Paper Group ANR 1609
Virtual organelle self-coding for fluorescence imaging via adversarial learning. Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding. Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks. Combining Anatomical and Functional Networks for N …
Virtual organelle self-coding for fluorescence imaging via adversarial learning
| Title | Virtual organelle self-coding for fluorescence imaging via adversarial learning |
| Authors | Thanh Nguyen, Vy Bui, Anh Thai, Van Lam, Christopher B. Raub, Lin-Ching Chang, George Nehmetallah |
| Abstract | Fluorescence microscopy plays a vital role in understanding the subcellular structures of living cells. However, it requires considerable effort in sample preparation related to chemical fixation, staining, cost, and time. To reduce those factors, we present a virtual fluorescence staining method based on deep neural networks (VirFluoNet) to transform fluorescence images of molecular labels into other molecular fluorescence labels in the same field-of-view. To achieve this goal, we develop and train a conditional generative adversarial network (cGAN) to perform digital fluorescence imaging demonstrated on human osteosarcoma U2OS cell fluorescence images captured under Cell Painting staining protocol. A detailed comparative analysis is also conducted on the performance of the cGAN network between predicting fluorescence channels based on phase contrast or based on another fluorescence channel using human breast cancer MDA-MB-231 cell line as a test case. In addition, we implement a deep learning model to perform autofocusing on another human U2OS fluorescence dataset as a preprocessing step to defocus an out-focus channel in U2OS dataset. A quantitative index of image prediction error is introduced based on signal pixel-wise spatial and intensity differences with ground truth to evaluate the performance of prediction to high-complex and throughput fluorescence. This index provides a rational way to perform image segmentation on error signals and to understand the likelihood of mis-interpreting biology from the predicted image. In total, these findings contribute to the utility of deep learning image regression for fluorescence microscopy datasets of biological cells, balanced against savings of cost, time, and experimental effort. Furthermore, the approach introduced here holds promise for modeling the internal relationships between organelles and biomolecules within living cells. |
| Tasks | Semantic Segmentation |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04518v1 |
| https://arxiv.org/pdf/1909.04518v1.pdf | |
| PWC | https://paperswithcode.com/paper/virtual-organelle-self-coding-for |
| Repo | |
| Framework | |
Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding
| Title | Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding |
| Authors | Utku Ozbulak, Arnout Van Messem, Wesley De Neve |
| Abstract | Detecting adversarial examples currently stands as one of the biggest challenges in the field of deep learning. Adversarial attacks, which produce adversarial examples, increase the prediction likelihood of a target class for a particular data point. During this process, the adversarial example can be further optimized, even when it has already been wrongly classified with 100% confidence, thus making the adversarial example even more difficult to detect. For this kind of adversarial examples, which we refer to as over-optimized adversarial examples, we discovered that the logits of the model provide solid clues on whether the data point at hand is adversarial or genuine. In this context, we first discuss the masking effect of the softmax function for the prediction made and explain why the logits of the model are more useful in detecting over-optimized adversarial examples. To identify this type of adversarial examples in practice, we propose a non-parametric and computationally efficient method which relies on interquartile range, with this method becoming more effective as the image resolution increases. We support our observations throughout the paper with detailed experiments for different datasets (MNIST, CIFAR-10, and ImageNet) and several architectures. |
| Tasks | |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.12744v1 |
| https://arxiv.org/pdf/1907.12744v1.pdf | |
| PWC | https://paperswithcode.com/paper/not-all-adversarial-examples-require-a |
| Repo | |
| Framework | |
Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks
| Title | Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks |
| Authors | Domen Tabernik, Matej Kristan, Aleš Leonardis |
