Paper Group ANR 1331
Projection-to-Projection Translation for Hybrid X-ray and Magnetic Resonance Imaging. Audience measurement using a top-view camera and oriented trajectories. I-MAD: A Novel Interpretable Malware Detector Using Hierarchical Transformer. Multi-player Multi-Armed Bandits with non-zero rewards on collisions for uncoordinated spectrum access. A novel me …
Projection-to-Projection Translation for Hybrid X-ray and Magnetic Resonance Imaging
| Title | Projection-to-Projection Translation for Hybrid X-ray and Magnetic Resonance Imaging |
| Authors | Bernhard Stimpel, Christopher Syben, Tobias Würfl, Katharina Breininger, Philipp Hoelter, Arnd Dörfler, Andreas Maier |
| Abstract | Hybrid X-ray and magnetic resonance (MR) imaging promises large potential in interventional medical imaging applications due to the broad variety of contrast of MRI combined with fast imaging of X-ray-based modalities. To fully utilize the potential of the vast amount of existing image enhancement techniques, the corresponding information from both modalities must be present in the same domain. For image-guided interventional procedures, X-ray fluoroscopy has proven to be the modality of choice. Synthesizing one modality from another in this case is an ill-posed problem due to ambiguous signal and overlapping structures in projective geometry. To take on these challenges, we present a learning-based solution to MR to X-ray projection-to-projection translation. We propose an image generator network that focuses on high representation capacity in higher resolution layers to allow for accurate synthesis of fine details in the projection images. Additionally, a weighting scheme in the loss computation that favors high-frequency structures is proposed to focus on the important details and contours in projection imaging. The proposed extensions prove valuable in generating X-ray projection images with natural appearance. Our approach achieves a deviation from the ground truth of only $6$% and structural similarity measure of $0.913,\pm,0.005$. In particular the high frequency weighting assists in generating projection images with sharp appearance and reduces erroneously synthesized fine details. |
| Tasks | Image Enhancement |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08163v1 |
| https://arxiv.org/pdf/1911.08163v1.pdf | |
| PWC | https://paperswithcode.com/paper/projection-to-projection-translation-for |
| Repo | |
| Framework | |
Audience measurement using a top-view camera and oriented trajectories
| Title | Audience measurement using a top-view camera and oriented trajectories |
| Authors | Manuel Lopez-Palma, Javier Gago, Montserrat Corbalan, Josep Ramon Morros |
| Abstract | A crucial aspect for selecting optimal areas for commercial advertising is the probability with which that publicity will be seen. This paper presents a method based on top-view camera measurement, where the probability of viewing is estimated according to the trajectories and movements of the head of the passerby individuals in the area of interest. Using a camera with a depth sensor, the head of the people in the range of view can be detected and modeled. That method allows determining the orientation of the head which is used to estimate the direction of vision. A tracking by detection algorithm is used to compute the trajectory of each user. The attention given at each advertising spot is estimated based on the trajectories and head orientations of the individuals in the area of interest |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.00354v1 |
| https://arxiv.org/pdf/1911.00354v1.pdf | |
| PWC | https://paperswithcode.com/paper/audience-measurement-using-a-top-view-camera |
| Repo | |
| Framework | |
I-MAD: A Novel Interpretable Malware Detector Using Hierarchical Transformer
| Title | I-MAD: A Novel Interpretable Malware Detector Using Hierarchical Transformer |
| Authors | Miles Q. Li, Benjamin C. M. Fung, Philippe Charland, Steven H. H. Ding |
| Abstract | Malware imposes tremendous threats to computer users nowadays. Since signature-based malware detection methods are neither effective nor efficient to identify new malware, many machine learning-based methods have been proposed. A common disadvantage of existing machine learning methods is that they are not based on understanding the full semantic meaning of assembly code of an executable. They rather use short assembly code fragments, because assembly code is usually too long to be modelled in its entirety. Another disadvantage is that those methods have either inferior performance or bad interpretability. To overcome these challenges, we propose an Interpretable MAware Detector (I-MAD), which achieves state-of-the-art performance on static malware detection with excellent interpretability. It integrates a hierarchical Transformer network that can understand assembly code at the basic block, function, and executable level. It also integrates our novel interpretable feed-forward neural network to provide interpretations for its detection results by pointing out the impact of each feature with respect to the prediction. Experiment results show that our model significantly outperforms previous state-of-the-art static malware detection models and presents meaningful interpretations. |
