Paper Group ANR 824
Distributed One-class Learning. MobiFace: A Novel Dataset for Mobile Face Tracking in the Wild. Structured nonlinear variable selection. Dirichlet Variational Autoencoder for Text Modeling. Optimize transfer learning for lung diseases in bronchoscopy using a new concept: sequential fine-tuning. Notes on stable learning with piecewise-linear basis f …
Distributed One-class Learning
| Title | Distributed One-class Learning |
| Authors | Ali Shahin Shamsabadi, Hamed Haddadi, Andrea Cavallaro |
| Abstract | We propose a cloud-based filter trained to block third parties from uploading privacy-sensitive images of others to online social media. The proposed filter uses Distributed One-Class Learning, which decomposes the cloud-based filter into multiple one-class classifiers. Each one-class classifier captures the properties of a class of privacy-sensitive images with an autoencoder. The multi-class filter is then reconstructed by combining the parameters of the one-class autoencoders. The training takes place on edge devices (e.g. smartphones) and therefore users do not need to upload their private and/or sensitive images to the cloud. A major advantage of the proposed filter over existing distributed learning approaches is that users cannot access, even indirectly, the parameters of other users. Moreover, the filter can cope with the imbalanced and complex distribution of the image content and the independent probability of addition of new users. We evaluate the performance of the proposed distributed filter using the exemplar task of blocking a user from sharing privacy-sensitive images of other users. In particular, we validate the behavior of the proposed multi-class filter with non-privacy-sensitive images, the accuracy when the number of classes increases, and the robustness to attacks when an adversary user has access to privacy-sensitive images of other users. |
| Tasks | One-class classifier |
| Published | 2018-02-10 |
| URL | http://arxiv.org/abs/1802.03583v1 |
| http://arxiv.org/pdf/1802.03583v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-one-class-learning |
| Repo | |
| Framework | |
MobiFace: A Novel Dataset for Mobile Face Tracking in the Wild
| Title | MobiFace: A Novel Dataset for Mobile Face Tracking in the Wild |
| Authors | Yiming Lin, Shiyang Cheng, Jie Shen, Maja Pantic |
| Abstract | Face tracking serves as the crucial initial step in mobile applications trying to analyse target faces over time in mobile settings. However, this problem has received little attention, mainly due to the scarcity of dedicated face tracking benchmarks. In this work, we introduce MobiFace, the first dataset for single face tracking in mobile situations. It consists of 80 unedited live-streaming mobile videos captured by 70 different smartphone users in fully unconstrained environments. Over $95K$ bounding boxes are manually labelled. The videos are carefully selected to cover typical smartphone usage. The videos are also annotated with 14 attributes, including 6 newly proposed attributes and 8 commonly seen in object tracking. 36 state-of-the-art trackers, including facial landmark trackers, generic object trackers and trackers that we have fine-tuned or improved, are evaluated. The results suggest that mobile face tracking cannot be solved through existing approaches. In addition, we show that fine-tuning on the MobiFace training data significantly boosts the performance of deep learning-based trackers, suggesting that MobiFace captures the unique characteristics of mobile face tracking. Our goal is to offer the community a diverse dataset to enable the design and evaluation of mobile face trackers. The dataset, annotations and the evaluation server will be on \url{https://mobiface.github.io/}. |
| Tasks | Face Detection, Object Tracking, Visual Tracking |
| Published | 2018-05-24 |
| URL | http://arxiv.org/abs/1805.09749v2 |
| http://arxiv.org/pdf/1805.09749v2.pdf | |
| PWC | https://paperswithcode.com/paper/mobiface-a-novel-dataset-for-mobile-face |
| Repo | |
| Framework | |
Structured nonlinear variable selection
| Title | Structured nonlinear variable selection |
| Authors | Magda Gregorová, Alexandros Kalousis, Stéphane Marchand-Maillet |