| Abstract | Convolutional neural networks excel in a number of computer vision tasks. One of their most crucial architectural elements is the effective receptive field size, that has to be manually set to accommodate a specific task. Standard solutions involve large kernels, down/up-sampling and dilated convolutions. These require testing a variety of dilation and down/up-sampling factors and result in non-compact representations and excessive number of parameters. We address this issue by proposing a new convolution filter composed of displaced aggregation units (DAU). DAUs learn spatial displacements and adapt the receptive field sizes of individual convolution filters to a given problem, thus eliminating the need for hand-crafted modifications. DAUs provide a seamless substitution of convolutional filters in existing state-of-the-art architectures, which we demonstrate on AlexNet, ResNet50, ResNet101, DeepLab and SRN-DeblurNet. The benefits of this design are demonstrated on a variety of computer vision tasks and datasets, such as image classification (ILSVRC 2012), semantic segmentation (PASCAL VOC 2011, Cityscape) and blind image de-blurring (GOPRO). Results show that DAUs efficiently allocate parameters resulting in up to four times more compact networks at similar or better performance. |
| Tasks | Image Classification, Semantic Segmentation |
| Published | 2019-02-20 |
| URL | https://arxiv.org/abs/1902.07474v2 |
| https://arxiv.org/pdf/1902.07474v2.pdf | |
| PWC | https://paperswithcode.com/paper/spatially-adaptive-filter-units-for-compact |
| Repo | |
| Framework | |
Combining Anatomical and Functional Networks for Neuropathology Identification: A Case Study on Autism Spectrum Disorder
| Title | Combining Anatomical and Functional Networks for Neuropathology Identification: A Case Study on Autism Spectrum Disorder |
| Authors | Sarah Itani, Dorina Thanou |
| Abstract | While the prevalence of Autism Spectrum Disorder (ASD) is increasing, research towards the definition of a common etiology is still ongoing. In this regard, modern machine learning and network science pave the way for a better understanding of the pathology and the development of diagnosis aid systems. At the same time, the culture of data sharing heads favorably in that direction, with the availability of large datasets such as the Autism Brain Imaging Data Exchange (ABIDE) one. The present work addresses the classification of neurotypical and ASD subjects by combining knowledge about both the anatomy and the functional activity of the brain. In particular, we model the brain structure as a graph, and the time-varying resting-state functional MRI (rs-fMRI) signals as values that live on the nodes of that graph. We then borrow tools from the emerging field of Graph Signal Processing (GSP) to build features related to the frequency content of these signals. In order to make these features highly discriminative, we apply an extension of the Fukunaga-Koontz transform. Finally, we use these new markers to train a decision tree, an interpretable classification scheme, which results in a final diagnosis aid model. Interestingly, the resulting decision tree outperforms state-of-the-art methods on the ABIDE dataset. Moreover, the analysis of the predictive markers reveals the influence of the frontal and temporal lobes in the diagnosis of the disorder, which is in line with previous findings in the literature of neuroscience. Our results indicate that exploiting jointly structural and functional information of the brain can reveal important information about the complexity of the neuropathology. |
| Tasks | |
| Published | 2019-04-25 |
| URL | http://arxiv.org/abs/1904.11296v1 |
| http://arxiv.org/pdf/1904.11296v1.pdf | |
| PWC | https://paperswithcode.com/paper/combining-anatomical-and-functional-networks |
| Repo | |
| Framework | |
Locale-agnostic Universal Domain Classification Model in Spoken Language Understanding
| Title | Locale-agnostic Universal Domain Classification Model in Spoken Language Understanding |
| Authors | Jihwan Lee, Ruhi Sarikaya, Young-Bum Kim |
| Abstract | In this paper, we introduce an approach for leveraging available data across multiple locales sharing the same language to 1) improve domain classification model accuracy in Spoken Language Understanding and user experience even if new locales do not have sufficient data and 2) reduce the cost of scaling the domain classifier to a large number of locales. We propose a locale-agnostic universal domain classification model based on selective multi-task learning that learns a joint representation of an utterance over locales with different sets of domains and allows locales to share knowledge selectively depending on the domains. The experimental results demonstrate the effectiveness of our approach on domain classification task in the scenario of multiple locales with imbalanced data and disparate domain sets. The proposed approach outperforms other baselines models especially when classifying locale-specific domains and also low-resourced domains. |
| Tasks | Multi-Task Learning, Spoken Language Understanding |
| Published | 2019-05-02 |
| URL | https://arxiv.org/abs/1905.00924v1 |
| https://arxiv.org/pdf/1905.00924v1.pdf | |
| PWC | https://paperswithcode.com/paper/locale-agnostic-universal-domain |
| Repo | |
| Framework | |
Distributed Layer-Partitioned Training for Privacy-Preserved Deep Learning
| Title | Distributed Layer-Partitioned Training for Privacy-Preserved Deep Learning |
| Authors | Chun-Hsien Yu, Chun-Nan Chou, Emily Chang |
| Abstract | Deep Learning techniques have achieved remarkable results in many domains. Often, training deep learning models requires large datasets, which may require sensitive information to be uploaded to the cloud to accelerate training. To adequately protect sensitive information, we propose distributed layer-partitioned training with step-wise activation functions for privacy-preserving deep learning. Experimental results attest our method to be simple and effective. |
