Paper Group ANR 863
SwipeCut: Interactive Segmentation with Diversified Seed Proposals. Dataset: Rare Event Classification in Multivariate Time Series. European Court of Human Right Open Data project. Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization. CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition. …
SwipeCut: Interactive Segmentation with Diversified Seed Proposals
| Title | SwipeCut: Interactive Segmentation with Diversified Seed Proposals |
| Authors | Ding-Jie Chen, Hwann-Tzong Chen, Long-Wen Chang |
| Abstract | Interactive image segmentation algorithms rely on the user to provide annotations as the guidance. When the task of interactive segmentation is performed on a small touchscreen device, the requirement of providing precise annotations could be cumbersome to the user. We design an efficient seed proposal method that actively proposes annotation seeds for the user to label. The user only needs to check which ones of the query seeds are inside the region of interest (ROI). We enforce the sparsity and diversity criteria on the selection of the query seeds. At each round of interaction the user is only presented with a small number of informative query seeds that are far apart from each other. As a result, we are able to derive a user friendly interaction mechanism for annotation on small touchscreen devices. The user merely has to swipe through on the ROI-relevant query seeds, which should be easy since those gestures are commonly used on a touchscreen. The performance of our algorithm is evaluated on six publicly available datasets. The evaluation results show that our algorithm achieves high segmentation accuracy, with short response time and less user feedback. |
| Tasks | Interactive Segmentation, Semantic Segmentation |
| Published | 2018-12-18 |
| URL | http://arxiv.org/abs/1812.07260v1 |
| http://arxiv.org/pdf/1812.07260v1.pdf | |
| PWC | https://paperswithcode.com/paper/swipecut-interactive-segmentation-with |
| Repo | |
| Framework | |
Dataset: Rare Event Classification in Multivariate Time Series
| Title | Dataset: Rare Event Classification in Multivariate Time Series |
| Authors | Chitta Ranjan, Mahendranath Reddy, Markku Mustonen, Kamran Paynabar, Karim Pourak |
| Abstract | A real-world dataset is provided from a pulp-and-paper manufacturing industry. The dataset comes from a multivariate time series process. The data contains a rare event of paper break that commonly occurs in the industry. The data contains sensor readings at regular time-intervals (x’s) and the event label (y). The primary purpose of the data is thought to be building a classification model for early prediction of the rare event. However, it can also be used for multivariate time series data exploration and building other supervised and unsupervised models. |
| Tasks | Time Series |
| Published | 2018-09-27 |
| URL | https://arxiv.org/abs/1809.10717v4 |
| https://arxiv.org/pdf/1809.10717v4.pdf | |
| PWC | https://paperswithcode.com/paper/dataset-rare-event-classification-in |
| Repo | |
| Framework | |
European Court of Human Right Open Data project
| Title | European Court of Human Right Open Data project |
| Authors | Alexandre Quemy |
| Abstract | This paper presents thirteen datasets for binary, multiclass and multilabel classification based on the European Court of Human Rights judgments since its creation. The interest of such datasets is explained through the prism of the researcher, the data scientist, the citizen and the legal practitioner. Contrarily to many datasets, the creation process, from the collection of raw data to the feature transformation, is provided under the form of a collection of fully automated and open-source scripts. It ensures reproducibility and a high level of confidence in the processed data, which is some of the most important issues in data governance nowadays. A first experimental campaign is performed to study some predictability properties and to establish baseline results on popular machine learning algorithms. The results are consistently good across the binary datasets with an accuracy comprised between 75.86% and 98.32% for an average accuracy of 96.45%. |
| Tasks | |
| Published | 2018-10-07 |
| URL | http://arxiv.org/abs/1810.03115v2 |
| http://arxiv.org/pdf/1810.03115v2.pdf | |
| PWC | https://paperswithcode.com/paper/european-court-of-human-right-open-data |
| Repo | |
| Framework | |
Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization
| Title | Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization |
| Authors | Jie Cao, Yibo Hu, Hongwen Zhang, Ran He, Zhenan Sun |