| Tasks | Malware Detection |
| Published | 2019-09-15 |
| URL | https://arxiv.org/abs/1909.06865v2 |
| https://arxiv.org/pdf/1909.06865v2.pdf | |
| PWC | https://paperswithcode.com/paper/i-mad-a-novel-interpretable-malware-detector |
| Repo | |
| Framework | |
Multi-player Multi-Armed Bandits with non-zero rewards on collisions for uncoordinated spectrum access
| Title | Multi-player Multi-Armed Bandits with non-zero rewards on collisions for uncoordinated spectrum access |
| Authors | Akshayaa Magesh, Venugopal V. Veeravalli |
| Abstract | In this paper, we study the uncoordinated spectrum access problem using the multi-player multi-armed bandits framework. We consider a model where there is no central control and the users cannot communicate with each other. The environment may appear differently to different users, \textit{i.e.}, the mean rewards as seen by different users for a particular channel may be different. Additionally, in case of a collision, we allow for the colliding users to receive non-zero rewards. With this setup, we present a policy that achieves expected regret of order $O(\log^{2+\delta}{T})$ for some $\delta > 0$. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09089v1 |
| https://arxiv.org/pdf/1910.09089v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-player-multi-armed-bandits-with-non |
| Repo | |
| Framework | |
A novel method for identifying the deep neural network model with the Serial Number
| Title | A novel method for identifying the deep neural network model with the Serial Number |
| Authors | XiangRui Xu, YaQin Li, Cao Yuan |
| Abstract | Deep neural network (DNN) with the state of art performance has emerged as a viable and lucrative business service. However, those impressive performances require a large number of computational resources, which comes at a high cost for the model creators. The necessity for protecting DNN models from illegal reproducing and distribution appears salient now. Recently, trigger-set watermarking, breaking the white-box restriction, relying on adversarial training pre-defined (incorrect) labels for crafted inputs, and subsequently using them to verify the model authenticity, has been the main topic of DNN ownership verification. While these methods have successfully demonstrated robustness against removal attacks, few are effective against the tampering attacks from competitors forging the fake watermarks and dogging in the manager. In this paper, we put forth a new framework of the trigger-set watermark by embedding a unique Serial Number (relatedness less original labels) to the deep neural network for model ownership identification, which is both robust to model pruning and resist to tampering attacks. Experiment results demonstrate that the DNN Serial Number only incurs slight accuracy degradation of the original performance and is valid for ownership verification. |
| Tasks | |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08053v1 |
| https://arxiv.org/pdf/1911.08053v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-method-for-identifying-the-deep |
| Repo | |
| Framework | |
Blending-target Domain Adaptation by Adversarial Meta-Adaptation Networks
| Title | Blending-target Domain Adaptation by Adversarial Meta-Adaptation Networks |
| Authors | Ziliang Chen, Jingyu Zhuang, Xiaodan Liang, Liang Lin |
| Abstract | (Unsupervised) Domain Adaptation (DA) seeks for classifying target instances when solely provided with source labeled and target unlabeled examples for training. Learning domain-invariant features helps to achieve this goal, whereas it underpins unlabeled samples drawn from a single or multiple explicit target domains (Multi-target DA). In this paper, we consider a more realistic transfer scenario: our target domain is comprised of multiple sub-targets implicitly blended with each other, so that learners could not identify which sub-target each unlabeled sample belongs to. This Blending-target Domain Adaptation (BTDA) scenario commonly appears in practice and threatens the validities of most existing DA algorithms, due to the presence of domain gaps and categorical misalignments among these hidden sub-targets. To reap the transfer performance gains in this new scenario, we propose Adversarial Meta-Adaptation Network (AMEAN). AMEAN entails two adversarial transfer learning processes. The first is a conventional adversarial transfer to bridge our source and mixed target domains. To circumvent the intra-target category misalignment, the second process presents as learning to adapt'': It deploys an unsupervised meta-learner receiving target data and their ongoing feature-learning feedbacks, to discover target clusters as our meta-sub-target’’ domains. These meta-sub-targets auto-design our meta-sub-target DA loss, which empirically eliminates the implicit category mismatching in our mixed target. We evaluate AMEAN and a variety of DA algorithms in three benchmarks under the BTDA setup. Empirical results show that BTDA is a quite challenging transfer setup for most existing DA algorithms, yet AMEAN significantly outperforms these state-of-the-art baselines and effectively restrains the negative transfer effects in BTDA. |
