Paper Group ANR 236
Black-box Combinatorial Optimization using Models with Integer-valued Minima. Fast Infant MRI Skullstripping with Multiview 2D Convolutional Neural Networks. Repeated sequential learning increases memory capacity via effective decorrelation in a recurrent neural network. Toward Robust Image Classification. In Vitro Fertilization (IVF) Cumulative Pr …
Black-box Combinatorial Optimization using Models with Integer-valued Minima
| Title | Black-box Combinatorial Optimization using Models with Integer-valued Minima |
| Authors | Laurens Bliek, Sicco Verwer, Mathijs de Weerdt |
| Abstract | When a black-box optimization objective can only be evaluated with costly or noisy measurements, most standard optimization algorithms are unsuited to find the optimal solution. Specialized algorithms that deal with exactly this situation make use of surrogate models. These models are usually continuous and smooth, which is beneficial for continuous optimization problems, but not necessarily for combinatorial problems. However, by choosing the basis functions of the surrogate model in a certain way, we show that it can be guaranteed that the optimal solution of the surrogate model is integer. This approach outperforms random search, simulated annealing and one Bayesian optimization algorithm on the problem of finding robust routes for a noise-perturbed traveling salesman benchmark problem, with similar performance as another Bayesian optimization algorithm, and outperforms all compared algorithms on a convex binary optimization problem with a large number of variables. |
| Tasks | Combinatorial Optimization |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.08817v1 |
| https://arxiv.org/pdf/1911.08817v1.pdf | |
| PWC | https://paperswithcode.com/paper/black-box-combinatorial-optimization-using |
| Repo | |
| Framework | |
Fast Infant MRI Skullstripping with Multiview 2D Convolutional Neural Networks
| Title | Fast Infant MRI Skullstripping with Multiview 2D Convolutional Neural Networks |
| Authors | Amod Jog, P. Ellen Grant, Joseph L. Jacobson, Andre van der Kouwe, Ernesta M. Meintjes, Bruce Fischl, Lilla Zöllei |
| Abstract | Skullstripping is defined as the task of segmenting brain tissue from a full head magnetic resonance image~(MRI). It is a critical component in neuroimage processing pipelines. Downstream deformable registration and whole brain segmentation performance is highly dependent on accurate skullstripping. Skullstripping is an especially challenging task for infant~(age range 0–18 months) head MRI images due to the significant size and shape variability of the head and the brain in that age range. Infant brain tissue development also changes the $T_1$-weighted image contrast over time, making consistent skullstripping a difficult task. Existing tools for adult brain MRI skullstripping are ill equipped to handle these variations and a specialized infant MRI skullstripping algorithm is necessary. In this paper, we describe a supervised skullstripping algorithm that utilizes three trained fully convolutional neural networks~(CNN), each of which segments 2D $T_1$-weighted slices in axial, coronal, and sagittal views respectively. The three probabilistic segmentations in the three views are linearly fused and thresholded to produce a final brain mask. We compared our method to existing adult and infant skullstripping algorithms and showed significant improvement based on Dice overlap metric~(average Dice of 0.97) with a manually labeled ground truth data set. Label fusion experiments on multiple, unlabeled data sets show that our method is consistent and has fewer failure modes. In addition, our method is computationally very fast with a run time of 30 seconds per image on NVidia P40/P100/Quadro 4000 GPUs. |
| Tasks | Brain Segmentation |
| Published | 2019-04-27 |
| URL | http://arxiv.org/abs/1904.12101v1 |
| http://arxiv.org/pdf/1904.12101v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-infant-mri-skullstripping-with-multiview |
| Repo | |
| Framework | |
Repeated sequential learning increases memory capacity via effective decorrelation in a recurrent neural network
| Title | Repeated sequential learning increases memory capacity via effective decorrelation in a recurrent neural network |
| Authors | Tomoki Kurikawa, Omri Barak, Kunihiko Kaneko |
| Abstract | Memories in neural system are shaped through the interplay of neural and learning dynamics under external inputs. By introducing a simple local learning rule to a neural network, we found that the memory capacity is drastically increased by sequentially repeating the learning steps of input-output mappings. The origin of this enhancement is attributed to the generation of a Psuedo-inverse correlation in the connectivity. This is associated with the emergence of spontaneous activity that intermittently exhibits neural patterns corresponding to embedded memories. Stablization of memories is achieved by a distinct bifurcation from the spontaneous activity under the application of each input. |