| Tasks | Privacy Preserving Deep Learning |
| Published | 2019-04-12 |
| URL | http://arxiv.org/abs/1904.06049v1 |
| http://arxiv.org/pdf/1904.06049v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-layer-partitioned-training-for |
| Repo | |
| Framework | |
Solving NP-Hard Problems on Graphs with Extended AlphaGo Zero
| Title | Solving NP-Hard Problems on Graphs with Extended AlphaGo Zero |
| Authors | Kenshin Abe, Zijian Xu, Issei Sato, Masashi Sugiyama |
| Abstract | There have been increasing challenges to solve combinatorial optimization problems by machine learning. Khalil et al. proposed an end-to-end reinforcement learning framework, S2V-DQN, which automatically learns graph embeddings to construct solutions to a wide range of problems. To improve the generalization ability of their Q-learning method, we propose a novel learning strategy based on AlphaGo Zero which is a Go engine that achieved a superhuman level without the domain knowledge of the game. Our framework is redesigned for combinatorial problems, where the final reward might take any real number instead of a binary response, win/lose. In experiments conducted for five kinds of NP-hard problems including {\sc MinimumVertexCover} and {\sc MaxCut}, our method is shown to generalize better to various graphs than S2V-DQN. Furthermore, our method can be combined with recently-developed graph neural network (GNN) models such as the \emph{Graph Isomorphism Network}, resulting in even better performance. This experiment also gives an interesting insight into a suitable choice of GNN models for each task. |
| Tasks | Combinatorial Optimization, Q-Learning |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11623v2 |
| https://arxiv.org/pdf/1905.11623v2.pdf | |
| PWC | https://paperswithcode.com/paper/solving-np-hard-problems-on-graphs-by |
| Repo | |
| Framework | |
Deep neural network Grad-Shafranov solver constrained with measured magnetic signals
| Title | Deep neural network Grad-Shafranov solver constrained with measured magnetic signals |
| Authors | Semin Joung, Jaewook Kim, Sehyun Kwak, J. G. Bak, S. G. Lee, H. S. Han, H. S. Kim, Geunho Lee, Daeho Kwon, Y. -c. Ghim |
| Abstract | A neural network solving Grad-Shafranov equation constrained with measured magnetic signals to reconstruct magnetic equilibria in real time is developed. Database created to optimize the neural network’s free parameters contain off-line EFIT results as the output of the network from $1,118$ KSTAR experimental discharges of two different campaigns. Input data to the network constitute magnetic signals measured by a Rogowski coil (plasma current), magnetic pick-up coils (normal and tangential components of magnetic fields) and flux loops (poloidal magnetic fluxes). The developed neural networks fully reconstruct not only the poloidal flux function $\psi\left( R, Z\right)$ but also the toroidal current density function $j_\phi\left( R, Z\right)$ with the off-line EFIT quality. To preserve robustness of the networks against a few missing input data, an imputation scheme is utilized to eliminate the required additional training sets with large number of possible combinations of the missing inputs. |
| Tasks | Imputation |
| Published | 2019-11-07 |
| URL | https://arxiv.org/abs/1911.02882v1 |
| https://arxiv.org/pdf/1911.02882v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-neural-network-grad-shafranov-solver |
| Repo | |
| Framework | |
Demographic Inference and Representative Population Estimates from Multilingual Social Media Data
| Title | Demographic Inference and Representative Population Estimates from Multilingual Social Media Data |
| Authors | Zijian Wang, Scott A. Hale, David Adelani, Przemyslaw A. Grabowicz, Timo Hartmann, Fabian Flöck, David Jurgens |
| Abstract | Social media provide access to behavioural data at an unprecedented scale and granularity. However, using these data to understand phenomena in a broader population is difficult due to their non-representativeness and the bias of statistical inference tools towards dominant languages and groups. While demographic attribute inference could be used to mitigate such bias, current techniques are almost entirely monolingual and fail to work in a global environment. We address these challenges by combining multilingual demographic inference with post-stratification to create a more representative population sample. To learn demographic attributes, we create a new multimodal deep neural architecture for joint classification of age, gender, and organization-status of social media users that operates in 32 languages. This method substantially outperforms current state of the art while also reducing algorithmic bias. To correct for sampling biases, we propose fully interpretable multilevel regression methods that estimate inclusion probabilities from inferred joint population counts and ground-truth population counts. In a large experiment over multilingual heterogeneous European regions, we show that our demographic inference and bias correction together allow for more accurate estimates of populations and make a significant step towards representative social sensing in downstream applications with multilingual social media. |
