Paper Group ANR 1016
A New Approach for Explainable Multiple Organ Annotation with Few Data. Stochastic Inverse Reinforcement Learning. Parareal with a Learned Coarse Model for Robotic Manipulation. Generalized Linear Rule Models. Generative Imaging and Image Processing via Generative Encoder. A Hierarchical Bayesian Model for Size Recommendation in Fashion. A Deep Lea …
A New Approach for Explainable Multiple Organ Annotation with Few Data
| Title | A New Approach for Explainable Multiple Organ Annotation with Few Data |
| Authors | Régis Pierrard, Jean-Philippe Poli, Céline Hudelot |
| Abstract | Despite the recent successes of deep learning, such models are still far from some human abilities like learning from few examples, reasoning and explaining decisions. In this paper, we focus on organ annotation in medical images and we introduce a reasoning framework that is based on learning fuzzy relations on a small dataset for generating explanations. Given a catalogue of relations, it efficiently induces the most relevant relations and combines them for building constraints in order to both solve the organ annotation task and generate explanations. We test our approach on a publicly available dataset of medical images where several organs are already segmented. A demonstration of our model is proposed with an example of explained annotations. It was trained on a small training set containing as few as a couple of examples. |
| Tasks | |
| Published | 2019-12-30 |
| URL | https://arxiv.org/abs/1912.12932v1 |
| https://arxiv.org/pdf/1912.12932v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-approach-for-explainable-multiple-organ |
| Repo | |
| Framework | |
Stochastic Inverse Reinforcement Learning
| Title | Stochastic Inverse Reinforcement Learning |
| Authors | Ce Ju, Dong Eui Chang |
| Abstract | Inverse reinforcement learning (IRL) is an ill-posed inverse problem since expert demonstrations may infer many solutions of reward functions which is hard to recover by local search methods such as a gradient method. In this paper, we generalize the original IRL problem to recover a probability distribution for reward functions. We call such a generalized problem stochastic inverse reinforcement learning (SIRL) which is first formulated as an expectation optimization problem. We adopt the Monte Carlo expectation-maximization (MCEM) method, a global search method, to estimate the parameter of the probability distribution as the first solution to SIRL. With our approach, it is possible to observe the deep intrinsic property in IRL from a global viewpoint, and the technique achieves a considerable robust recovery performance on the classic learning environment, objectworld. |
| Tasks | |
| Published | 2019-05-21 |
| URL | https://arxiv.org/abs/1905.08513v2 |
| https://arxiv.org/pdf/1905.08513v2.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-inverse-reinforcement-learning |
| Repo | |
| Framework | |
Parareal with a Learned Coarse Model for Robotic Manipulation
| Title | Parareal with a Learned Coarse Model for Robotic Manipulation |
| Authors | Wisdom Agboh, Oliver Grainger, Daniel Ruprecht, Mehmet Dogar |
| Abstract | A key component of many robotics model-based planning and control algorithms is physics predictions, that is, forecasting a sequence of states given an initial state and a sequence of controls. This process is slow and a major computational bottleneck for robotics planning algorithms. Parallel-in-time integration methods can help to leverage parallel computing to accelerate physics predictions and thus planning. The Parareal algorithm iterates between a coarse serial integrator and a fine parallel integrator. A key challenge is to devise a coarse level model that is computationally cheap but accurate enough for Parareal to converge quickly. Here, we investigate the use of a deep neural network physics model as a coarse model for Parareal in the context of robotic manipulation. In simulated experiments using the physics engine Mujoco as fine propagator we show that the learned coarse model leads to faster Parareal convergence than a coarse physics-based model. We further show that the learned coarse model allows to apply Parareal to scenarios with multiple objects, where the physics-based coarse model is not applicable. Finally, We conduct experiments on a real robot and show that Parareal predictions are close to real-world physics predictions for robotic pushing of multiple objects. Some real robot manipulation plans using Parareal can be found at https://www.youtube.com/watch?v=wCh2o1rf-gA . |
| Tasks | |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.05958v1 |
| https://arxiv.org/pdf/1912.05958v1.pdf | |
| PWC | https://paperswithcode.com/paper/parareal-with-a-learned-coarse-model-for |
| Repo | |
| Framework | |
Generalized Linear Rule Models
| Title | Generalized Linear Rule Models |
| Authors | Dennis Wei, Sanjeeb Dash, Tian Gao, Oktay Günlük |
| Abstract | This paper considers generalized linear models using rule-based features, also referred to as rule ensembles, for regression and probabilistic classification. Rules facilitate model interpretation while also capturing nonlinear dependences and interactions. Our problem formulation accordingly trades off rule set complexity and prediction accuracy. Column generation is used to optimize over an exponentially large space of rules without pre-generating a large subset of candidates or greedily boosting rules one by one. The column generation subproblem is solved using either integer programming or a heuristic optimizing the same objective. In experiments involving logistic and linear regression, the proposed methods obtain better accuracy-complexity trade-offs than existing rule ensemble algorithms. At one end of the trade-off, the methods are competitive with less interpretable benchmark models. |
