Paper Group ANR 19
Fusarium Damaged Kernels Detection Using Transfer Learning on Deep Neural Network Architecture. Motivating the Rules of the Game for Adversarial Example Research. Adversarial vulnerability for any classifier. Representation Learning for Spatial Graphs. On Bi-Objective convex-quadratic problems. Multi-Task Learning with Incomplete Data for Healthcar …
Fusarium Damaged Kernels Detection Using Transfer Learning on Deep Neural Network Architecture
Title | Fusarium Damaged Kernels Detection Using Transfer Learning on Deep Neural Network Architecture |
Authors | Márcio Nicolau, Márcia Barrocas Moreira Pimentel, Casiane Salete Tibola, José Mauricio Cunha Fernandes, Willingthon Pavan |
Abstract | The present work shows the application of transfer learning for a pre-trained deep neural network (DNN), using a small image dataset ($\approx$ 12,000) on a single workstation with enabled NVIDIA GPU card that takes up to 1 hour to complete the training task and archive an overall average accuracy of $94.7%$. The DNN presents a $20%$ score of misclassification for an external test dataset. The accuracy of the proposed methodology is equivalent to ones using HSI methodology $(81%-91%)$ used for the same task, but with the advantage of being independent on special equipment to classify wheat kernel for FHB symptoms. |
Tasks | Transfer Learning |
Published | 2018-01-31 |
URL | http://arxiv.org/abs/1802.00030v1 |
http://arxiv.org/pdf/1802.00030v1.pdf | |
PWC | https://paperswithcode.com/paper/fusarium-damaged-kernels-detection-using |
Repo | |
Framework | |
Motivating the Rules of the Game for Adversarial Example Research
Title | Motivating the Rules of the Game for Adversarial Example Research |
Authors | Justin Gilmer, Ryan P. Adams, Ian Goodfellow, David Andersen, George E. Dahl |
Abstract | Advances in machine learning have led to broad deployment of systems with impressive performance on important problems. Nonetheless, these systems can be induced to make errors on data that are surprisingly similar to examples the learned system handles correctly. The existence of these errors raises a variety of questions about out-of-sample generalization and whether bad actors might use such examples to abuse deployed systems. As a result of these security concerns, there has been a flurry of recent papers proposing algorithms to defend against such malicious perturbations of correctly handled examples. It is unclear how such misclassifications represent a different kind of security problem than other errors, or even other attacker-produced examples that have no specific relationship to an uncorrupted input. In this paper, we argue that adversarial example defense papers have, to date, mostly considered abstract, toy games that do not relate to any specific security concern. Furthermore, defense papers have not yet precisely described all the abilities and limitations of attackers that would be relevant in practical security. Towards this end, we establish a taxonomy of motivations, constraints, and abilities for more plausible adversaries. Finally, we provide a series of recommendations outlining a path forward for future work to more clearly articulate the threat model and perform more meaningful evaluation. |
Tasks | |
Published | 2018-07-18 |
URL | http://arxiv.org/abs/1807.06732v2 |
http://arxiv.org/pdf/1807.06732v2.pdf | |
PWC | https://paperswithcode.com/paper/motivating-the-rules-of-the-game-for |
Repo | |
Framework | |
Adversarial vulnerability for any classifier
Title | Adversarial vulnerability for any classifier |
Authors | Alhussein Fawzi, Hamza Fawzi, Omar Fawzi |
Abstract | Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven empirically to be very intricate to address. In this paper, we study the phenomenon of adversarial perturbations under the assumption that the data is generated with a smooth generative model. We derive fundamental upper bounds on the robustness to perturbations of any classification function, and prove the existence of adversarial perturbations that transfer well across different classifiers with small risk. Our analysis of the robustness also provides insights onto key properties of generative models, such as their smoothness and dimensionality of latent space. We conclude with numerical experimental results showing that our bounds provide informative baselines to the maximal achievable robustness on several datasets. |
