Paper Group ANR 850
Spectral Signatures in Backdoor Attacks. ScarGAN: Chained Generative Adversarial Networks to Simulate Pathological Tissue on Cardiovascular MR Scans. Pool-Based Sequential Active Learning for Regression. Parameters identification method for breast biomechanical numerical model. Deep Covariance Descriptors for Facial Expression Recognition. Human Em …
Spectral Signatures in Backdoor Attacks
| Title | Spectral Signatures in Backdoor Attacks |
| Authors | Brandon Tran, Jerry Li, Aleksander Madry |
| Abstract | A recent line of work has uncovered a new form of data poisoning: so-called \emph{backdoor} attacks. These attacks are particularly dangerous because they do not affect a network’s behavior on typical, benign data. Rather, the network only deviates from its expected output when triggered by a perturbation planted by an adversary. In this paper, we identify a new property of all known backdoor attacks, which we call \emph{spectral signatures}. This property allows us to utilize tools from robust statistics to thwart the attacks. We demonstrate the efficacy of these signatures in detecting and removing poisoned examples on real image sets and state of the art neural network architectures. We believe that understanding spectral signatures is a crucial first step towards designing ML systems secure against such backdoor attacks |
| Tasks | data poisoning |
| Published | 2018-11-01 |
| URL | http://arxiv.org/abs/1811.00636v1 |
| http://arxiv.org/pdf/1811.00636v1.pdf | |
| PWC | https://paperswithcode.com/paper/spectral-signatures-in-backdoor-attacks |
| Repo | |
| Framework | |
ScarGAN: Chained Generative Adversarial Networks to Simulate Pathological Tissue on Cardiovascular MR Scans
| Title | ScarGAN: Chained Generative Adversarial Networks to Simulate Pathological Tissue on Cardiovascular MR Scans |
| Authors | Felix Lau, Tom Hendriks, Jesse Lieman-Sifry, Berk Norman, Sean Sall, Daniel Golden |
| Abstract | Medical images with specific pathologies are scarce, but a large amount of data is usually required for a deep convolutional neural network (DCNN) to achieve good accuracy. We consider the problem of segmenting the left ventricular (LV) myocardium on late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) scans of which only some of the scans have scar tissue. We propose ScarGAN to simulate scar tissue on healthy myocardium using chained generative adversarial networks (GAN). Our novel approach factorizes the simulation process into 3 steps: 1) a mask generator to simulate the shape of the scar tissue; 2) a domain-specific heuristic to produce the initial simulated scar tissue from the simulated shape; 3) a refining generator to add details to the simulated scar tissue. Unlike other approaches that generate samples from scratch, we simulate scar tissue on normal scans resulting in highly realistic samples. We show that experienced radiologists are unable to distinguish between real and simulated scar tissue. Training a U-Net with additional scans with scar tissue simulated by ScarGAN increases the percentage of scar pixels correctly included in LV myocardium prediction from 75.9% to 80.5%. |
| Tasks | |
| Published | 2018-08-14 |
| URL | http://arxiv.org/abs/1808.04500v1 |
| http://arxiv.org/pdf/1808.04500v1.pdf | |
| PWC | https://paperswithcode.com/paper/scargan-chained-generative-adversarial |
| Repo | |
| Framework | |
Pool-Based Sequential Active Learning for Regression
| Title | Pool-Based Sequential Active Learning for Regression |
| Authors | Dongrui Wu |
| Abstract | Active learning is a machine learning approach for reducing the data labeling effort. Given a pool of unlabeled samples, it tries to select the most useful ones to label so that a model built from them can achieve the best possible performance. This paper focuses on pool-based sequential active learning for regression (ALR). We first propose three essential criteria that an ALR approach should consider in selecting the most useful unlabeled samples: informativeness, representativeness, and diversity, and compare four existing ALR approaches against them. We then propose a new ALR approach using passive sampling, which considers both the representativeness and the diversity in both the initialization and subsequent iterations. Remarkably, this approach can also be integrated with other existing ALR approaches in the literature to further improve the performance. Extensive experiments on 11 UCI, CMU StatLib, and UFL Media Core datasets from various domains verified the effectiveness of our proposed ALR approaches. |