| Tasks | |
| Published | 2019-06-22 |
| URL | https://arxiv.org/abs/1906.11770v1 |
| https://arxiv.org/pdf/1906.11770v1.pdf | |
| PWC | https://paperswithcode.com/paper/repeated-sequential-learning-increases-memory |
| Repo | |
| Framework | |
Toward Robust Image Classification
| Title | Toward Robust Image Classification |
| Authors | Basemah Alshemali, Alta Graham, Jugal Kalita |
| Abstract | Neural networks are frequently used for image classification, but can be vulnerable to misclassification caused by adversarial images. Attempts to make neural network image classification more robust have included variations on preprocessing (cropping, applying noise, blurring), adversarial training, and dropout randomization. In this paper, we implemented a model for adversarial detection based on a combination of two of these techniques: dropout randomization with preprocessing applied to images within a given Bayesian uncertainty. We evaluated our model on the MNIST dataset, using adversarial images generated using Fast Gradient Sign Method (FGSM), Jacobian-based Saliency Map Attack (JSMA) and Basic Iterative Method (BIM) attacks. Our model achieved an average adversarial image detection accuracy of 97%, with an average image classification accuracy, after discarding images flagged as adversarial, of 99%. Our average detection accuracy exceeded that of recent papers using similar techniques. |
| Tasks | Image Classification |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.12927v1 |
| https://arxiv.org/pdf/1909.12927v1.pdf | |
| PWC | https://paperswithcode.com/paper/toward-robust-image-classification |
| Repo | |
| Framework | |
In Vitro Fertilization (IVF) Cumulative Pregnancy Rate Prediction from Basic Patient Characteristics
| Title | In Vitro Fertilization (IVF) Cumulative Pregnancy Rate Prediction from Basic Patient Characteristics |
| Authors | Bo Zhang, Yuqi Cui, Meng Wang, Jingjing Li, Lei Jin, Dongrui Wu |
| Abstract | Tens of millions of women suffer from infertility worldwide each year. In vitro fertilization (IVF) is the best choice for many such patients. However, IVF is expensive, time-consuming, and both physically and emotionally demanding. The first question that a patient usually asks before the IVF is how likely she will conceive, given her basic medical examination information. This paper proposes three approaches to predict the cumulative pregnancy rate after multiple oocyte pickup cycles. Experiments on 11,190 patients showed that first clustering the patients into different groups and then building a support vector machine model for each group can achieve the best overall performance. Our model could be a quick and economic approach for reliably estimating the cumulative pregnancy rate for a patient, given only her basic medical examination information, well before starting the actual IVF procedure. The predictions can help the patient make optimal decisions on whether to use her own oocyte or donor oocyte, how many oocyte pickup cycles she may need, whether to use embryo frozen, etc. They will also reduce the patient’s cost and time to pregnancy, and improve her quality of life. |
| Tasks | |
| Published | 2019-11-10 |
| URL | https://arxiv.org/abs/1911.03839v1 |
| https://arxiv.org/pdf/1911.03839v1.pdf | |
| PWC | https://paperswithcode.com/paper/in-vitro-fertilization-ivf-cumulative |
| Repo | |
| Framework | |
PFA-ScanNet: Pyramidal Feature Aggregation with Synergistic Learning for Breast Cancer Metastasis Analysis
| Title | PFA-ScanNet: Pyramidal Feature Aggregation with Synergistic Learning for Breast Cancer Metastasis Analysis |
| Authors | Zixu Zhao, Huangjing Lin, Hao Chen, Pheng-Ann Heng |
| Abstract | Automatic detection of cancer metastasis from whole slide images (WSIs) is a crucial step for following patient staging and prognosis. Recent convolutional neural network based approaches are struggling with the trade-off between accuracy and computational efficiency due to the difficulty in processing large-scale gigapixel WSIs. To meet this challenge, we propose a novel Pyramidal Feature Aggregation ScanNet (PFA-ScanNet) for robust and fast analysis of breast cancer metastasis. Our method mainly benefits from the aggregation of extracted local-to-global features with diverse receptive fields, as well as the proposed synergistic learning for training the main detector and extra decoder with semantic guidance. Furthermore, a high-efficiency inference mechanism is designed with dense pooling layers, which allows dense and fast scanning for gigapixel WSI analysis. As a result, the proposed PFA-ScanNet achieved the state-of-the-art FROC of 90.2% on the Camelyon16 dataset, as well as competitive kappa score of 0.905 on the Camelyon17 leaderboard. In addition, our method shows leading speed advantage over other methods, about 7.2 min per WSI with a single GPU, making automatic analysis of breast cancer metastasis more applicable in the clinical usage. |