| Abstract | We investigate structured sparsity methods for variable selection in regression problems where the target depends nonlinearly on the inputs. We focus on general nonlinear functions not limiting a priori the function space to additive models. We propose two new regularizers based on partial derivatives as nonlinear equivalents of group lasso and elastic net. We formulate the problem within the framework of learning in reproducing kernel Hilbert spaces and show how the variational problem can be reformulated into a more practical finite dimensional equivalent. We develop a new algorithm derived from the ADMM principles that relies solely on closed forms of the proximal operators. We explore the empirical properties of our new algorithm for Nonlinear Variable Selection based on Derivatives (NVSD) on a set of experiments and confirm favourable properties of our structured-sparsity models and the algorithm in terms of both prediction and variable selection accuracy. |
| Tasks | |
| Published | 2018-05-16 |
| URL | http://arxiv.org/abs/1805.06258v1 |
| http://arxiv.org/pdf/1805.06258v1.pdf | |
| PWC | https://paperswithcode.com/paper/structured-nonlinear-variable-selection |
| Repo | |
| Framework | |
Dirichlet Variational Autoencoder for Text Modeling
| Title | Dirichlet Variational Autoencoder for Text Modeling |
| Authors | Yijun Xiao, Tiancheng Zhao, William Yang Wang |
| Abstract | We introduce an improved variational autoencoder (VAE) for text modeling with topic information explicitly modeled as a Dirichlet latent variable. By providing the proposed model topic awareness, it is more superior at reconstructing input texts. Furthermore, due to the inherent interactions between the newly introduced Dirichlet variable and the conventional multivariate Gaussian variable, the model is less prone to KL divergence vanishing. We derive the variational lower bound for the new model and conduct experiments on four different data sets. The results show that the proposed model is superior at text reconstruction across the latent space and classifications on learned representations have higher test accuracies. |
| Tasks | |
| Published | 2018-10-31 |
| URL | http://arxiv.org/abs/1811.00135v1 |
| http://arxiv.org/pdf/1811.00135v1.pdf | |
| PWC | https://paperswithcode.com/paper/dirichlet-variational-autoencoder-for-text |
| Repo | |
| Framework | |
Optimize transfer learning for lung diseases in bronchoscopy using a new concept: sequential fine-tuning
| Title | Optimize transfer learning for lung diseases in bronchoscopy using a new concept: sequential fine-tuning |
| Authors | Tao Tan, Zhang Li, Haixia Liu, Ping Liu, Wenfang Tang, Hui Li, Yue Sun, Yusheng Yan, Keyu Li, Tao Xu, Shanshan Wan, Ke Lou, Jun Xu, Huiming Ying, Quchang Ouyang, Yuling Tang, Zheyu Hu, Qiang Li |
| Abstract | Bronchoscopy inspection as a follow-up procedure from the radiological imaging plays a key role in lung disease diagnosis and determining treatment plans for the patients. Doctors needs to make a decision whether to biopsy the patients timely when performing bronchoscopy. However, the doctors also needs to be very selective with biopsies as biopsies may cause uncontrollable bleeding of the lung tissue which is life-threaten. To help doctors to be more selective on biopsies and provide a second opinion on diagnosis, in this work, we propose a computer-aided diagnosis (CAD) system for lung diseases including cancers and tuberculosis (TB). The system is developed based on transfer learning. We propose a novel transfer learning method: sentential fine-tuning . Compared to traditional fine-tuning methods, our methods achieves the best performance. We obtained a overall accuracy of 77.0% a dataset of 81 normal cases, 76 tuberculosis cases and 277 lung cancer cases while the other traditional transfer learning methods achieve an accuracy of 73% and 68%. . The detection accuracy of our method for cancers, TB and normal cases are 87%, 54% and 91% respectively. This indicates that the CAD system has potential to improve lung disease diagnosis accuracy in bronchoscopy and it also might be used to be more selective with biopsies. |
| Tasks | Transfer Learning |
| Published | 2018-02-10 |
| URL | http://arxiv.org/abs/1802.03617v1 |
| http://arxiv.org/pdf/1802.03617v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimize-transfer-learning-for-lung-diseases |
| Repo | |
| Framework | |
Notes on stable learning with piecewise-linear basis functions
| Title | Notes on stable learning with piecewise-linear basis functions |
| Authors | Winfried Lohmiller, Philipp Gassert, Jean-Jacques Slotine |
| Abstract | We discuss technical results on learning function approximations using piecewise-linear basis functions, and analyze their stability and convergence using nonlinear contraction theory. |
| Tasks | |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.10085v1 |
| http://arxiv.org/pdf/1804.10085v1.pdf | |
| PWC | https://paperswithcode.com/paper/notes-on-stable-learning-with-piecewise |
| Repo | |
| Framework | |
Investigating Backtranslation in Neural Machine Translation
| Title | Investigating Backtranslation in Neural Machine Translation |