| Tasks | Active Learning |
| Published | 2018-05-12 |
| URL | http://arxiv.org/abs/1805.04735v1 |
| http://arxiv.org/pdf/1805.04735v1.pdf | |
| PWC | https://paperswithcode.com/paper/pool-based-sequential-active-learning-for |
| Repo | |
| Framework | |
Parameters identification method for breast biomechanical numerical model
| Title | Parameters identification method for breast biomechanical numerical model |
| Authors | Diogo Lopes, Stéphane Clain, António Ramires Fernandes |
| Abstract | Bio-mechanical breast simulations are based on a gravity free geometry as a reference domain and a nonlinear mechanical model parameterised by physical coefficients. As opposed to complex models proposed in the literature based on medical imagery, we propose a simple but yet realistic model that uses a basic set of measurements easy to realise in the context of routinely operations. Both the mechanical system and the geometry are controlled with parameters we shall identify in an optimisation procedure. We give a detailed presentation of the model together with the optimisation method and the associated discretisation. Sensitivity analysis is then carried out to evaluate the robustness of the method. |
| Tasks | |
| Published | 2018-12-06 |
| URL | https://arxiv.org/abs/1901.00518v2 |
| https://arxiv.org/pdf/1901.00518v2.pdf | |
| PWC | https://paperswithcode.com/paper/parameters-identification-method-for-breast |
| Repo | |
| Framework | |
Deep Covariance Descriptors for Facial Expression Recognition
| Title | Deep Covariance Descriptors for Facial Expression Recognition |
| Authors | Naima Otberdout, Anis Kacem, Mohamed Daoudi, Lahoucine Ballihi, Stefano Berretti |
| Abstract | In this paper, covariance matrices are exploited to encode the deep convolutional neural networks (DCNN) features for facial expression recognition. The space geometry of the covariance matrices is that of Symmetric Positive Definite (SPD) matrices. By performing the classification of the facial expressions using Gaussian kernel on SPD manifold, we show that the covariance descriptors computed on DCNN features are more efficient than the standard classification with fully connected layers and softmax. By implementing our approach using the VGG-face and ExpNet architectures with extensive experiments on the Oulu-CASIA and SFEW datasets, we show that the proposed approach achieves performance at the state of the art for facial expression recognition. |
| Tasks | Facial Expression Recognition |
| Published | 2018-05-10 |
| URL | http://arxiv.org/abs/1805.03869v1 |
| http://arxiv.org/pdf/1805.03869v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-covariance-descriptors-for-facial |
| Repo | |
| Framework | |
Human Emotional Facial Expression Recognition
| Title | Human Emotional Facial Expression Recognition |
| Authors | Chendi Wang |
| Abstract | An automatic Facial Expression Recognition (FER) model with Adaboost face detector, feature selection based on manifold learning and synergetic prototype based classifier has been proposed. Improved feature selection method and proposed classifier can achieve favorable effectiveness to performance FER in reasonable processing time. |
| Tasks | Facial Expression Recognition, Feature Selection |
| Published | 2018-03-28 |
| URL | http://arxiv.org/abs/1803.10864v1 |
| http://arxiv.org/pdf/1803.10864v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-emotional-facial-expression-recognition |
| Repo | |
| Framework | |
Regularizing Output Distribution of Abstractive Chinese Social Media Text Summarization for Improved Semantic Consistency
| Title | Regularizing Output Distribution of Abstractive Chinese Social Media Text Summarization for Improved Semantic Consistency |
| Authors | Bingzhen Wei, Xuancheng Ren, Xu Sun, Yi Zhang, Xiaoyan Cai, Qi Su |
| Abstract | Abstractive text summarization is a highly difficult problem, and the sequence-to-sequence model has shown success in improving the performance on the task. However, the generated summaries are often inconsistent with the source content in semantics. In such cases, when generating summaries, the model selects semantically unrelated words with respect to the source content as the most probable output. The problem can be attributed to heuristically constructed training data, where summaries can be unrelated to the source content, thus containing semantically unrelated words and spurious word correspondence. In this paper, we propose a regularization approach for the sequence-to-sequence model and make use of what the model has learned to regularize the learning objective to alleviate the effect of the problem. In addition, we propose a practical human evaluation method to address the problem that the existing automatic evaluation method does not evaluate the semantic consistency with the source content properly. Experimental results demonstrate the effectiveness of the proposed approach, which outperforms almost all the existing models. Especially, the proposed approach improves the semantic consistency by 4% in terms of human evaluation. |