Tasks | |
Published | 2018-02-23 |
URL | http://arxiv.org/abs/1802.08686v2 |
http://arxiv.org/pdf/1802.08686v2.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-vulnerability-for-any-classifier |
Repo | |
Framework | |
Representation Learning for Spatial Graphs
Title | Representation Learning for Spatial Graphs |
Authors | Zheng Wang, Ce Ju, Gao Cong, Cheng Long |
Abstract | Recently, the topic of graph representation learning has received plenty of attention. Existing approaches usually focus on structural properties only and thus they are not sufficient for those spatial graphs where the nodes are associated with some spatial information. In this paper, we present the first deep learning approach called s2vec for learning spatial graph representations, which is based on denoising autoencoders framework (DAF). We evaluate the learned representations on real datasets and the results verified the effectiveness of s2vec when used for spatial clustering. |
Tasks | Denoising, Graph Representation Learning, Representation Learning |
Published | 2018-12-17 |
URL | http://arxiv.org/abs/1812.06668v4 |
http://arxiv.org/pdf/1812.06668v4.pdf | |
PWC | https://paperswithcode.com/paper/representation-learning-for-spatial-graphs |
Repo | |
Framework | |
On Bi-Objective convex-quadratic problems
Title | On Bi-Objective convex-quadratic problems |
Authors | Cheikh Toure, Anne Auger, Dimo Brockhoff, Nikolaus Hansen |
Abstract | In this paper we analyze theoretical properties of bi-objective convex-quadratic problems. We give a complete description of their Pareto set and prove the convexity of their Pareto front. We show that the Pareto set is a line segment when both Hessian matrices are proportional. We then propose a novel set of convex-quadratic test problems, describe their theoretical properties and the algorithm abilities required by those test problems. This includes in particular testing the sensitivity with respect to separability, ill-conditioned problems, rotational invariance, and whether the Pareto set is aligned with the coordinate axis. |
Tasks | |
Published | 2018-12-01 |
URL | http://arxiv.org/abs/1812.00289v1 |
http://arxiv.org/pdf/1812.00289v1.pdf | |
PWC | https://paperswithcode.com/paper/on-bi-objective-convex-quadratic-problems |
Repo | |
Framework | |
Multi-Task Learning with Incomplete Data for Healthcare
Title | Multi-Task Learning with Incomplete Data for Healthcare |
Authors | Xin J. Hunt, Saba Emrani, Ilknur Kaynar Kabul, Jorge Silva |
Abstract | Multi-task learning is a type of transfer learning that trains multiple tasks simultaneously and leverages the shared information between related tasks to improve the generalization performance. However, missing features in the input matrix is a much more difficult problem which needs to be carefully addressed. Removing records with missing values can significantly reduce the sample size, which is impractical for datasets with large percentage of missing values. Popular imputation methods often distort the covariance structure of the data, which causes inaccurate inference. In this paper we propose using plug-in covariance matrix estimators to tackle the challenge of missing features. Specifically, we analyze the plug-in estimators under the framework of robust multi-task learning with LASSO and graph regularization, which captures the relatedness between tasks via graph regularization. We use the Alzheimer’s disease progression dataset as an example to show how the proposed framework is effective for prediction and model estimation when missing data is present. |
Tasks | Imputation, Multi-Task Learning, Transfer Learning |
Published | 2018-07-06 |
URL | http://arxiv.org/abs/1807.02442v1 |
http://arxiv.org/pdf/1807.02442v1.pdf | |
PWC | https://paperswithcode.com/paper/multi-task-learning-with-incomplete-data-for |
Repo | |
Framework | |
Information Theory: A Tutorial Introduction
Title | Information Theory: A Tutorial Introduction |
Authors | James V Stone |
Abstract | Shannon’s mathematical theory of communication defines fundamental limits on how much information can be transmitted between the different components of any man-made or biological system. This paper is an informal but rigorous introduction to the main ideas implicit in Shannon’s theory. An annotated reading list is provided for further reading. |
