v1.pdf | |
PWC | https://paperswithcode.com/paper/phasestain-digital-staining-of-label-free |
Repo | |
Framework | |
Transcribing Lyrics From Commercial Song Audio: The First Step Towards Singing Content Processing
Title | Transcribing Lyrics From Commercial Song Audio: The First Step Towards Singing Content Processing |
Authors | Che-Ping Tsai, Yi-Lin Tuan, Lin-shan Lee |
Abstract | Spoken content processing (such as retrieval and browsing) is maturing, but the singing content is still almost completely left out. Songs are human voice carrying plenty of semantic information just as speech, and may be considered as a special type of speech with highly flexible prosody. The various problems in song audio, for example the significantly changing phone duration over highly flexible pitch contours, make the recognition of lyrics from song audio much more difficult. This paper reports an initial attempt towards this goal. We collected music-removed version of English songs directly from commercial singing content. The best results were obtained by TDNN-LSTM with data augmentation with 3-fold speed perturbation plus some special approaches. The WER achieved (73.90%) was significantly lower than the baseline (96.21%), but still relatively high. |
Tasks | Data Augmentation |
Published | 2018-04-15 |
URL | http://arxiv.org/abs/1804.05306v1 |
http://arxiv.org/pdf/1804.05306v1.pdf | |
PWC | https://paperswithcode.com/paper/transcribing-lyrics-from-commercial-song |
Repo | |
Framework | |
Segmentation of Liver Lesions with Reduced Complexity Deep Models
Title | Segmentation of Liver Lesions with Reduced Complexity Deep Models |
Authors | Ram Krishna Pandey, Aswin Vasan, A G Ramakrishnan |
Abstract | We propose a computationally efficient architecture that learns to segment lesions from CT images of the liver. The proposed architecture uses bilinear interpolation with sub-pixel convolution at the last layer to upscale the course feature in bottle neck architecture. Since bilinear interpolation and sub-pixel convolution do not have any learnable parameter, our overall model is faster and occupies less memory footprint than the traditional U-net. We evaluate our proposed architecture on the highly competitive dataset of 2017 Liver Tumor Segmentation (LiTS) Challenge. Our method achieves competitive results while reducing the number of learnable parameters roughly by a factor of 13.8 compared to the original UNet model. |
Tasks | |
Published | 2018-05-23 |
URL | http://arxiv.org/abs/1805.09233v1 |
http://arxiv.org/pdf/1805.09233v1.pdf | |
PWC | https://paperswithcode.com/paper/segmentation-of-liver-lesions-with-reduced |
Repo | |
Framework | |
Environments for Lifelong Reinforcement Learning
Title | Environments for Lifelong Reinforcement Learning |
Authors | Khimya Khetarpal, Shagun Sodhani, Sarath Chandar, Doina Precup |
Abstract | To achieve general artificial intelligence, reinforcement learning (RL) agents should learn not only to optimize returns for one specific task but also to constantly build more complex skills and scaffold their knowledge about the world, without forgetting what has already been learned. In this paper, we discuss the desired characteristics of environments that can support the training and evaluation of lifelong reinforcement learning agents, review existing environments from this perspective, and propose recommendations for devising suitable environments in the future. |
Tasks | |
Published | 2018-11-26 |
URL | http://arxiv.org/abs/1811.10732v2 |
http://arxiv.org/pdf/1811.10732v2.pdf | |
PWC | https://paperswithcode.com/paper/environments-for-lifelong-reinforcement |
Repo | |
Framework | |
A Deep Learning Architecture for De-identification of Patient Notes: Implementation and Evaluation
Title | A Deep Learning Architecture for De-identification of Patient Notes: Implementation and Evaluation |
Authors | Kaung Khin, Philipp Burckhardt, Rema Padman |
Abstract | De-identification is the process of removing 18 protected health information (PHI) from clinical notes in order for the text to be considered not individually identifiable. Recent advances in natural language processing (NLP) has allowed for the use of deep learning techniques for the task of de-identification. In this paper, we present a deep learning architecture that builds on the latest NLP advances by incorporating deep contextualized word embeddings and variational drop out Bi-LSTMs. We test this architecture on two gold standard datasets and show that the architecture achieves state-of-the-art performance on both data sets while also converging faster than other systems without the use of dictionaries or other knowledge sources. |
Tasks | Word Embeddings |
Published | 2018-10-03 |
URL | http://arxiv.org/abs/1810.01570v1 |
http://arxiv.org/pdf/1810.01570v1.pdf | |
PWC | https://paperswithcode.com/paper/a-deep-learning-architecture-for-de |
Repo | |
Framework | |
Fault Location in Power Distribution Systems via Deep Graph Convolutional Networks