| Tasks | Abstractive Text Summarization, Text Summarization |
| Published | 2018-05-10 |
| URL | http://arxiv.org/abs/1805.04033v1 |
| http://arxiv.org/pdf/1805.04033v1.pdf | |
| PWC | https://paperswithcode.com/paper/regularizing-output-distribution-of |
| Repo | |
| Framework | |
Neurons Merging Layer: Towards Progressive Redundancy Reduction for Deep Supervised Hashing
| Title | Neurons Merging Layer: Towards Progressive Redundancy Reduction for Deep Supervised Hashing |
| Authors | Chaoyou Fu, Liangchen Song, Xiang Wu, Guoli Wang, Ran He |
| Abstract | Deep supervised hashing has become an active topic in information retrieval. It generates hashing bits by the output neurons of a deep hashing network. During binary discretization, there often exists much redundancy between hashing bits that degenerates retrieval performance in terms of both storage and accuracy. This paper proposes a simple yet effective Neurons Merging Layer (NMLayer) for deep supervised hashing. A graph is constructed to represent the redundancy relationship between hashing bits that is used to guide the learning of a hashing network. Specifically, it is dynamically learned by a novel mechanism defined in our active and frozen phases. According to the learned relationship, the NMLayer merges the redundant neurons together to balance the importance of each output neuron. Moreover, multiple NMLayers are progressively trained for a deep hashing network to learn a more compact hashing code from a long redundant code. Extensive experiments on four datasets demonstrate that our proposed method outperforms state-of-the-art hashing methods. |
| Tasks | Information Retrieval |
| Published | 2018-09-07 |
| URL | https://arxiv.org/abs/1809.02302v4 |
| https://arxiv.org/pdf/1809.02302v4.pdf | |
| PWC | https://paperswithcode.com/paper/neurons-merging-layer-towards-progressive |
| Repo | |
| Framework | |
A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization
| Title | A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization |
| Authors | Li Wang, Junlin Yao, Yunzhe Tao, Li Zhong, Wei Liu, Qiang Du |
| Abstract | In this paper, we propose a deep learning approach to tackle the automatic summarization tasks by incorporating topic information into the convolutional sequence-to-sequence (ConvS2S) model and using self-critical sequence training (SCST) for optimization. Through jointly attending to topics and word-level alignment, our approach can improve coherence, diversity, and informativeness of generated summaries via a biased probability generation mechanism. On the other hand, reinforcement training, like SCST, directly optimizes the proposed model with respect to the non-differentiable metric ROUGE, which also avoids the exposure bias during inference. We carry out the experimental evaluation with state-of-the-art methods over the Gigaword, DUC-2004, and LCSTS datasets. The empirical results demonstrate the superiority of our proposed method in the abstractive summarization. |
| Tasks | Abstractive Text Summarization, Text Summarization |
| Published | 2018-05-09 |
| URL | http://arxiv.org/abs/1805.03616v2 |
| http://arxiv.org/pdf/1805.03616v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-reinforced-topic-aware-convolutional |
| Repo | |
| Framework | |
Group-Representative Functional Network Estimation from Multi-Subject fMRI Data via MRF-based Image Segmentation
| Title | Group-Representative Functional Network Estimation from Multi-Subject fMRI Data via MRF-based Image Segmentation |
| Authors | Aditi Iyer, Bingjing Tang, Vinayak Rao, Nan Kong |