| Abstract | Face frontalization refers to the process of synthesizing the frontal view of a face from a given profile. Due to self-occlusion and appearance distortion in the wild, it is extremely challenging to recover faithful results and preserve texture details in a high-resolution. This paper proposes a High Fidelity Pose Invariant Model (HF-PIM) to produce photographic and identity-preserving results. HF-PIM frontalizes the profiles through a novel texture warping procedure and leverages a dense correspondence field to bind the 2D and 3D surface spaces. We decompose the prerequisite of warping into dense correspondence field estimation and facial texture map recovering, which are both well addressed by deep networks. Different from those reconstruction methods relying on 3D data, we also propose Adversarial Residual Dictionary Learning (ARDL) to supervise facial texture map recovering with only monocular images. Exhaustive experiments on both controlled and uncontrolled environments demonstrate that the proposed method not only boosts the performance of pose-invariant face recognition but also dramatically improves high-resolution frontalization appearances. |
| Tasks | Dictionary Learning, Face Recognition, Robust Face Recognition |
| Published | 2018-06-22 |
| URL | http://arxiv.org/abs/1806.08472v2 |
| http://arxiv.org/pdf/1806.08472v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-high-fidelity-pose-invariant-model |
| Repo | |
| Framework | |
CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition
| Title | CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition |
| Authors | Xuejing Yuan, Yuxuan Chen, Yue Zhao, Yunhui Long, Xiaokang Liu, Kai Chen, Shengzhi Zhang, Heqing Huang, Xiaofeng Wang, Carl A. Gunter |
| Abstract | The popularity of ASR (automatic speech recognition) systems, like Google Voice, Cortana, brings in security concerns, as demonstrated by recent attacks. The impacts of such threats, however, are less clear, since they are either less stealthy (producing noise-like voice commands) or requiring the physical presence of an attack device (using ultrasound). In this paper, we demonstrate that not only are more practical and surreptitious attacks feasible but they can even be automatically constructed. Specifically, we find that the voice commands can be stealthily embedded into songs, which, when played, can effectively control the target system through ASR without being noticed. For this purpose, we developed novel techniques that address a key technical challenge: integrating the commands into a song in a way that can be effectively recognized by ASR through the air, in the presence of background noise, while not being detected by a human listener. Our research shows that this can be done automatically against real world ASR applications. We also demonstrate that such CommanderSongs can be spread through Internet (e.g., YouTube) and radio, potentially affecting millions of ASR users. We further present a new mitigation technique that controls this threat. |
| Tasks | Speech Recognition |
| Published | 2018-01-24 |
| URL | http://arxiv.org/abs/1801.08535v3 |
| http://arxiv.org/pdf/1801.08535v3.pdf | |
| PWC | https://paperswithcode.com/paper/commandersong-a-systematic-approach-for |
| Repo | |
| Framework | |
Generating Continuous Representations of Medical Texts
| Title | Generating Continuous Representations of Medical Texts |
| Authors | Graham Spinks, Marie-Francine Moens |
| Abstract | We present an architecture that generates medical texts while learning an informative, continuous representation with discriminative features. During training the input to the system is a dataset of captions for medical X-Rays. The acquired continuous representations are of particular interest for use in many machine learning techniques where the discrete and high-dimensional nature of textual input is an obstacle. We use an Adversarially Regularized Autoencoder to create realistic text in both an unconditional and conditional setting. We show that this technique is applicable to medical texts which often contain syntactic and domain-specific shorthands. A quantitative evaluation shows that we achieve a lower model perplexity than a traditional LSTM generator. |
| Tasks | |
| Published | 2018-05-15 |
| URL | http://arxiv.org/abs/1805.05691v1 |
| http://arxiv.org/pdf/1805.05691v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-continuous-representations-of |
| Repo | |
| Framework | |
Multi-Objective Cognitive Model: a supervised approach for multi-subject fMRI analysis
| Title | Multi-Objective Cognitive Model: a supervised approach for multi-subject fMRI analysis |
| Authors | Muhammad Yousefnezhad, Daoqiang Zhang |