| Tasks | |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.05961v1 |
| https://arxiv.org/pdf/1905.05961v1.pdf | |
| PWC | https://paperswithcode.com/paper/demographic-inference-and-representative |
| Repo | |
| Framework | |
Disguised-Nets: Image Disguising for Privacy-preserving Outsourced Deep Learning
| Title | Disguised-Nets: Image Disguising for Privacy-preserving Outsourced Deep Learning |
| Authors | Sagar Sharma, Keke Chen |
| Abstract | Deep learning model developers often use cloud GPU resources to experiment with large data and models that need expensive setups. However, this practice raises privacy concerns. Adversaries may be interested in: 1) personally identifiable information or objects encoded in the training images, and 2) the models trained with sensitive data to launch model-based attacks. Learning deep neural networks (DNN) from encrypted data is still impractical due to the large training data and the expensive learning process. A few recent studies have tried to provide efficient, practical solutions to protect data privacy in outsourced deep-learning. However, we find out that they are vulnerable under certain attacks. In this paper, we specifically identify two types of unique attacks on outsourced deep-learning: 1) the visual re-identification attack on the training data, and 2) the class membership attack on the learned models, which can break existing privacy-preserving solutions. We develop an image disguising approach to address these attacks and design a suite of methods to evaluate the levels of attack resilience for a privacy-preserving solution for outsourced deep learning. The experimental results show that our image-disguising mechanisms can provide a high level of protection against the two attacks while still generating high-quality DNN models for image classification. |
| Tasks | Image Classification, Privacy Preserving Deep Learning |
| Published | 2019-02-05 |
| URL | http://arxiv.org/abs/1902.01878v2 |
| http://arxiv.org/pdf/1902.01878v2.pdf | |
| PWC | https://paperswithcode.com/paper/disguised-nets-image-disguising-for-privacy |
| Repo | |
| Framework | |
Speech bandwidth extension with WaveNet
| Title | Speech bandwidth extension with WaveNet |
| Authors | Archit Gupta, Brendan Shillingford, Yannis Assael, Thomas C. Walters |
| Abstract | Large-scale mobile communication systems tend to contain legacy transmission channels with narrowband bottlenecks, resulting in characteristic “telephone-quality” audio. While higher quality codecs exist, due to the scale and heterogeneity of the networks, transmitting higher sample rate audio with modern high-quality audio codecs can be difficult in practice. This paper proposes an approach where a communication node can instead extend the bandwidth of a band-limited incoming speech signal that may have been passed through a low-rate codec. To this end, we propose a WaveNet-based model conditioned on a log-mel spectrogram representation of a bandwidth-constrained speech audio signal of 8 kHz and audio with artifacts from GSM full-rate (FR) compression to reconstruct the higher-resolution signal. In our experimental MUSHRA evaluation, we show that a model trained to upsample to 24kHz speech signals from audio passed through the 8kHz GSM-FR codec is able to reconstruct audio only slightly lower in quality to that of the Adaptive Multi-Rate Wideband audio codec (AMR-WB) codec at 16kHz, and closes around half the gap in perceptual quality between the original encoded signal and the original speech sampled at 24kHz. We further show that when the same model is passed 8kHz audio that has not been compressed, is able to again reconstruct audio of slightly better quality than 16kHz AMR-WB, in the same MUSHRA evaluation. |
| Tasks | |
| Published | 2019-07-05 |
| URL | https://arxiv.org/abs/1907.04927v1 |
| https://arxiv.org/pdf/1907.04927v1.pdf | |
| PWC | https://paperswithcode.com/paper/speech-bandwidth-extension-with-wavenet |
| Repo | |
| Framework | |
Unsupervised Discovery of Gendered Language through Latent-Variable Modeling
| Title | Unsupervised Discovery of Gendered Language through Latent-Variable Modeling |
| Authors | Alexander Hoyle, Wolf-Sonkin, Hanna Wallach, Isabelle Augenstein, Ryan Cotterell |
| Abstract | Studying the ways in which language is gendered has long been an area of interest in sociolinguistics. Studies have explored, for example, the speech of male and female characters in film and the language used to describe male and female politicians. In this paper, we aim not to merely study this phenomenon qualitatively, but instead to quantify the degree to which the language used to describe men and women is different and, moreover, different in a positive or negative way. To that end, we introduce a generative latent-variable model that jointly represents adjective (or verb) choice, with its sentiment, given the natural gender of a head (or dependent) noun. We find that there are significant differences between descriptions of male and female nouns and that these differences align with common gender stereotypes: Positive adjectives used to describe women are more often related to their bodies than adjectives used to describe men. |