| Authors | Alberto Poncelas, Dimitar Shterionov, Andy Way, Gideon Maillette de Buy Wenniger, Peyman Passban |
| Abstract | A prerequisite for training corpus-based machine translation (MT) systems – either Statistical MT (SMT) or Neural MT (NMT) – is the availability of high-quality parallel data. This is arguably more important today than ever before, as NMT has been shown in many studies to outperform SMT, but mostly when large parallel corpora are available; in cases where data is limited, SMT can still outperform NMT. Recently researchers have shown that back-translating monolingual data can be used to create synthetic parallel corpora, which in turn can be used in combination with authentic parallel data to train a high-quality NMT system. Given that large collections of new parallel text become available only quite rarely, backtranslation has become the norm when building state-of-the-art NMT systems, especially in resource-poor scenarios. However, we assert that there are many unknown factors regarding the actual effects of back-translated data on the translation capabilities of an NMT model. Accordingly, in this work we investigate how using back-translated data as a training corpus – both as a separate standalone dataset as well as combined with human-generated parallel data – affects the performance of an NMT model. We use incrementally larger amounts of back-translated data to train a range of NMT systems for German-to-English, and analyse the resulting translation performance. |
| Tasks | Machine Translation |
| Published | 2018-04-17 |
| URL | http://arxiv.org/abs/1804.06189v1 |
| http://arxiv.org/pdf/1804.06189v1.pdf | |
| PWC | https://paperswithcode.com/paper/investigating-backtranslation-in-neural |
| Repo | |
| Framework | |
Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations
| Title | Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations |
| Authors | Ashwin Kalyan, Stefan Lee, Anitha Kannan, Dhruv Batra |
| Abstract | Many structured prediction problems (particularly in vision and language domains) are ambiguous, with multiple outputs being correct for an input - e.g. there are many ways of describing an image, multiple ways of translating a sentence; however, exhaustively annotating the applicability of all possible outputs is intractable due to exponentially large output spaces (e.g. all English sentences). In practice, these problems are cast as multi-class prediction, with the likelihood of only a sparse set of annotations being maximized - unfortunately penalizing for placing beliefs on plausible but unannotated outputs. We make and test the following hypothesis - for a given input, the annotations of its neighbors may serve as an additional supervisory signal. Specifically, we propose an objective that transfers supervision from neighboring examples. We first study the properties of our developed method in a controlled toy setup before reporting results on multi-label classification and two image-grounded sequence modeling tasks - captioning and question generation. We evaluate using standard task-specific metrics and measures of output diversity, finding consistent improvements over standard maximum likelihood training and other baselines. |
| Tasks | Multi-Label Classification, Question Generation, Structured Prediction |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.02934v1 |
| http://arxiv.org/pdf/1806.02934v1.pdf | |
| PWC | https://paperswithcode.com/paper/learn-from-your-neighbor-learning-multi-modal |
| Repo | |
| Framework | |
Modeling Human Inference of Others’ Intentions in Complex Situations with Plan Predictability Bias
| Title | Modeling Human Inference of Others’ Intentions in Complex Situations with Plan Predictability Bias |
| Authors | Ryo Nakahashi, Seiji Yamada |
| Abstract | A recent approach based on Bayesian inverse planning for the “theory of mind” has shown good performance in modeling human cognition. However, perfect inverse planning differs from human cognition during one kind of complex tasks due to human bounded rationality. One example is an environment in which there are many available plans for achieving a specific goal. We propose a “plan predictability oriented model” as a model of inferring other peoples’ goals in complex environments. This model adds the bias that people prefer predictable plans. This bias is calculated with simple plan prediction. We tested this model with a behavioral experiment in which humans observed the partial path of goal-directed actions. Our model had a higher correlation with human inference. We also confirmed the robustness of our model with complex tasks and determined that it can be improved by taking account of individual differences in “bounded rationality”. |