| Abstract | We propose a novel two-phase approach to functional network estimation of multi-subject functional Magnetic Resonance Imaging (fMRI) data, which applies model-based image segmentation to determine a group-representative connectivity map. In our approach, we first improve clustering-based Independent Component Analysis (ICA) to generate maps of components occurring consistently across subjects, and then estimate the group-representative map through MAP-MRF (Maximum a priori - Markov random field) labeling. For the latter, we provide a novel and efficient variational Bayes algorithm. We study the performance of the proposed method using synthesized data following a theoretical model, and demonstrate its viability in blind extraction of group-representative functional networks using simulated fMRI data. We anticipate the proposed method will be applied in identifying common neuronal characteristics in a population, and could be further extended to real-world clinical diagnosis. |
| Tasks | Semantic Segmentation |
| Published | 2018-08-29 |
| URL | http://arxiv.org/abs/1809.01046v1 |
| http://arxiv.org/pdf/1809.01046v1.pdf | |
| PWC | https://paperswithcode.com/paper/group-representative-functional-network |
| Repo | |
| Framework | |
A Hierarchical End-to-End Model for Jointly Improving Text Summarization and Sentiment Classification
| Title | A Hierarchical End-to-End Model for Jointly Improving Text Summarization and Sentiment Classification |
| Authors | Shuming Ma, Xu Sun, Junyang Lin, Xuancheng Ren |
| Abstract | Text summarization and sentiment classification both aim to capture the main ideas of the text but at different levels. Text summarization is to describe the text within a few sentences, while sentiment classification can be regarded as a special type of summarization which “summarizes” the text into a even more abstract fashion, i.e., a sentiment class. Based on this idea, we propose a hierarchical end-to-end model for joint learning of text summarization and sentiment classification, where the sentiment classification label is treated as the further “summarization” of the text summarization output. Hence, the sentiment classification layer is put upon the text summarization layer, and a hierarchical structure is derived. Experimental results on Amazon online reviews datasets show that our model achieves better performance than the strong baseline systems on both abstractive summarization and sentiment classification. |
| Tasks | Abstractive Text Summarization, Sentiment Analysis, Text Summarization |
| Published | 2018-05-03 |
| URL | http://arxiv.org/abs/1805.01089v2 |
| http://arxiv.org/pdf/1805.01089v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-hierarchical-end-to-end-model-for-jointly |
| Repo | |
| Framework | |
VGAN-Based Image Representation Learning for Privacy-Preserving Facial Expression Recognition
| Title | VGAN-Based Image Representation Learning for Privacy-Preserving Facial Expression Recognition |
| Authors | Jiawei Chen, Janusz Konrad, Prakash Ishwar |
| Abstract | Reliable facial expression recognition plays a critical role in human-machine interactions. However, most of the facial expression analysis methodologies proposed to date pay little or no attention to the protection of a user’s privacy. In this paper, we propose a Privacy-Preserving Representation-Learning Variational Generative Adversarial Network (PPRL-VGAN) to learn an image representation that is explicitly disentangled from the identity information. At the same time, this representation is discriminative from the standpoint of facial expression recognition and generative as it allows expression-equivalent face image synthesis. We evaluate the proposed model on two public datasets under various threat scenarios. Quantitative and qualitative results demonstrate that our approach strikes a balance between the preservation of privacy and data utility. We further demonstrate that our model can be effectively applied to other tasks such as expression morphing and image completion. |
| Tasks | Facial Expression Recognition, Image Generation, Representation Learning |
| Published | 2018-03-19 |
| URL | http://arxiv.org/abs/1803.07100v2 |
| http://arxiv.org/pdf/1803.07100v2.pdf | |
| PWC | https://paperswithcode.com/paper/vgan-based-image-representation-learning-for |
| Repo | |
| Framework | |
Examining the Use of Neural Networks for Feature Extraction: A Comparative Analysis using Deep Learning, Support Vector Machines, and K-Nearest Neighbor Classifiers
| Title | Examining the Use of Neural Networks for Feature Extraction: A Comparative Analysis using Deep Learning, Support Vector Machines, and K-Nearest Neighbor Classifiers |
| Authors | Stephen Notley, Malik Magdon-Ismail |