Title | Fault Location in Power Distribution Systems via Deep Graph Convolutional Networks |
Authors | Kunjin Chen, Jun Hu, Yu Zhang, Zhanqing Yu, Jinliang He |
Abstract | This paper develops a novel graph convolutional network (GCN) framework for fault location in power distribution networks. The proposed approach integrates multiple measurements at different buses while taking system topology into account. The effectiveness of the GCN model is corroborated by the IEEE 123 bus benchmark system. Simulation results show that the GCN model significantly outperforms other widely-used machine learning schemes with very high fault location accuracy. In addition, the proposed approach is robust to measurement noise and data loss errors. Data visualization results of two competing neural networks are presented to explore the mechanism of GCN’s superior performance. A data augmentation procedure is proposed to increase the robustness of the model under various levels of noise and data loss errors. Further experiments show that the model can adapt to topology changes of distribution networks and perform well with a limited number of measured buses. |
Tasks | Data Augmentation |
Published | 2018-12-22 |
URL | https://arxiv.org/abs/1812.09464v2 |
https://arxiv.org/pdf/1812.09464v2.pdf | |
PWC | https://paperswithcode.com/paper/fault-location-in-power-distribution-systems |
Repo | |
Framework | |
Yedrouj-Net: An efficient CNN for spatial steganalysis
Title | Yedrouj-Net: An efficient CNN for spatial steganalysis |
Authors | Mehdi Yedroudj, Frederic Comby, Marc Chaumont |
Abstract | For about 10 years, detecting the presence of a secret message hidden in an image was performed with an Ensemble Classifier trained with Rich features. In recent years, studies such as Xu et al. have indicated that well-designed convolutional Neural Networks (CNN) can achieve comparable performance to the two-step machine learning approaches. In this paper, we propose a CNN that outperforms the state-ofthe-art in terms of error probability. The proposition is in the continuity of what has been recently proposed and it is a clever fusion of important bricks used in various papers. Among the essential parts of the CNN, one can cite the use of a pre-processing filterbank and a Truncation activation function, five convolutional layers with a Batch Normalization associated with a Scale Layer, as well as the use of a sufficiently sized fully connected section. An augmented database has also been used to improve the training of the CNN. Our CNN was experimentally evaluated against S-UNIWARD and WOW embedding algorithms and its performances were compared with those of three other methods: an Ensemble Classifier plus a Rich Model, and two other CNN steganalyzers. |
Tasks | |
Published | 2018-02-26 |
URL | http://arxiv.org/abs/1803.00407v1 |
http://arxiv.org/pdf/1803.00407v1.pdf | |
PWC | https://paperswithcode.com/paper/yedrouj-net-an-efficient-cnn-for-spatial |
Repo | |
Framework | |
Collective evolution of weights in wide neural networks
Title | Collective evolution of weights in wide neural networks |
Authors | Dmitry Yarotsky |
Abstract | We derive a nonlinear integro-differential transport equation describing collective evolution of weights under gradient descent in large-width neural-network-like models. We characterize stationary points of the evolution and analyze several scenarios where the transport equation can be solved approximately. We test our general method in the special case of linear free-knot splines, and find good agreement between theory and experiment in observations of global optima, stability of stationary points, and convergence rates. |
Tasks | |
Published | 2018-10-09 |
URL | http://arxiv.org/abs/1810.03974v1 |
http://arxiv.org/pdf/1810.03974v1.pdf | |
PWC | https://paperswithcode.com/paper/collective-evolution-of-weights-in-wide |
Repo | |
Framework | |
PolyNeuron: Automatic Neuron Discovery via Learned Polyharmonic Spline Activations
Title | PolyNeuron: Automatic Neuron Discovery via Learned Polyharmonic Spline Activations |
Authors | Andrew Hryniowski, Alexander Wong |
Abstract | Automated deep neural network architecture design has received a significant amount of recent attention. However, this attention has not been equally shared by one of the fundamental building blocks of a deep neural network, the neurons. In this study, we propose PolyNeuron, a novel automatic neuron discovery approach based on learned polyharmonic spline activations. More specifically, PolyNeuron revolves around learning polyharmonic splines, characterized by a set of control points, that represent the activation functions of the neurons in a deep neural network. A relaxed variant of PolyNeuron, which we term PolyNeuron-R, loosens the constraints imposed by PolyNeuron to reduce the computational complexity for discovering the neuron activation functions in an automated manner. Experiments show both PolyNeuron and PolyNeuron-R lead to networks that have improved or comparable performance on multiple network architectures (LeNet-5 and ResNet-20) using different datasets (MNIST and CIFAR10). As such, automatic neuron discovery approaches such as PolyNeuron is a worthy direction to explore. |