Tasks | |
Published | 2018-02-16 |
URL | https://arxiv.org/abs/1802.05968v3 |
https://arxiv.org/pdf/1802.05968v3.pdf | |
PWC | https://paperswithcode.com/paper/information-theory-a-tutorial-introduction |
Repo | |
Framework | |
Learning to Jointly Translate and Predict Dropped Pronouns with a Shared Reconstruction Mechanism
Title | Learning to Jointly Translate and Predict Dropped Pronouns with a Shared Reconstruction Mechanism |
Authors | Longyue Wang, Zhaopeng Tu, Andy Way, Qun Liu |
Abstract | Pronouns are frequently omitted in pro-drop languages, such as Chinese, generally leading to significant challenges with respect to the production of complete translations. Recently, Wang et al. (2018) proposed a novel reconstruction-based approach to alleviating dropped pronoun (DP) translation problems for neural machine translation models. In this work, we improve the original model from two perspectives. First, we employ a shared reconstructor to better exploit encoder and decoder representations. Second, we jointly learn to translate and predict DPs in an end-to-end manner, to avoid the errors propagated from an external DP prediction model. Experimental results show that our approach significantly improves both translation performance and DP prediction accuracy. |
Tasks | Machine Translation |
Published | 2018-10-15 |
URL | http://arxiv.org/abs/1810.06195v1 |
http://arxiv.org/pdf/1810.06195v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-to-jointly-translate-and-predict |
Repo | |
Framework | |
Combining Sentinel-1 and Sentinel-2 Time Series via RNN for object-based land cover classification
Title | Combining Sentinel-1 and Sentinel-2 Time Series via RNN for object-based land cover classification |
Authors | Dino Ienco, Raffaele Gaetano, Roberto Interdonato Kenji Ose, Dinh Ho Tong Minh |
Abstract | Radar and Optical Satellite Image Time Series (SITS) are sources of information that are commonly employed to monitor earth surfaces for tasks related to ecology, agriculture, mobility, land management planning and land cover monitoring. Many studies have been conducted using one of the two sources, but how to smartly combine the complementary information provided by radar and optical SITS is still an open challenge. In this context, we propose a new neural architecture for the combination of Sentinel-1 (S1) and Sentinel-2 (S2) imagery at object level, applied to a real-world land cover classification task. Experiments carried out on the Reunion Island, a overseas department of France in the Indian Ocean, demonstrate the significance of our proposal. |
Tasks | Time Series |
Published | 2018-12-13 |
URL | http://arxiv.org/abs/1812.05530v1 |
http://arxiv.org/pdf/1812.05530v1.pdf | |
PWC | https://paperswithcode.com/paper/combining-sentinel-1-and-sentinel-2-time |
Repo | |
Framework | |
Fast K-Means Clustering with Anderson Acceleration
Title | Fast K-Means Clustering with Anderson Acceleration |
Authors | Juyong Zhang, Yuxin Yao, Yue Peng, Hao Yu, Bailin Deng |
Abstract | We propose a novel method to accelerate Lloyd’s algorithm for K-Means clustering. Unlike previous acceleration approaches that reduce computational cost per iterations or improve initialization, our approach is focused on reducing the number of iterations required for convergence. This is achieved by treating the assignment step and the update step of Lloyd’s algorithm as a fixed-point iteration, and applying Anderson acceleration, a well-established technique for accelerating fixed-point solvers. Classical Anderson acceleration utilizes m previous iterates to find an accelerated iterate, and its performance on K-Means clustering can be sensitive to choice of m and the distribution of samples. We propose a new strategy to dynamically adjust the value of m, which achieves robust and consistent speedups across different problem instances. Our method complements existing acceleration techniques, and can be combined with them to achieve state-of-the-art performance. We perform extensive experiments to evaluate the performance of the proposed method, where it outperforms other algorithms in 106 out of 120 test cases, and the mean decrease ratio of computational time is more than 33%. |
Tasks | |
Published | 2018-05-27 |
URL | http://arxiv.org/abs/1805.10638v1 |
http://arxiv.org/pdf/1805.10638v1.pdf | |