| Tasks | |
| Published | 2019-05-03 |
| URL | https://arxiv.org/abs/1905.01040v2 |
| https://arxiv.org/pdf/1905.01040v2.pdf | |
| PWC | https://paperswithcode.com/paper/pfa-scannet-pyramidal-feature-aggregation |
| Repo | |
| Framework | |
Unsupervised Classification of Street Architectures Based on InfoGAN
| Title | Unsupervised Classification of Street Architectures Based on InfoGAN |
| Authors | Ning Wang, Xianhan Zeng, Renjie Xie, Zefei Gao, Yi Zheng, Ziran Liao, Junyan Yang, Qiao Wang |
| Abstract | Street architectures play an essential role in city image and streetscape analysing. However, existing approaches are all supervised which require costly labeled data. To solve this, we propose a street architectural unsupervised classification framework based on Information maximizing Generative Adversarial Nets (InfoGAN), in which we utilize the auxiliary distribution $Q$ of InfoGAN as an unsupervised classifier. Experiments on database of true street view images in Nanjing, China validate the practicality and accuracy of our framework. Furthermore, we draw a series of heuristic conclusions from the intrinsic information hidden in true images. These conclusions will assist planners to know the architectural categories better. |
| Tasks | |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.12844v1 |
| https://arxiv.org/pdf/1905.12844v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-classification-of-street |
| Repo | |
| Framework | |
Mimic Learning to Generate a Shareable Network Intrusion Detection Model
| Title | Mimic Learning to Generate a Shareable Network Intrusion Detection Model |
| Authors | Ahmed Shafee, Mohamed Baza, Douglas A. Talbert, Mostafa M. Fouda, Mahmoud Nabil, Mohamed Mahmoud |
| Abstract | Purveyors of malicious network attacks continue to increase the complexity and the sophistication of their techniques, and their ability to evade detection continues to improve as well. Hence, intrusion detection systems must also evolve to meet these increasingly challenging threats. Machine learning is often used to support this needed improvement. However, training a good prediction model can require a large set of labelled training data. Such datasets are difficult to obtain because privacy concerns prevent the majority of intrusion detection agencies from sharing their sensitive data. In this paper, we propose the use of mimic learning to enable the transfer of intrusion detection knowledge through a teacher model trained on private data to a student model. This student model provides a mean of publicly sharing knowledge extracted from private data without sharing the data itself. Our results confirm that the proposed scheme can produce a student intrusion detection model that mimics the teacher model without requiring access to the original dataset. |
| Tasks | Intrusion Detection, Network Intrusion Detection |
| Published | 2019-05-02 |
| URL | https://arxiv.org/abs/1905.00919v3 |
| https://arxiv.org/pdf/1905.00919v3.pdf | |
| PWC | https://paperswithcode.com/paper/mimic-learning-to-generate-a-shareable |
| Repo | |
| Framework | |
Generalized Residual Ratio Thresholding
| Title | Generalized Residual Ratio Thresholding |
| Authors | Sreejith Kallummil, Sheetal Kalyani |
| Abstract | Simultaneous orthogonal matching pursuit (SOMP) and block OMP (BOMP) are two widely used techniques for sparse support recovery in multiple measurement vector (MMV) and block sparse (BS) models respectively. For optimal performance, both SOMP and BOMP require \textit{a priori} knowledge of signal sparsity or noise variance. However, sparsity and noise variance are unavailable in most practical applications. This letter presents a novel technique called generalized residual ratio thresholding (GRRT) for operating SOMP and BOMP without the \textit{a priori} knowledge of signal sparsity and noise variance and derive finite sample and finite signal to noise ratio (SNR) guarantees for exact support recovery. Numerical simulations indicate that GRRT performs similar to BOMP and SOMP with \textit{a priori} knowledge of signal and noise statistics. |
| Tasks | |
| Published | 2019-12-18 |
| URL | https://arxiv.org/abs/1912.08637v1 |
| https://arxiv.org/pdf/1912.08637v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-residual-ratio-thresholding |
| Repo | |
| Framework | |
Learning to Deceive with Attention-Based Explanations
| Title | Learning to Deceive with Attention-Based Explanations |
| Authors | Danish Pruthi, Mansi Gupta, Bhuwan Dhingra, Graham Neubig, Zachary C. Lipton |