| Tasks | |
| Published | 2018-05-16 |
| URL | https://arxiv.org/abs/1805.06248v3 |
| https://arxiv.org/pdf/1805.06248v3.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-human-inference-of-others-intentions |
| Repo | |
| Framework | |
Markov Chain Block Coordinate Descent
| Title | Markov Chain Block Coordinate Descent |
| Authors | Tao Sun, Yuejiao Sun, Yangyang Xu, Wotao Yin |
| Abstract | The method of block coordinate gradient descent (BCD) has been a powerful method for large-scale optimization. This paper considers the BCD method that successively updates a series of blocks selected according to a Markov chain. This kind of block selection is neither i.i.d. random nor cyclic. On the other hand, it is a natural choice for some applications in distributed optimization and Markov decision process, where i.i.d. random and cyclic selections are either infeasible or very expensive. By applying mixing-time properties of a Markov chain, we prove convergence of Markov chain BCD for minimizing Lipschitz differentiable functions, which can be nonconvex. When the functions are convex and strongly convex, we establish both sublinear and linear convergence rates, respectively. We also present a method of Markov chain inertial BCD. Finally, we discuss potential applications. |
| Tasks | Distributed Optimization |
| Published | 2018-11-22 |
| URL | http://arxiv.org/abs/1811.08990v1 |
| http://arxiv.org/pdf/1811.08990v1.pdf | |
| PWC | https://paperswithcode.com/paper/markov-chain-block-coordinate-descent |
| Repo | |
| Framework | |
Care2Vec: A Deep learning approach for the classification of self-care problems in physically disabled children
| Title | Care2Vec: A Deep learning approach for the classification of self-care problems in physically disabled children |
| Authors | Sayan Putatunda |
| Abstract | Accurate classification of self-care problems in children who suffer from physical and motor affliction is an important problem in the healthcare industry. This is a difficult and a time consumming process and it needs the expertise of occupational therapists. In recent years, healthcare professionals have opened up to the idea of using expert systems and artificial intelligence in the diagnosis and classification of self care problems. In this study, we propose a new deep learning based approach named Care2Vec for solving these kind of problems and use a real world self care activities dataset that is based on a conceptual framework designed by the World Health Organization (WHO). Care2Vec is a mix of unsupervised and supervised learning where we use Autoencoders and Deep neural networks as a two step modeling process. We found that Care2Vec has a better prediction accuracy than some of the traditional methods reported in the literature for solving the self care classification problem viz. Decision trees and Artificial neural networks. |
| Tasks | |
| Published | 2018-12-03 |
| URL | https://arxiv.org/abs/1812.00715v2 |
| https://arxiv.org/pdf/1812.00715v2.pdf | |
| PWC | https://paperswithcode.com/paper/care2vec-a-deep-learning-approach-for-the |
| Repo | |
| Framework | |
Representing smooth functions as compositions of near-identity functions with implications for deep network optimization
| Title | Representing smooth functions as compositions of near-identity functions with implications for deep network optimization |
| Authors | Peter L. Bartlett, Steven N. Evans, Philip M. Long |
| Abstract | We show that any smooth bi-Lipschitz $h$ can be represented exactly as a composition $h_m \circ … \circ h_1$ of functions $h_1,…,h_m$ that are close to the identity in the sense that each $\left(h_i-\mathrm{Id}\right)$ is Lipschitz, and the Lipschitz constant decreases inversely with the number $m$ of functions composed. This implies that $h$ can be represented to any accuracy by a deep residual network whose nonlinear layers compute functions with a small Lipschitz constant. Next, we consider nonlinear regression with a composition of near-identity nonlinear maps. We show that, regarding Fr'echet derivatives with respect to the $h_1,…,h_m$, any critical point of a quadratic criterion in this near-identity region must be a global minimizer. In contrast, if we consider derivatives with respect to parameters of a fixed-size residual network with sigmoid activation functions, we show that there are near-identity critical points that are suboptimal, even in the realizable case. Informally, this means that functional gradient methods for residual networks cannot get stuck at suboptimal critical points corresponding to near-identity layers, whereas parametric gradient methods for sigmoidal residual networks suffer from suboptimal critical points in the near-identity region. |