PWC | https://paperswithcode.com/paper/fast-k-means-clustering-with-anderson |
Repo | |
Framework | |
Self-supervised Learning for Dense Depth Estimation in Monocular Endoscopy
Title | Self-supervised Learning for Dense Depth Estimation in Monocular Endoscopy |
Authors | Xingtong Liu, Ayushi Sinha, Mathias Unberath, Masaru Ishii, Gregory Hager, Russell H. Taylor, Austin Reiter |
Abstract | We present a self-supervised approach to training convolutional neural networks for dense depth estimation from monocular endoscopy data without a priori modeling of anatomy or shading. Our method only requires sequential data from monocular endoscopic videos and a multi-view stereo reconstruction method, e.g. structure from motion, that supervises learning in a sparse but accurate manner. Consequently, our method requires neither manual interaction, such as scaling or labeling, nor patient CT in the training and application phases. We demonstrate the performance of our method on sinus endoscopy data from two patients and validate depth prediction quantitatively using corresponding patient CT scans where we found submillimeter residual errors. |
Tasks | Depth Estimation |
Published | 2018-06-25 |
URL | http://arxiv.org/abs/1806.09521v2 |
http://arxiv.org/pdf/1806.09521v2.pdf | |
PWC | https://paperswithcode.com/paper/self-supervised-learning-for-dense-depth-1 |
Repo | |
Framework | |
Learning sparse optimal rule fit by safe screening
Title | Learning sparse optimal rule fit by safe screening |
Authors | Hiroki Kato, Hiroyuki Hanada, Ichiro Takeuchi |
Abstract | In this paper, we consider linear prediction models in the form of a sparse linear combination of rules, where a rule is an indicator function defined over a hyperrectangle in the input space. Since the number of all possible rules generated from the training dataset becomes extremely large, it has been difficult to consider all of them when fitting a sparse model. In this paper, we propose Safe Optimal Rule Fit (SORF) as an approach to resolve this problem, which is formulated as a convex optimization problem with sparse regularization. The proposed SORF method utilizes the fact that the set of all possible rules can be represented as a tree. By extending a recently popularized convex optimization technique called safe screening, we develop a novel method for pruning the tree such that pruned nodes are guaranteed to be irrelevant to the prediction model. This approach allows us to efficiently learn a prediction model constructed from an exponentially large number of all possible rules. We demonstrate the usefulness of the proposed method by numerical experiments using several benchmark datasets. |
Tasks | |
Published | 2018-10-03 |
URL | http://arxiv.org/abs/1810.01683v1 |
http://arxiv.org/pdf/1810.01683v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-sparse-optimal-rule-fit-by-safe |
Repo | |
Framework | |
Deep Learning Architectures for Face Recognition in Video Surveillance
Title | Deep Learning Architectures for Face Recognition in Video Surveillance |
Authors | Saman Bashbaghi, Eric Granger, Robert Sabourin, Mostafa Parchami |
Abstract | Face recognition (FR) systems for video surveillance (VS) applications attempt to accurately detect the presence of target individuals over a distributed network of cameras. In video-based FR systems, facial models of target individuals are designed a priori during enrollment using a limited number of reference still images or video data. These facial models are not typically representative of faces being observed during operations due to large variations in illumination, pose, scale, occlusion, blur, and to camera inter-operability. Specifically, in still-to-video FR application, a single high-quality reference still image captured with still camera under controlled conditions is employed to generate a facial model to be matched later against lower-quality faces captured with video cameras under uncontrolled conditions. Current video-based FR systems can perform well on controlled scenarios, while their performance is not satisfactory in uncontrolled scenarios mainly because of the differences between the source (enrollment) and the target (operational) domains. Most of the efforts in this area have been toward the design of robust video-based FR systems in unconstrained surveillance environments. This chapter presents an overview of recent advances in still-to-video FR scenario through deep convolutional neural networks (CNNs). In particular, deep learning architectures proposed in the literature based on triplet-loss function (e.g., cross-correlation matching CNN, trunk-branch ensemble CNN and HaarNet) and supervised autoencoders (e.g., canonical face representation CNN) are reviewed and compared in terms of accuracy and computational complexity. |