| Abstract | Attention mechanisms are ubiquitous components in neural architectures applied in natural language processing. In addition to yielding gains in predictive accuracy, researchers often claim that attention weights confer interpretability, purportedly useful both for providing insights to practitioners and for explaining why a model makes its decisions to stakeholders. We call the latter use of attention mechanisms into question, demonstrating a simple method for training models to produce deceptive attention masks, diminishing the total weight assigned to designated impermissible tokens, even as the models are shown to nevertheless rely on these features to drive predictions. Across multiple models and datasets, our approach manipulates attention weights while paying surprisingly little cost in accuracy. Although our results do not rule out potential insights due to organically-trained attention, they cast doubt on attention’s reliability as a tool for auditing algorithms, as in the context of fairness and accountability. |
| Tasks | |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.07913v1 |
| https://arxiv.org/pdf/1909.07913v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-deceive-with-attention-based |
| Repo | |
| Framework | |
CUSUM Filter for Brain Segmentation on DSC Perfusion MR Head Scans with Abnormal Brain Anatomy
| Title | CUSUM Filter for Brain Segmentation on DSC Perfusion MR Head Scans with Abnormal Brain Anatomy |
| Authors | Svitlana Alkhimova |
| Abstract | This paper presents a new approach for relatively accurate brain region of interest (ROI) detection from dynamic susceptibility contrast (DSC) perfusion magnetic resonance (MR) images of a human head with abnormal brain anatomy. Such images produce problems for automatic brain segmentation algorithms, and as a result, poor perfusion ROI detection affects both quantitative measurements and visual assessment of perfusion data. In the proposed approach image segmentation is based on CUSUM filter usage that was adapted to be applicable to process DSC perfusion MR images. The result of segmentation is a binary mask of brain ROI that is generated via usage of brain boundary location. Each point of the boundary between the brain and surrounding tissues is detected as a change-point by CUSUM filter. Proposed adopted CUSUM filter operates by accumulating the deviations between the observed and expected intensities of image points at the time of moving on a trajectory. Motion trajectory is created by the iterative change of movement direction inside the background region in order to reach brain region, and vice versa after boundary crossing. Proposed segmentation approach was evaluated with Dice index comparing obtained results to the reference standard. Manually marked brain region pixels (reference standard), as well as visual inspection of detected with CUSUM filter usage brain ROI, were provided by experienced radiologists. The results showed that proposed approach is suitable to be used for brain ROI detection from DSC perfusion MR images of a human head with abnormal brain anatomy and can, therefore, be applied in the DSC perfusion data analysis. |
| Tasks | Brain Segmentation, Semantic Segmentation |
| Published | 2019-03-26 |
| URL | http://arxiv.org/abs/1904.00787v1 |
| http://arxiv.org/pdf/1904.00787v1.pdf | |
| PWC | https://paperswithcode.com/paper/cusum-filter-for-brain-segmentation-on-dsc |
| Repo | |
| Framework | |
LightMC: A Dynamic and Efficient Multiclass Decomposition Algorithm
| Title | LightMC: A Dynamic and Efficient Multiclass Decomposition Algorithm |
| Authors | Ziyu Liu, Guolin Ke, Jiang Bian, Tieyan Liu |
| Abstract | Multiclass decomposition splits a multiclass classification problem into a series of independent binary learners and recomposes them by combining their outputs to reconstruct the multiclass classification results. Three widely-used realizations of such decomposition methods are One-Versus-All (OVA), One-Versus-One (OVO), and Error-Correcting-Output-Code (ECOC). While OVA and OVO are quite simple, both of them assume all classes are orthogonal which neglect the latent correlation between classes in real-world. Error-Correcting-Output-Code (ECOC) based decomposition methods, on the other hand, are more preferable due to its integration of the correlation among classes. However, the performance of existing ECOC-based methods highly depends on the design of coding matrix and decoding strategy. Unfortunately, it is quite uncertain and time-consuming to discover an effective coding matrix with appropriate decoding strategy. To address this problem, we propose LightMC, an efficient dynamic multiclass decomposition algorithm. Instead of using fixed coding matrix and decoding strategy, LightMC uses a differentiable decoding strategy, which enables it to dynamically optimize the coding matrix and decoding strategy, toward increasing the overall accuracy of multiclass classification, via back propagation jointly with the training of base learners in an iterative way. Empirical experimental results on several public large-scale multiclass classification datasets have demonstrated the effectiveness of LightMC in terms of both good accuracy and high efficiency. |