| Tasks | |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.01761v1 |
| https://arxiv.org/pdf/1906.01761v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-linear-rule-models |
| Repo | |
| Framework | |
Generative Imaging and Image Processing via Generative Encoder
| Title | Generative Imaging and Image Processing via Generative Encoder |
| Authors | Lin Chen, Haizhao Yang |
| Abstract | This paper introduces a novel generative encoder (GE) model for generative imaging and image processing with applications in compressed sensing and imaging, image compression, denoising, inpainting, deblurring, and super-resolution. The GE model consists of a pre-training phase and a solving phase. In the pre-training phase, we separately train two deep neural networks: a generative adversarial network (GAN) with a generator $\G$ that captures the data distribution of a given image set, and an auto-encoder (AE) network with an encoder $\EN$ that compresses images following the estimated distribution by GAN. In the solving phase, given a noisy image $x=\mathcal{P}(x^*)$, where $x^*$ is the target unknown image, $\mathcal{P}$ is an operator adding an addictive, or multiplicative, or convolutional noise, or equivalently given such an image $x$ in the compressed domain, i.e., given $m=\EN(x)$, we solve the optimization problem [ z^*=\underset{z}{\mathrm{argmin}} \EN(\G(z))-m_2^2+\lambda\z_2^2 ] to recover the image $x^*$ in a generative way via $\hat{x}:=\G(z^*)\approx x^*$, where $\lambda>0$ is a hyperparameter. The GE model unifies the generative capacity of GANs and the stability of AEs in an optimization framework above instead of stacking GANs and AEs into a single network or combining their loss functions into one as in existing literature. Numerical experiments show that the proposed model outperforms several state-of-the-art algorithms. |
| Tasks | Deblurring, Denoising, Image Compression, Super-Resolution |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.13300v1 |
| https://arxiv.org/pdf/1905.13300v1.pdf | |
| PWC | https://paperswithcode.com/paper/190513300 |
| Repo | |
| Framework | |
A Hierarchical Bayesian Model for Size Recommendation in Fashion
| Title | A Hierarchical Bayesian Model for Size Recommendation in Fashion |
| Authors | Romain Guigourès, Yuen King Ho, Evgenii Koriagin, Abdul-Saboor Sheikh, Urs Bergmann, Reza Shirvany |
| Abstract | We introduce a hierarchical Bayesian approach to tackle the challenging problem of size recommendation in e-commerce fashion. Our approach jointly models a size purchased by a customer, and its possible return event: 1. no return, 2. returned too small 3. returned too big. Those events are drawn following a multinomial distribution parameterized on the joint probability of each event, built following a hierarchy combining priors. Such a model allows us to incorporate extended domain expertise and article characteristics as prior knowledge, which in turn makes it possible for the underlying parameters to emerge thanks to sufficient data. Experiments are presented on real (anonymized) data from millions of customers along with a detailed discussion on the efficiency of such an approach within a large scale production system. |
| Tasks | |
| Published | 2019-08-02 |
| URL | https://arxiv.org/abs/1908.00825v1 |
| https://arxiv.org/pdf/1908.00825v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-hierarchical-bayesian-model-for-size |
| Repo | |
| Framework | |
A Deep Learning Approach to Universal Binary Visible Light Communication Transceiver
| Title | A Deep Learning Approach to Universal Binary Visible Light Communication Transceiver |
| Authors | Hoon Lee, Tony Q. S. Quek, Sang Hyun Lee |
| Abstract | This paper studies a deep learning (DL) framework for the design of binary modulated visible light communication (VLC) transceiver with universal dimming support. The dimming control for the optical binary signal boils down to a combinatorial codebook design so that the average Hamming weight of binary codewords matches with arbitrary dimming target. An unsupervised DL technique is employed for obtaining a neural network to replace the encoder-decoder pair that recovers the message from the optically transmitted signal. In such a task, a novel stochastic binarization method is developed to generate the set of binary codewords from continuous-valued neural network outputs. For universal support of arbitrary dimming target, the DL-based VLC transceiver is trained with multiple dimming constraints, which turns out to be a constrained training optimization that is very challenging to handle with existing DL methods. We develop a new training algorithm that addresses the dimming constraints through a dual formulation of the optimization. Based on the developed algorithm, the resulting VLC transceiver can be optimized via the end-to-end training procedure. Numerical results verify that the proposed codebook outperforms theoretically best constant weight codebooks under various VLC setups. |
| Tasks | |
| Published | 2019-10-26 |
| URL | https://arxiv.org/abs/1910.12048v1 |
| https://arxiv.org/pdf/1910.12048v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-approach-to-universal-binary |
| Repo | |
| Framework | |
Stratospheric Aerosol Injection as a Deep Reinforcement Learning Problem
| Title | Stratospheric Aerosol Injection as a Deep Reinforcement Learning Problem |
| Authors | Christian Schroeder de Witt, Thomas Hornigold |