| Abstract | In order to decode the human brain, Multivariate Pattern (MVP) classification generates cognitive models by using functional Magnetic Resonance Imaging (fMRI) datasets. As a standard pipeline in the MVP analysis, brain patterns in multi-subject fMRI dataset must be mapped to a shared space and then a classification model is generated by employing the mapped patterns. However, the MVP models may not provide stable performance on a new fMRI dataset because the standard pipeline uses disjoint steps for generating these models. Indeed, each step in the pipeline includes an objective function with independent optimization approach, where the best solution of each step may not be optimum for the next steps. For tackling the mentioned issue, this paper introduces the Multi-Objective Cognitive Model (MOCM) that utilizes an integrated objective function for MVP analysis rather than just using those disjoint steps. For solving the integrated problem, we proposed a customized multi-objective optimization approach, where all possible solutions are firstly generated, and then our method ranks and selects the robust solutions as the final results. Empirical studies confirm that the proposed method can generate superior performance in comparison with other techniques. |
| Tasks | |
| Published | 2018-08-05 |
| URL | http://arxiv.org/abs/1808.01642v1 |
| http://arxiv.org/pdf/1808.01642v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-objective-cognitive-model-a-supervised |
| Repo | |
| Framework | |
Compositional Representation of Morphologically-Rich Input for Neural Machine Translation
| Title | Compositional Representation of Morphologically-Rich Input for Neural Machine Translation |
| Authors | Duygu Ataman, Marcello Federico |
| Abstract | Neural machine translation (NMT) models are typically trained with fixed-size input and output vocabularies, which creates an important bottleneck on their accuracy and generalization capability. As a solution, various studies proposed segmenting words into sub-word units and performing translation at the sub-lexical level. However, statistical word segmentation methods have recently shown to be prone to morphological errors, which can lead to inaccurate translations. In this paper, we propose to overcome this problem by replacing the source-language embedding layer of NMT with a bi-directional recurrent neural network that generates compositional representations of the input at any desired level of granularity. We test our approach in a low-resource setting with five languages from different morphological typologies, and under different composition assumptions. By training NMT to compose word representations from character n-grams, our approach consistently outperforms (from 1.71 to 2.48 BLEU points) NMT learning embeddings of statistically generated sub-word units. |
| Tasks | Machine Translation |
| Published | 2018-05-05 |
| URL | http://arxiv.org/abs/1805.02036v1 |
| http://arxiv.org/pdf/1805.02036v1.pdf | |
| PWC | https://paperswithcode.com/paper/compositional-representation-of |
| Repo | |
| Framework | |
Diversified Late Acceptance Search
| Title | Diversified Late Acceptance Search |
| Authors | Majid Namazi, Conrad Sanderson, M. A. Hakim Newton, M. M. A. Polash, Abdul Sattar |
| Abstract | The well-known Late Acceptance Hill Climbing (LAHC) search aims to overcome the main downside of traditional Hill Climbing (HC) search, which is often quickly trapped in a local optimum due to strictly accepting only non-worsening moves within each iteration. In contrast, LAHC also accepts worsening moves, by keeping a circular array of fitness values of previously visited solutions and comparing the fitness values of candidate solutions against the least recent element in the array. While this straightforward strategy has proven effective, there are nevertheless situations where LAHC can unfortunately behave in a similar manner to HC. For example, when a new local optimum is found, often the same fitness value is stored many times in the array. To address this shortcoming, we propose new acceptance and replacement strategies to take into account worsening, improving, and sideways movement scenarios with the aim to improve the diversity of values in the array. Compared to LAHC, the proposed Diversified Late Acceptance Search approach is shown to lead to better quality solutions that are obtained with a lower number of iterations on benchmark Travelling Salesman Problems and Quadratic Assignment Problems. |
| Tasks | |
| Published | 2018-06-25 |
| URL | http://arxiv.org/abs/1806.09328v3 |
| http://arxiv.org/pdf/1806.09328v3.pdf | |
| PWC | https://paperswithcode.com/paper/diversified-late-acceptance-search |
| Repo | |
| Framework | |
Direct Acceleration of SAGA using Sampled Negative Momentum
| Title | Direct Acceleration of SAGA using Sampled Negative Momentum |
| Authors | Kaiwen Zhou |