| Tasks | |
| Published | 2019-08-25 |
| URL | https://arxiv.org/abs/1908.09362v1 |
| https://arxiv.org/pdf/1908.09362v1.pdf | |
| PWC | https://paperswithcode.com/paper/lightmc-a-dynamic-and-efficient-multiclass |
| Repo | |
| Framework | |
Multi-Objectivizing Sum-of-the-Parts Combinatorial Optimization Problems by Random Objective Decomposition
| Title | Multi-Objectivizing Sum-of-the-Parts Combinatorial Optimization Problems by Random Objective Decomposition |
| Authors | Jialong Shi, Jianyong Sun, Qingfu Zhang |
| Abstract | Multi-objectivization is a term used to describe strategies developed for optimizing single-objective problems by multi-objective algorithms. This paper focuses on the multi-objectivization of the sum-of-the-parts Combinatorial Optimization Problems (COPs), which include the Traveling Salesman Problem (TSP), the Unconstrained Binary Quadratic Programming (UBQP) and other well-known COPs. For a sum-of-the-parts COP, we propose to decompose its original objective into two sub-objectives with controllable correlation. Based on the decomposition method, two new multi-objectivization techniques called Non-Dominance Search (NDS) and Non-Dominance Exploitation (NDE) are developed, respectively. NDS is combined with the Iterated Local Search (ILS) metaheuristic (with fixed neighborhood structure), while NDE is embedded within the Iterated Lin-Kernighan (ILK) metaheuristic (with varied neighborhood structure). The resultant metaheuristics are called ILS+NDS and ILK+NDE, respectively. Empirical studies on some TSP and UBQP instances show that with appropriate correlation between the sub-objectives, there are more chances to escape from local optima when new starting solution is selected from the non-dominated solutions defined by the decomposed sub-objectives. Experimental results also show that ILS+NDS and ILK+NDE both significantly outperform their counterparts on most of the test instances. |
| Tasks | Combinatorial Optimization |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.04658v2 |
| https://arxiv.org/pdf/1911.04658v2.pdf | |
| PWC | https://paperswithcode.com/paper/novel-multi-objectivization-approaches-for |
| Repo | |
| Framework | |
Neural Language Priors
| Title | Neural Language Priors |
| Authors | Joseph Enguehard, Dan Busbridge, Vitalii Zhelezniak, Nils Hammerla |
| Abstract | The choice of sentence encoder architecture reflects assumptions about how a sentence’s meaning is composed from its constituent words. We examine the contribution of these architectures by holding them randomly initialised and fixed, effectively treating them as as hand-crafted language priors, and evaluating the resulting sentence encoders on downstream language tasks. We find that even when encoders are presented with additional information that can be used to solve tasks, the corresponding priors do not leverage this information, except in an isolated case. We also find that apparently uninformative priors are just as good as seemingly informative priors on almost all tasks, indicating that learning is a necessary component to leverage information provided by architecture choice. |
| Tasks | |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.03492v1 |
| https://arxiv.org/pdf/1910.03492v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-language-priors |
| Repo | |
| Framework | |
Zeroth Order Non-convex optimization with Dueling-Choice Bandits
| Title | Zeroth Order Non-convex optimization with Dueling-Choice Bandits |
| Authors | Yichong Xu, Aparna Joshi, Aarti Singh, Artur Dubrawski |
| Abstract | We consider a novel setting of zeroth order non-convex optimization, where in addition to querying the function value at a given point, we can also duel two points and get the point with the larger function value. We refer to this setting as optimization with dueling-choice bandits since both direct queries and duels are available for optimization. We give the COMP-GP-UCB algorithm based on GP-UCB (Srinivas et al., 2009), where instead of directly querying the point with the maximum Upper Confidence Bound (UCB), we perform a constrained optimization and use comparisons to filter out suboptimal points. COMP-GP-UCB comes with theoretical guarantee of $O(\frac{\Phi}{\sqrt{T}})$ on simple regret where $T$ is the number of direct queries and $\Phi$ is an improved information gain corresponding to a comparison based constraint set that restricts the search space for the optimum. In contrast, in the direct query only setting, $\Phi$ depends on the entire domain. Finally, we present experimental results to show the efficacy of our algorithm. |
| Tasks | |
| Published | 2019-11-03 |
| URL | https://arxiv.org/abs/1911.00980v1 |
| https://arxiv.org/pdf/1911.00980v1.pdf | |
| PWC | https://paperswithcode.com/paper/zeroth-order-non-convex-optimization-with |
| Repo | |
| Framework | |