| Tasks | Domain Adaptation, Transfer Learning, Unsupervised Domain Adaptation |
| Published | 2019-07-08 |
| URL | https://arxiv.org/abs/1907.03389v1 |
| https://arxiv.org/pdf/1907.03389v1.pdf | |
| PWC | https://paperswithcode.com/paper/blending-target-domain-adaptation-by-1 |
| Repo | |
| Framework | |
Effective degrees of freedom for surface finish defect detection and classification
| Title | Effective degrees of freedom for surface finish defect detection and classification |
| Authors | Natalya Pya Arnqvist, Blaise Ngendangenzwa, Eric Lindahl, Leif Nilsson, Jun Yu |
| Abstract | One of the primary concerns of product quality control in the automotive industry is an automated detection of defects of small sizes on specular car body surfaces. A new statistical learning approach is presented for surface finish defect detection based on spline smoothing method for feature extraction and $k$-nearest neighbour probabilistic classifier. Since the surfaces are specular, structured lightning reflection technique is applied for image acquisition. Reduced rank cubic regression splines are used to smooth the pixel values while the effective degrees of freedom of the obtained smooths serve as components of the feature vector. A key advantage of the approach is that it allows reaching near zero misclassification error rate when applying standard learning classifiers. We also propose probability based performance evaluation metrics as alternatives to the conventional metrics. The usage of those provides the means for uncertainty estimation of the predictive performance of a classifier. Experimental classification results on the images obtained from the pilot system located at Volvo GTO Cab plant in Ume{\aa}, Sweden, show that the proposed approach is much more efficient than the compared methods. |
| Tasks | |
| Published | 2019-06-20 |
| URL | https://arxiv.org/abs/1906.11904v1 |
| https://arxiv.org/pdf/1906.11904v1.pdf | |
| PWC | https://paperswithcode.com/paper/effective-degrees-of-freedom-for-surface |
| Repo | |
| Framework | |
Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation
| Title | Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation |
| Authors | Yuyin Zhou, Zhe Li, Song Bai, Chong Wang, Xinlei Chen, Mei Han, Elliot Fishman, Alan Yuille |
| Abstract | Accurate multi-organ abdominal CT segmentation is essential to many clinical applications such as computer-aided intervention. As data annotation requires massive human labor from experienced radiologists, it is common that training data are partially labeled, e.g., pancreas datasets only have the pancreas labeled while leaving the rest marked as background. However, these background labels can be misleading in multi-organ segmentation since the “background” usually contains some other organs of interest. To address the background ambiguity in these partially-labeled datasets, we propose Prior-aware Neural Network (PaNN) via explicitly incorporating anatomical priors on abdominal organ sizes, guiding the training process with domain-specific knowledge. More specifically, PaNN assumes that the average organ size distributions in the abdomen should approximate their empirical distributions, a prior statistics obtained from the fully-labeled dataset. As our training objective is difficult to be directly optimized using stochastic gradient descent [20], we propose to reformulate it in a min-max form and optimize it via the stochastic primal-dual gradient algorithm. PaNN achieves state-of-the-art performance on the MICCAI2015 challenge “Multi-Atlas Labeling Beyond the Cranial Vault”, a competition on organ segmentation in the abdomen. We report an average Dice score of 84.97%, surpassing the prior art by a large margin of 3.27%. |
| Tasks | |
| Published | 2019-04-12 |
| URL | https://arxiv.org/abs/1904.06346v2 |
| https://arxiv.org/pdf/1904.06346v2.pdf | |
| PWC | https://paperswithcode.com/paper/prior-aware-neural-network-for-partially |
| Repo | |
| Framework | |
Covariance in Physics and Convolutional Neural Networks
| Title | Covariance in Physics and Convolutional Neural Networks |
| Authors | Miranda C. N. Cheng, Vassilis Anagiannis, Maurice Weiler, Pim de Haan, Taco S. Cohen, Max Welling |
| Abstract | In this proceeding we give an overview of the idea of covariance (or equivariance) featured in the recent development of convolutional neural networks (CNNs). We study the similarities and differences between the use of covariance in theoretical physics and in the CNN context. Additionally, we demonstrate that the simple assumption of covariance, together with the required properties of locality, linearity and weight sharing, is sufficient to uniquely determine the form of the convolution. |
| Tasks | |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02481v1 |
| https://arxiv.org/pdf/1906.02481v1.pdf | |
| PWC | https://paperswithcode.com/paper/covariance-in-physics-and-convolutional |
| Repo | |
| Framework | |
Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networks
| Title | Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networks |
| Authors | Hao Peng, Jianxin Li, Qiran Gong, Yangqiu Song, Yuanxing Ning, Kunfeng Lai, Philip S. Yu |