| Abstract | Variance reduction is a simple and effective technique that accelerates convex (or non-convex) stochastic optimization. Among existing variance reduction methods, SVRG and SAGA adopt unbiased gradient estimators and are the most popular variance reduction methods in recent years. Although various accelerated variants of SVRG (e.g., Katyusha and Acc-Prox-SVRG) have been proposed, the direct acceleration of SAGA still remains unknown. In this paper, we propose a directly accelerated variant of SAGA using a novel Sampled Negative Momentum (SSNM), which achieves the best known oracle complexity for strongly convex problems (with known strong convexity parameter). Consequently, our work fills the void of directly accelerated SAGA. |
| Tasks | Stochastic Optimization |
| Published | 2018-06-28 |
| URL | http://arxiv.org/abs/1806.11048v4 |
| http://arxiv.org/pdf/1806.11048v4.pdf | |
| PWC | https://paperswithcode.com/paper/direct-acceleration-of-saga-using-sampled |
| Repo | |
| Framework | |
A mullti- or many- objective evolutionary algorithm with global loop update
| Title | A mullti- or many- objective evolutionary algorithm with global loop update |
| Authors | Yingyu Zhang, Bing Zeng, Yuanzhen Li, Junqing Li |
| Abstract | Multi- or many-objective evolutionary algorithm- s(MOEAs), especially the decomposition-based MOEAs have been widely concerned in recent years. The decomposition-based MOEAs emphasize convergence and diversity in a simple model and have made a great success in dealing with theoretical and practical multi- or many-objective optimization problems. In this paper, we focus on update strategies of the decomposition- based MOEAs, and their criteria for comparing solutions. Three disadvantages of the decomposition-based MOEAs with local update strategies and several existing criteria for comparing solutions are analyzed and discussed. And a global loop update strategy and two hybrid criteria are suggested. Subsequently, an evolutionary algorithm with the global loop update is implement- ed and compared to several of the best multi- or many-objective optimization algorithms on two famous unconstraint test suites with up to 15 objectives. Experimental results demonstrate that unlike evolutionary algorithms with local update strategies, the population of our algorithm does not degenerate at any generation of its evolution, which guarantees the diversity of the resulting population. In addition, our algorithm wins in most instances of the two test suites, indicating that it is very compet- itive in terms of convergence and diversity. Running results of our algorithm with different criteria for comparing solutions are also compared. Their differences are very significant, indicating that the performance of our algorithm is affected by the criterion it adopts. |
| Tasks | |
| Published | 2018-01-25 |
| URL | http://arxiv.org/abs/1803.06282v1 |
| http://arxiv.org/pdf/1803.06282v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-mullti-or-many-objective-evolutionary |
| Repo | |
| Framework | |
Metamorphic Relation Based Adversarial Attacks on Differentiable Neural Computer
| Title | Metamorphic Relation Based Adversarial Attacks on Differentiable Neural Computer |
| Authors | Alvin Chan, Lei Ma, Felix Juefei-Xu, Xiaofei Xie, Yang Liu, Yew Soon Ong |
| Abstract | Deep neural networks (DNN), while becoming the driving force of many novel technology and achieving tremendous success in many cutting-edge applications, are still vulnerable to adversarial attacks. Differentiable neural computer (DNC) is a novel computing machine with DNN as its central controller operating on an external memory module for data processing. The unique architecture of DNC contributes to its state-of-the-art performance in tasks which requires the ability to represent variables and data structure as well as to store data over long timescales. However, there still lacks a comprehensive study on how adversarial examples affect DNC in terms of robustness. In this paper, we propose metamorphic relation based adversarial techniques for a range of tasks described in the natural processing language domain. We show that the near-perfect performance of the DNC in bAbI logical question answering tasks can be degraded by adversarially injected sentences. We further perform in-depth study on the role of DNC’s memory size in its robustness and analyze the potential reason causing why DNC fails. Our study demonstrates the current challenges and potential opportunities towards constructing more robust DNCs. |
| Tasks | Question Answering |
| Published | 2018-09-07 |
| URL | http://arxiv.org/abs/1809.02444v1 |
| http://arxiv.org/pdf/1809.02444v1.pdf | |
| PWC | https://paperswithcode.com/paper/metamorphic-relation-based-adversarial |
| Repo | |
| Framework | |