| Tasks | |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04760v1 |
| https://arxiv.org/pdf/1906.04760v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-discovery-of-gendered-language |
| Repo | |
| Framework | |
Enumeration of Distinct Support Vectors for Interactive Decision Making
| Title | Enumeration of Distinct Support Vectors for Interactive Decision Making |
| Authors | Kentaro Kanamori, Satoshi Hara, Masakazu Ishihata, Hiroki Arimura |
| Abstract | In conventional prediction tasks, a machine learning algorithm outputs a single best model that globally optimizes its objective function, which typically is accuracy. Therefore, users cannot access the other models explicitly. In contrast to this, multiple model enumeration attracts increasing interests in non-standard machine learning applications where other criteria, e.g., interpretability or fairness, than accuracy are main concern and a user may want to access more than one non-optimal, but suitable models. In this paper, we propose a K-best model enumeration algorithm for Support Vector Machines (SVM) that given a dataset S and an integer K>0, enumerates the K-best models on S with distinct support vectors in the descending order of the objective function values in the dual SVM problem. Based on analysis of the lattice structure of support vectors, our algorithm efficiently finds the next best model with small latency. This is useful in supporting users’s interactive examination of their requirements on enumerated models. By experiments on real datasets, we evaluated the efficiency and usefulness of our algorithm. |
| Tasks | Decision Making |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.01876v1 |
| https://arxiv.org/pdf/1906.01876v1.pdf | |
| PWC | https://paperswithcode.com/paper/enumeration-of-distinct-support-vectors-for |
| Repo | |
| Framework | |
Dynamic Malware Analysis with Feature Engineering and Feature Learning
| Title | Dynamic Malware Analysis with Feature Engineering and Feature Learning |
| Authors | Zhaoqi Zhang, Panpan Qi, Wei Wang |
| Abstract | Dynamic malware analysis executes the program in an isolated environment and monitors its run-time behaviour (e.g. system API calls) for malware detection. This technique has been proven to be effective against various code obfuscation techniques and newly released (“zero-day”) malware. However, existing works typically only consider the API name while ignoring the arguments, or require complex feature engineering operations and expert knowledge to process the arguments. In this paper, we propose a novel and low-cost feature extraction approach, and an effective deep neural network architecture for accurate and fast malware detection. Specifically, the feature representation approach utilizes a feature hashing trick to encode the API call arguments associated with the API name. The deep neural network architecture applies multiple Gated-CNNs (convolutional neural networks) to transform the extracted features of each API call. The outputs are further processed through bidirectional LSTM (long-short term memory networks) to learn the sequential correlation among API calls. Experiments show that our solution outperforms baselines significantly on a large real dataset. Valuable insights about feature engineering and architecture design are derived from the ablation study. |
| Tasks | Feature Engineering, Malware Detection |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.07352v5 |
| https://arxiv.org/pdf/1907.07352v5.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-malware-analysis-with-feature |
| Repo | |
| Framework | |
Activity2Vec: Learning ADL Embeddings from Sensor Data with a Sequence-to-Sequence Model
| Title | Activity2Vec: Learning ADL Embeddings from Sensor Data with a Sequence-to-Sequence Model |
| Authors | Alireza Ghods, Diane J. Cook |
| Abstract | Recognizing activities of daily living (ADLs) plays an essential role in analyzing human health and behavior. The widespread availability of sensors implanted in homes, smartphones, and smart watches have engendered collection of big datasets that reflect human behavior. To obtain a machine learning model based on these data,researchers have developed multiple feature extraction methods. In this study, we investigate a method for automatically extracting universal and meaningful features that are applicable across similar time series-based learning tasks such as activity recognition and fall detection. We propose creating a sequence-to-sequence (seq2seq) model to perform this feature learning. Beside avoiding feature engineering, the meaningful features learned by the seq2seq model can also be utilized for semi-supervised learning. We evaluate both of these benefits on datasets collected from wearable and ambient sensors. |
| Tasks | Activity Recognition, Feature Engineering, Time Series |
| Published | 2019-07-12 |
| URL | https://arxiv.org/abs/1907.05597v1 |
| https://arxiv.org/pdf/1907.05597v1.pdf | |
| PWC | https://paperswithcode.com/paper/activity2vec-learning-adl-embeddings-from |
| Repo | |
| Framework | |