| Abstract | Events are happening in real-world and real-time, which can be planned and organized occasions involving multiple people and objects. Social media platforms publish a lot of text messages containing public events with comprehensive topics. However, mining social events is challenging due to the heterogeneous event elements in texts and explicit and implicit social network structures. In this paper, we design an event meta-schema to characterize the semantic relatedness of social events and build an event-based heterogeneous information network (HIN) integrating information from external knowledge base, and propose a novel Pair-wise Popularity Graph Convolutional Network (PP-GCN) based fine-grained social event categorization model. We propose a Knowledgeable meta-paths Instances based social Event Similarity (KIES) between events and build a weighted adjacent matrix as input to the PP-GCN model. Comprehensive experiments on real data collections are conducted to compare various social event detection and clustering tasks. Experimental results demonstrate that our proposed framework outperforms other alternative social event categorization techniques. |
| Tasks | |
| Published | 2019-06-09 |
| URL | https://arxiv.org/abs/1906.04580v1 |
| https://arxiv.org/pdf/1906.04580v1.pdf | |
| PWC | https://paperswithcode.com/paper/fine-grained-event-categorization-with |
| Repo | |
| Framework | |
Exact confidence interval for generalized Flajolet-Martin algorithms
| Title | Exact confidence interval for generalized Flajolet-Martin algorithms |
| Authors | Giacomo Aletti |
| Abstract | This paper develop a deep mathematical-statistical approach to analyze a class of Flajolet-Martin algorithms (FMa), and provide a exact analytical confidence interval for the number $F_0$ of distinct elements in a stream, based on Chernoff bounds. The class of FMa has reached a significant popularity in bigdata stream learning, and the attention of the literature has mainly been based on algorithmic aspects, basically complexity optimality, while the statistical analysis of these class of algorithms has been often faced heuristically. The analysis provided here shows a deep connections with special mathematical functions and with extreme value theory. The latter connection may help in explaining heuristic considerations, while the first opens many numerical issues, faced at the end of the present paper. Finally, MonteCarlo simulations are provided to support our analytical choice in this context. |
| Tasks | |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11564v1 |
| https://arxiv.org/pdf/1909.11564v1.pdf | |
| PWC | https://paperswithcode.com/paper/exact-confidence-interval-for-generalized |
| Repo | |
| Framework | |
A Contextual Hierarchical Graph Model for Generating Random Sequences of Objects with Application to Music Playlists
| Title | A Contextual Hierarchical Graph Model for Generating Random Sequences of Objects with Application to Music Playlists |
| Authors | Igor de Oliveira Nunes, Gabriel Matos Cardoso Leite, Daniel Ratton Figueiredo |
| Abstract | Recommending the right content in large scale multimedia streaming services is an important and challenging problem that has received much attention in the past decade. A key ingredient for successful recommendations is an effective similarity metric between two objects, and models that leverage the current context to constrain the recommendations. This work proposes a model for random object generation that introduces two key novel elements: (i) a similarity metric based on the distance between objects in a given object sequence, that is also used to measure similarity between meta-data associated with the objects, such as artists and genres; (ii) a hierarchical graph model with different graphs each associated with a different meta-data. A biased random walk in each graph that are coupled and synchronized dictate the random generation of objects, leveraging the current context to constrain randomness. The proposed model is fully parameterized from sequences of objects, requiring no external parameters or tuning. The model is applied to a large music dataset with over 1 million playlists generating a hierarchy with three layers (genre, artist, track). Results indicate its superiority in generating actual full playlists against two baseline models. |
| Tasks | |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04273v1 |
| https://arxiv.org/pdf/1911.04273v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-contextual-hierarchical-graph-model-for |
| Repo | |
| Framework | |
Segmentation of the Prostatic Gland and the Intraprostatic Lesions on Multiparametic MRI Using Mask-RCNN
| Title | Segmentation of the Prostatic Gland and the Intraprostatic Lesions on Multiparametic MRI Using Mask-RCNN |
| Authors | Zhenzhen Dai, Eric Carver, Chang Liu, Joon Lee, Aharon Feldman, Weiwei Zong, Milan Pantelic, Mohamed Elshaikh, Ning Wen |