Tasks | |
Published | 2018-11-10 |
URL | http://arxiv.org/abs/1811.04303v1 |
http://arxiv.org/pdf/1811.04303v1.pdf | |
PWC | https://paperswithcode.com/paper/polyneuron-automatic-neuron-discovery-via |
Repo | |
Framework | |
Dual Pattern Learning Networks by Empirical Dual Prediction Risk Minimization
Title | Dual Pattern Learning Networks by Empirical Dual Prediction Risk Minimization |
Authors | Haimin Zhang, Min Xu |
Abstract | Motivated by the observation that humans can learn patterns from two given images at one time, we propose a dual pattern learning network architecture in this paper. Unlike conventional networks, the proposed architecture has two input branches and two loss functions. Instead of minimizing the empirical risk of a given dataset, dual pattern learning networks is trained by minimizing the empirical dual prediction loss. We show that this can improve the performance for single image classification. This architecture forces the network to learn discriminative class-specific features by analyzing and comparing two input images. In addition, the dual input structure allows the network to have a considerably large number of image pairs, which can help address the overfitting issue due to limited training data. Moreover, we propose to associate each input branch with a random interest value for learning corresponding image during training. This method can be seen as a stochastic regularization technique, and can further lead to generalization performance improvement. State-of-the-art deep networks can be adapted to dual pattern learning networks without increasing the same number of parameters. Extensive experiments on CIFAR-10, CIFAR- 100, FI-8, Google commands dataset, and MNIST demonstrate that our DPLNets exhibit better performance than original networks. The experimental results on subsets of CIFAR- 10, CIFAR-100, and MNIST demonstrate that dual pattern learning networks have good generalization performance on small datasets. |
Tasks | Image Classification |
Published | 2018-06-11 |
URL | http://arxiv.org/abs/1806.03902v1 |
http://arxiv.org/pdf/1806.03902v1.pdf | |
PWC | https://paperswithcode.com/paper/dual-pattern-learning-networks-by-empirical |
Repo | |
Framework | |
Privacy Mining from IoT-based Smart Homes
Title | Privacy Mining from IoT-based Smart Homes |
Authors | Ming-Chang Lee, Jia-Chun Lin, Olaf Owe |
Abstract | Recently, a wide range of smart devices are deployed in a variety of environments to improve the quality of human life. One of the important IoT-based applications is smart homes for healthcare, especially for elders. IoT-based smart homes enable elders’ health to be properly monitored and taken care of. However, elders’ privacy might be disclosed from smart homes due to non-fully protected network communication or other reasons. To demonstrate how serious this issue is, we introduce in this paper a Privacy Mining Approach (PMA) to mine privacy from smart homes by conducting a series of deductions and analyses on sensor datasets generated by smart homes. The experimental results demonstrate that PMA is able to deduce a global sensor topology for a smart home and disclose elders’ privacy in terms of their house layouts. |
Tasks | |
Published | 2018-08-18 |
URL | http://arxiv.org/abs/1808.07379v2 |
http://arxiv.org/pdf/1808.07379v2.pdf | |
PWC | https://paperswithcode.com/paper/privacy-mining-from-iot-based-smart-homes |
Repo | |
Framework | |
r-Instance Learning for Missing People Tweets Identification
Title | r-Instance Learning for Missing People Tweets Identification |
Authors | Yang Yang, Haoyan Liu, Xia Hu, Jiawei Zhang, Xiaoming Zhang, Zhoujun Li, Philip S. Yu |
Abstract | The number of missing people (i.e., people who get lost) greatly increases in recent years. It is a serious worldwide problem, and finding the missing people consumes a large amount of social resources. In tracking and finding these missing people, timely data gathering and analysis actually play an important role. With the development of social media, information about missing people can get propagated through the web very quickly, which provides a promising way to solve the problem. The information in online social media is usually of heterogeneous categories, involving both complex social interactions and textual data of diverse structures. Effective fusion of these different types of information for addressing the missing people identification problem can be a great challenge. Motivated by the multi-instance learning problem and existing social science theory of “homophily”, in this paper, we propose a novel r-instance (RI) learning model. |
Tasks | |
Published | 2018-05-28 |
URL | http://arxiv.org/abs/1805.10856v2 |
http://arxiv.org/pdf/1805.10856v2.pdf | |