Tasks | Face Recognition |
Published | 2018-02-27 |
URL | http://arxiv.org/abs/1802.09990v2 |
http://arxiv.org/pdf/1802.09990v2.pdf | |
PWC | https://paperswithcode.com/paper/deep-learning-architectures-for-face |
Repo | |
Framework | |
Jointly Detecting and Separating Singing Voice: A Multi-Task Approach
Title | Jointly Detecting and Separating Singing Voice: A Multi-Task Approach |
Authors | Daniel Stoller, Sebastian Ewert, Simon Dixon |
Abstract | A main challenge in applying deep learning to music processing is the availability of training data. One potential solution is Multi-task Learning, in which the model also learns to solve related auxiliary tasks on additional datasets to exploit their correlation. While intuitive in principle, it can be challenging to identify related tasks and construct the model to optimally share information between tasks. In this paper, we explore vocal activity detection as an additional task to stabilise and improve the performance of vocal separation. Further, we identify problematic biases specific to each dataset that could limit the generalisation capability of separation and detection models, to which our proposed approach is robust. Experiments show improved performance in separation as well as vocal detection compared to single-task baselines. However, we find that the commonly used Signal-to-Distortion Ratio (SDR) metrics did not capture the improvement on non-vocal sections, indicating the need for improved evaluation methodologies. |
Tasks | Action Detection, Activity Detection, Multi-Task Learning |
Published | 2018-04-05 |
URL | http://arxiv.org/abs/1804.01650v1 |
http://arxiv.org/pdf/1804.01650v1.pdf | |
PWC | https://paperswithcode.com/paper/jointly-detecting-and-separating-singing |
Repo | |
Framework | |
Part-Aligned Bilinear Representations for Person Re-identification
Title | Part-Aligned Bilinear Representations for Person Re-identification |
Authors | Yumin Suh, Jingdong Wang, Siyu Tang, Tao Mei, Kyoung Mu Lee |
Abstract | We propose a novel network that learns a part-aligned representation for person re-identification. It handles the body part misalignment problem, that is, body parts are misaligned across human detections due to pose/viewpoint change and unreliable detection. Our model consists of a two-stream network (one stream for appearance map extraction and the other one for body part map extraction) and a bilinear-pooling layer that generates and spatially pools a part-aligned map. Each local feature of the part-aligned map is obtained by a bilinear mapping of the corresponding local appearance and body part descriptors. Our new representation leads to a robust image matching similarity, which is equivalent to an aggregation of the local similarities of the corresponding body parts combined with the weighted appearance similarity. This part-aligned representation reduces the part misalignment problem significantly. Our approach is also advantageous over other pose-guided representations (e.g., extracting representations over the bounding box of each body part) by learning part descriptors optimal for person re-identification. For training the network, our approach does not require any part annotation on the person re-identification dataset. Instead, we simply initialize the part sub-stream using a pre-trained sub-network of an existing pose estimation network, and train the whole network to minimize the re-identification loss. We validate the effectiveness of our approach by demonstrating its superiority over the state-of-the-art methods on the standard benchmark datasets, including Market-1501, CUHK03, CUHK01 and DukeMTMC, and standard video dataset MARS. |
Tasks | Person Re-Identification, Pose Estimation |
Published | 2018-04-19 |
URL | http://arxiv.org/abs/1804.07094v1 |
http://arxiv.org/pdf/1804.07094v1.pdf | |
PWC | https://paperswithcode.com/paper/part-aligned-bilinear-representations-for |
Repo | |
Framework | |