| Abstract | Prostate cancer (PCa) is the most common cancer in men in the United States. Multiparametic magnetic resonance imaging (mp-MRI) has been explored by many researchers to targeted prostate biopsies and radiation therapy. However, assessment on mp-MRI can be subjective, development of computer-aided diagnosis systems to automatically delineate the prostate gland and the intraprostratic lesions (ILs) becomes important to facilitate with radiologists in clinical practice. In this paper, we first study the implementation of the Mask-RCNN model to segment the prostate and ILs. We trained and evaluated models on 120 patients from two different cohorts of patients. We also used 2D U-Net and 3D U-Net as benchmarks to segment the prostate and compared the model’s performance. The contour variability of ILs using the algorithm was also benchmarked against the interobserver variability between two different radiation oncologists on 19 patients. Our results indicate that the Mask-RCNN model is able to reach state-of-art performance in the prostate segmentation and outperforms several competitive baselines in ILs segmentation. |
| Tasks | |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02575v1 |
| http://arxiv.org/pdf/1904.02575v1.pdf | |
| PWC | https://paperswithcode.com/paper/segmentation-of-the-prostatic-gland-and-the |
| Repo | |
| Framework | |
A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning
| Title | A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning |
| Authors | Thanh-Toan Do, Toan Tran, Ian Reid, Vijay Kumar, Tuan Hoang, Gustavo Carneiro |
| Abstract | We propose a method that substantially improves the efficiency of deep distance metric learning based on the optimization of the triplet loss function. One epoch of such training process based on a naive optimization of the triplet loss function has a run-time complexity O(N^3), where N is the number of training samples. Such optimization scales poorly, and the most common approach proposed to address this high complexity issue is based on sub-sampling the set of triplets needed for the training process. Another approach explored in the field relies on an ad-hoc linearization (in terms of N) of the triplet loss that introduces class centroids, which must be optimized using the whole training set for each mini-batch - this means that a naive implementation of this approach has run-time complexity O(N^2). This complexity issue is usually mitigated with poor, but computationally cheap, approximate centroid optimization methods. In this paper, we first propose a solid theory on the linearization of the triplet loss with the use of class centroids, where the main conclusion is that our new linear loss represents a tight upper-bound to the triplet loss. Furthermore, based on the theory above, we propose a training algorithm that no longer requires the centroid optimization step, which means that our approach is the first in the field with a guaranteed linear run-time complexity. We show that the training of deep distance metric learning methods using the proposed upper-bound is substantially faster than triplet-based methods, while producing competitive retrieval accuracy results on benchmark datasets (CUB-200-2011 and CAR196). |
| Tasks | Metric Learning |
| Published | 2019-04-18 |
| URL | http://arxiv.org/abs/1904.08720v1 |
| http://arxiv.org/pdf/1904.08720v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-theoretically-sound-upper-bound-on-the |
| Repo | |
| Framework | |
Robust Regression via Deep Negative Correlation Learning
| Title | Robust Regression via Deep Negative Correlation Learning |
| Authors | Le Zhang, Zenglin Shi, Ming-Ming Cheng, Yun Liu, Jia-Wang Bian, Joey Tianyi Zhou, Guoyan Zheng, Zeng Zeng |
| Abstract | Nonlinear regression has been extensively employed in many computer vision problems (e.g., crowd counting, age estimation, affective computing). Under the umbrella of deep learning, two common solutions exist i) transforming nonlinear regression to a robust loss function which is jointly optimizable with the deep convolutional network, and ii) utilizing ensemble of deep networks. Although some improved performance is achieved, the former may be lacking due to the intrinsic limitation of choosing a single hypothesis and the latter usually suffers from much larger computational complexity. To cope with those issues, we propose to regress via an efficient “divide and conquer” manner. The core of our approach is the generalization of negative correlation learning that has been shown, both theoretically and empirically, to work well for non-deep regression problems. Without extra parameters, the proposed method controls the bias-variance-covariance trade-off systematically and usually yields a deep regression ensemble where each base model is both “accurate” and “diversified”. Moreover, we show that each sub-problem in the proposed method has less Rademacher Complexity and thus is easier to optimize. Extensive experiments on several diverse and challenging tasks including crowd counting, personality analysis, age estimation, and image super-resolution demonstrate the superiority over challenging baselines as well as the versatility of the proposed method. |
| Tasks | Age Estimation, Crowd Counting, Image Super-Resolution, Super-Resolution |
| Published | 2019-08-24 |
| URL | https://arxiv.org/abs/1908.09066v1 |
| https://arxiv.org/pdf/1908.09066v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-regression-via-deep-negative |
| Repo | |
| Framework | |