PWC | https://paperswithcode.com/paper/r-instance-learning-for-missing-people-tweets |
Repo | |
Framework | |
Proceedings of eNTERFACE 2015 Workshop on Intelligent Interfaces
Title | Proceedings of eNTERFACE 2015 Workshop on Intelligent Interfaces |
Authors | Matei Mancas, Christian Frisson, Joëlle Tilmanne, Nicolas d’Alessandro, Petr Barborka, Furkan Bayansar, Francisco Bernard, Rebecca Fiebrink, Alexis Heloir, Edgar Hemery, Sohaib Laraba, Alexis Moinet, Fabrizio Nunnari, Thierry Ravet, Loïc Reboursière, Alvaro Sarasua, Mickaël Tits, Noé Tits, François Zajéga, Paolo Alborno, Ksenia Kolykhalova, Emma Frid, Damiano Malafronte, Lisanne Huis in’t Veld, Hüseyin Cakmak, Kevin El Haddad, Nicolas Riche, Julien Leroy, Pierre Marighetto, Bekir Berker Türker, Hossein Khaki, Roberto Pulisci, Emer Gilmartin, Fasih Haider, Kübra Cengiz, Martin Sulir, Ilaria Torre, Shabbir Marzban, Ramazan Yazıcı, Furkan Burak Bâgcı, Vedat Gazi Kılı, Hilal Sezer, Sena Büsra Yenge, Charles-Alexandre Delestage, Sylvie Leleu-Merviel, Muriel Meyer-Chemenska, Daniel Schmitt, Willy Yvart, Stéphane Dupont, Ozan Can Altiok, Aysegül Bumin, Ceren Dikmen, Ivan Giangreco, Silvan Heller, Emre Külah, Gueorgui Pironkov, Luca Rossetto, Yusuf Sahillioglu, Heiko Schuldt, Omar Seddati, Yusuf Setinkaya, Metin Sezgin, Claudiu Tanase, Emre Toyan, Sean Wood, Doguhan Yeke, Françcois Rocca, Pierre-Henri De Deken, Alessandra Bandrabur, Fabien Grisard, Axel Jean-Caurant, Vincent Courboulay, Radhwan Ben Madhkour, Ambroise Moreau |
Abstract | The 11th Summer Workshop on Multimodal Interfaces eNTERFACE 2015 was hosted by the Numediart Institute of Creative Technologies of the University of Mons from August 10th to September 2015. During the four weeks, students and researchers from all over the world came together in the Numediart Institute of the University of Mons to work on eight selected projects structured around intelligent interfaces. Eight projects were selected and their reports are shown here. |
Tasks | |
Published | 2018-01-19 |
URL | http://arxiv.org/abs/1801.06349v1 |
http://arxiv.org/pdf/1801.06349v1.pdf | |
PWC | https://paperswithcode.com/paper/proceedings-of-enterface-2015-workshop-on |
Repo | |
Framework | |
SepNE: Bringing Separability to Network Embedding
Title | SepNE: Bringing Separability to Network Embedding |
Authors | Ziyao Li, Liang Zhang, Guojie Song |
Abstract | Many successful methods have been proposed for learning low dimensional representations on large-scale networks, while almost all existing methods are designed in inseparable processes, learning embeddings for entire networks even when only a small proportion of nodes are of interest. This leads to great inconvenience, especially on super-large or dynamic networks, where these methods become almost impossible to implement. In this paper, we formalize the problem of separated matrix factorization, based on which we elaborate a novel objective function that preserves both local and global information. We further propose SepNE, a simple and flexible network embedding algorithm which independently learns representations for different subsets of nodes in separated processes. By implementing separability, our algorithm reduces the redundant efforts to embed irrelevant nodes, yielding scalability to super-large networks, automatic implementation in distributed learning and further adaptations. We demonstrate the effectiveness of this approach on several real-world networks with different scales and subjects. With comparable accuracy, our approach significantly outperforms state-of-the-art baselines in running times on large networks. |
Tasks | Network Embedding |
Published | 2018-11-14 |
URL | http://arxiv.org/abs/1811.05614v2 |
http://arxiv.org/pdf/1811.05614v2.pdf | |
PWC | https://paperswithcode.com/paper/sepne-bringing-separability-to-network |
Repo | |
Framework | |
Research on Artificial Intelligence Ethics Based on the Evolution of Population Knowledge Base
Title | Research on Artificial Intelligence Ethics Based on the Evolution of Population Knowledge Base |
Authors | Feng Liu, Yong Shi |
Abstract | The unclear development direction of human society is a deep reason for that it is difficult to form a uniform ethical standard for human society and artificial intelligence. Since the 21st century, the latest advances in the Internet, brain science and artificial intelligence have brought new inspiration to the research on the development direction of human society. Through the study of the Internet brain model, AI IQ evaluation, and the evolution of the brain, this paper proposes that the evolution of population knowledge base is the key for judging the development direction of human society, thereby discussing the standards and norms for the construction of artificial intelligence ethics. |
Tasks | |
Published | 2018-06-09 |
URL | http://arxiv.org/abs/1806.10095v3 |
http://arxiv.org/pdf/1806.10095v3.pdf | |
PWC | https://paperswithcode.com/paper/research-on-artificial-intelligence-ethics |
Repo | |
Framework | |