| Abstract | Neural networks in many varieties are touted as very powerful machine learning tools because of their ability to distill large amounts of information from different forms of data, extracting complex features and enabling powerful classification abilities. In this study, we use neural networks to extract features from both images and numeric data and use these extracted features as inputs for other machine learning models, namely support vector machines (SVMs) and k-nearest neighbor classifiers (KNNs), in order to see if neural-network-extracted features enhance the capabilities of these models. We tested 7 different neural network architectures in this manner, 4 for images and 3 for numeric data, training each for varying lengths of time and then comparing the results of the neural network independently to those of an SVM and KNN on the data, and finally comparing these results to models of SVM and KNN trained using features extracted via the neural network architecture. This process was repeated on 3 different image datasets and 2 different numeric datasets. The results show that, in many cases, the features extracted using the neural network significantly improve the capabilities of SVMs and KNNs compared to running these algorithms on the raw features, and in some cases also surpass the performance of the neural network alone. This in turn suggests that it may be a reasonable practice to use neural networks as a means to extract features for classification by other machine learning models for some datasets. |
| Tasks | |
| Published | 2018-05-06 |
| URL | http://arxiv.org/abs/1805.02294v2 |
| http://arxiv.org/pdf/1805.02294v2.pdf | |
| PWC | https://paperswithcode.com/paper/examining-the-use-of-neural-networks-for |
| Repo | |
| Framework | |
syGlass: Interactive Exploration of Multidimensional Images Using Virtual Reality Head-mounted Displays
| Title | syGlass: Interactive Exploration of Multidimensional Images Using Virtual Reality Head-mounted Displays |
| Authors | Stanislav Pidhorskyi, Michael Morehead, Quinn Jones, George Spirou, Gianfranco Doretto |
| Abstract | The quest for deeper understanding of biological systems has driven the acquisition of increasingly larger multidimensional image datasets. Inspecting and manipulating data of this complexity is very challenging in traditional visualization systems. We developed syGlass, a software package capable of visualizing large scale volumetric data with inexpensive virtual reality head-mounted display technology. This allows leveraging stereoscopic vision to significantly improve perception of complex 3D structures, and provides immersive interaction with data directly in 3D. We accomplished this by developing highly optimized data flow and volume rendering pipelines, tested on datasets up to 16TB in size, as well as tools available in a virtual reality GUI to support advanced data exploration, annotation, and cataloguing. |
| Tasks | |
| Published | 2018-04-23 |
| URL | http://arxiv.org/abs/1804.08197v4 |
| http://arxiv.org/pdf/1804.08197v4.pdf | |
| PWC | https://paperswithcode.com/paper/syglass-interactive-exploration-of |
| Repo | |
| Framework | |
Facial Expression Recognition Based on Complexity Perception Classification Algorithm
| Title | Facial Expression Recognition Based on Complexity Perception Classification Algorithm |
| Authors | Tianyuan Chang, Guihua Wen, Yang Hu, JiaJiong Ma |
| Abstract | Facial expression recognition (FER) has always been a challenging issue in computer vision. The different expressions of emotion and uncontrolled environmental factors lead to inconsistencies in the complexity of FER and variability of between expression categories, which is often overlooked in most facial expression recognition systems. In order to solve this problem effectively, we presented a simple and efficient CNN model to extract facial features, and proposed a complexity perception classification (CPC) algorithm for FER. The CPC algorithm divided the dataset into an easy classification sample subspace and a complex classification sample subspace by evaluating the complexity of facial features that are suitable for classification. The experimental results of our proposed algorithm on Fer2013 and CK-plus datasets demonstrated the algorithm’s effectiveness and superiority over other state-of-the-art approaches. |
| Tasks | Facial Expression Recognition |
| Published | 2018-03-01 |
| URL | http://arxiv.org/abs/1803.00185v1 |
| http://arxiv.org/pdf/1803.00185v1.pdf | |
| PWC | https://paperswithcode.com/paper/facial-expression-recognition-based-on |
| Repo | |
| Framework | |