| Tasks | |
| Published | 2018-04-13 |
| URL | http://arxiv.org/abs/1804.05012v2 |
| http://arxiv.org/pdf/1804.05012v2.pdf | |
| PWC | https://paperswithcode.com/paper/representing-smooth-functions-as-compositions |
| Repo | |
| Framework | |
Situation Calculus for Synthesis of Manufacturing Controllers
| Title | Situation Calculus for Synthesis of Manufacturing Controllers |
| Authors | Giuseppe De Giacomo, Brian Logan, Paolo Felli, Fabio Patrizi, Sebastian Sardina |
| Abstract | Manufacturing is transitioning from a mass production model to a manufacturing as a service model in which manufacturing facilities ‘bid’ to produce products. To decide whether to bid for a complex, previously unseen product, a manufacturing facility must be able to synthesize, ‘on the fly’, a process plan controller that delegates abstract manufacturing tasks in the supplied process recipe to the appropriate manufacturing resources, e.g., CNC machines, robots etc. Previous work in applying AI behaviour composition to synthesize process plan controllers has considered only finite state ad-hoc representations. Here, we study the problem in the relational setting of the Situation Calculus. By taking advantage of recent work on abstraction in the Situation Calculus, process recipes and available resources are represented by ConGolog programs over, respectively, an abstract and a concrete action theory. This allows us to capture the problem in a formal, general framework, and show decidability for the case of bounded action theories. We also provide techniques for actually synthesizing the controller. |
| Tasks | |
| Published | 2018-07-12 |
| URL | http://arxiv.org/abs/1807.04561v1 |
| http://arxiv.org/pdf/1807.04561v1.pdf | |
| PWC | https://paperswithcode.com/paper/situation-calculus-for-synthesis-of |
| Repo | |
| Framework | |
Feed-forward Uncertainty Propagation in Belief and Neural Networks
| Title | Feed-forward Uncertainty Propagation in Belief and Neural Networks |
| Authors | Alexander Shekhovtsov, Boris Flach, Michal Busta |
| Abstract | We propose a feed-forward inference method applicable to belief and neural networks. In a belief network, the method estimates an approximate factorized posterior of all hidden units given the input. In neural networks the method propagates uncertainty of the input through all the layers. In neural networks with injected noise, the method analytically takes into account uncertainties resulting from this noise. Such feed-forward analytic propagation is differentiable in parameters and can be trained end-to-end. Compared to standard NN, which can be viewed as propagating only the means, we propagate the mean and variance. The method can be useful in all scenarios that require knowledge of the neuron statistics, e.g. when dealing with uncertain inputs, considering sigmoid activations as probabilities of Bernoulli units, training the models regularized by injected noise (dropout) or estimating activation statistics over the dataset (as needed for normalization methods). In the experiments we show the possible utility of the method in all these tasks as well as its current limitations. |
| Tasks | |
| Published | 2018-03-28 |
| URL | http://arxiv.org/abs/1803.10590v2 |
| http://arxiv.org/pdf/1803.10590v2.pdf | |
| PWC | https://paperswithcode.com/paper/feed-forward-uncertainty-propagation-in |
| Repo | |
| Framework | |
Translating Natural Language to SQL using Pointer-Generator Networks and How Decoding Order Matters
| Title | Translating Natural Language to SQL using Pointer-Generator Networks and How Decoding Order Matters |
| Authors | Denis Lukovnikov, Nilesh Chakraborty, Jens Lehmann, Asja Fischer |
| Abstract | Translating natural language to SQL queries for table-based question answering is a challenging problem and has received significant attention from the research community. In this work, we extend a pointer-generator and investigate the order-matters problem in semantic parsing for SQL. Even though our model is a straightforward extension of a general-purpose pointer-generator, it outperforms early works for WikiSQL and remains competitive to concurrently introduced, more complex models. Moreover, we provide a deeper investigation of the potential order-matters problem that could arise due to having multiple correct decoding paths, and investigate the use of REINFORCE as well as a dynamic oracle in this context. |
| Tasks | Question Answering, Semantic Parsing |
| Published | 2018-11-13 |
| URL | http://arxiv.org/abs/1811.05303v1 |
| http://arxiv.org/pdf/1811.05303v1.pdf | |
| PWC | https://paperswithcode.com/paper/translating-natural-language-to-sql-using |
| Repo | |
| Framework | |