Novel Video Prediction for Large-scale Scene using Optical Flow
| Title | Novel Video Prediction for Large-scale Scene using Optical Flow |
| Authors | Henglai Wei, Xiaochuan Yin, Penghong Lin |
| Abstract | Making predictions of future frames is a critical challenge in autonomous driving research. Most of the existing methods for video prediction attempt to generate future frames in simple and fixed scenes. In this paper, we propose a novel and effective optical flow conditioned method for the task of video prediction with an application to complex urban scenes. In contrast with previous work, the prediction model only requires video sequences and optical flow sequences for training and testing. Our method uses the rich spatial-temporal features in video sequences. The method takes advantage of the motion information extracting from optical flow maps between neighbor images as well as previous images. Empirical evaluations on the KITTI dataset and the Cityscapes dataset demonstrate the effectiveness of our method. |
| Tasks | Autonomous Driving, Optical Flow Estimation, Video Prediction |
| Published | 2018-05-30 |
| URL | http://arxiv.org/abs/1805.12243v1 |
| http://arxiv.org/pdf/1805.12243v1.pdf | |
| PWC | https://paperswithcode.com/paper/novel-video-prediction-for-large-scale-scene |
| Repo | |
| Framework | |
Downstream Effects of Affirmative Action
| Title | Downstream Effects of Affirmative Action |
| Authors | Sampath Kannan, Aaron Roth, Juba Ziani |
| Abstract | We study a two-stage model, in which students are 1) admitted to college on the basis of an entrance exam which is a noisy signal about their qualifications (type), and then 2) those students who were admitted to college can be hired by an employer as a function of their college grades, which are an independently drawn noisy signal of their type. Students are drawn from one of two populations, which might have different type distributions. We assume that the employer at the end of the pipeline is rational, in the sense that it computes a posterior distribution on student type conditional on all information that it has available (college admissions, grades, and group membership), and makes a decision based on posterior expectation. We then study what kinds of fairness goals can be achieved by the college by setting its admissions rule and grading policy. For example, the college might have the goal of guaranteeing equal opportunity across populations: that the probability of passing through the pipeline and being hired by the employer should be independent of group membership, conditioned on type. Alternately, the college might have the goal of incentivizing the employer to have a group blind hiring rule. We show that both goals can be achieved when the college does not report grades. On the other hand, we show that under reasonable conditions, these goals are impossible to achieve even in isolation when the college uses an (even minimally) informative grading policy. |
| Tasks | |
| Published | 2018-08-27 |
| URL | http://arxiv.org/abs/1808.09004v1 |
| http://arxiv.org/pdf/1808.09004v1.pdf | |
| PWC | https://paperswithcode.com/paper/downstream-effects-of-affirmative-action |
| Repo | |
| Framework | |
Variational Option Discovery Algorithms
| Title | Variational Option Discovery Algorithms |
| Authors | Joshua Achiam, Harrison Edwards, Dario Amodei, Pieter Abbeel |
| Abstract | We explore methods for option discovery based on variational inference and make two algorithmic contributions. First: we highlight a tight connection between variational option discovery methods and variational autoencoders, and introduce Variational Autoencoding Learning of Options by Reinforcement (VALOR), a new method derived from the connection. In VALOR, the policy encodes contexts from a noise distribution into trajectories, and the decoder recovers the contexts from the complete trajectories. Second: we propose a curriculum learning approach where the number of contexts seen by the agent increases whenever the agent’s performance is strong enough (as measured by the decoder) on the current set of contexts. We show that this simple trick stabilizes training for VALOR and prior variational option discovery methods, allowing a single agent to learn many more modes of behavior than it could with a fixed context distribution. Finally, we investigate other topics related to variational option discovery, including fundamental limitations of the general approach and the applicability of learned options to downstream tasks. |
| Tasks | |
| Published | 2018-07-26 |
| URL | http://arxiv.org/abs/1807.10299v1 |
| http://arxiv.org/pdf/1807.10299v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-option-discovery-algorithms |
| Repo | |
| Framework | |