| Abstract | As global greenhouse gas emissions continue to rise, the use of stratospheric aerosol injection (SAI), a form of solar geoengineering, is increasingly considered in order to artificially mitigate climate change effects. However, initial research in simulation suggests that naive SAI can have catastrophic regional consequences, which may induce serious geostrategic conflicts. Current geo-engineering research treats SAI control in low-dimensional approximation only. We suggest treating SAI as a high-dimensional control problem, with policies trained according to a context-sensitive reward function within the Deep Reinforcement Learning (DRL) paradigm. In order to facilitate training in simulation, we suggest to emulate HadCM3, a widely used General Circulation Model, using deep learning techniques. We believe this is the first application of DRL to the climate sciences. |
| Tasks | |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.07366v1 |
| https://arxiv.org/pdf/1905.07366v1.pdf | |
| PWC | https://paperswithcode.com/paper/stratospheric-aerosol-injection-as-a-deep |
| Repo | |
| Framework | |
Neural Inverse Knitting: From Images to Manufacturing Instructions
| Title | Neural Inverse Knitting: From Images to Manufacturing Instructions |
| Authors | Alexandre Kaspar, Tae-Hyun Oh, Liane Makatura, Petr Kellnhofer, Jacqueline Aslarus, Wojciech Matusik |
| Abstract | Motivated by the recent potential of mass customization brought by whole-garment knitting machines, we introduce the new problem of automatic machine instruction generation using a single image of the desired physical product, which we apply to machine knitting. We propose to tackle this problem by directly learning to synthesize regular machine instructions from real images. We create a cured dataset of real samples with their instruction counterpart and propose to use synthetic images to augment it in a novel way. We theoretically motivate our data mixing framework and show empirical results suggesting that making real images look more synthetic is beneficial in our problem setup. |
| Tasks | |
| Published | 2019-02-07 |
| URL | https://arxiv.org/abs/1902.02752v2 |
| https://arxiv.org/pdf/1902.02752v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-inverse-knitting-from-images-to |
| Repo | |
| Framework | |
Iterative Hard Thresholding for Low CP-rank Tensor Models
| Title | Iterative Hard Thresholding for Low CP-rank Tensor Models |
| Authors | Rachel Grotheer, Shuang Li, Anna Ma, Deanna Needell, Jing Qin |
| Abstract | Recovery of low-rank matrices from a small number of linear measurements is now well-known to be possible under various model assumptions on the measurements. Such results demonstrate robustness and are backed with provable theoretical guarantees. However, extensions to tensor recovery have only recently began to be studied and developed, despite an abundance of practical tensor applications. Recently, a tensor variant of the Iterative Hard Thresholding method was proposed and theoretical results were obtained that guarantee exact recovery of tensors with low Tucker rank. In this paper, we utilize the same tensor version of the Restricted Isometry Property (RIP) to extend these results for tensors with low CANDECOMP/PARAFAC (CP) rank. In doing so, we leverage recent results on efficient approximations of CP decompositions that remove the need for challenging assumptions in prior works. We complement our theoretical findings with empirical results that showcase the potential of the approach. |
| Tasks | |
| Published | 2019-08-22 |
| URL | https://arxiv.org/abs/1908.08479v1 |
| https://arxiv.org/pdf/1908.08479v1.pdf | |
| PWC | https://paperswithcode.com/paper/iterative-hard-thresholding-for-low-cp-rank |
| Repo | |
| Framework | |
Q-Learning Inspired Self-Tuning for Energy Efficiency in HPC
| Title | Q-Learning Inspired Self-Tuning for Energy Efficiency in HPC |
| Authors | Andreas Gocht, Robert Schöne, Mario Bielert |
| Abstract | System self-tuning is a crucial task to lower the energy consumption of computers. Traditional approaches decrease the processor frequency in idle or synchronisation periods. However, in High-Performance Computing (HPC) this is not sufficient: if the executed code is load balanced, there are neither idle nor synchronisation phases that can be exploited. Therefore, alternative self-tuning approaches are needed, which allow exploiting different compute characteristics of HPC programs. The novel notion of application regions based on function call stacks, introduced in the Horizon 2020 Project READEX, allows us to define such a self-tuning approach. In this paper, we combine these regions with the Q-Learning typical state-action maps, which save information about available states, possible actions to take, and the expected rewards. By exploiting the existing processor power interface, we are able to provide direct feedback to the learning process. This approach allows us to save up to 15% energy, while only adding a minor runtime overhead. |
| Tasks | Q-Learning |
| Published | 2019-06-26 |
| URL | https://arxiv.org/abs/1906.10970v1 |
| https://arxiv.org/pdf/1906.10970v1.pdf | |
| PWC | https://paperswithcode.com/paper/q-learning-inspired-self-tuning-for-energy |
| Repo | |
| Framework | |
Sequential vs. Integrated Algorithm Selection and Configuration: A Case Study for the Modular CMA-ES
| Title | Sequential vs. Integrated Algorithm Selection and Configuration: A Case Study for the Modular CMA-ES |
| Authors | Diederick Vermetten, Hao Wang, Carola Doerr, Thomas Bäck |
| Abstract | When faced with a specific optimization problem, choosing which algorithm to use is always a tough task. Not only is there a vast variety of algorithms to select from, but these algorithms often are controlled by many hyperparameters, which need to be tuned in order to achieve the best performance possible. Usually, this problem is separated into two parts: algorithm selection and algorithm configuration. With the significant advances made in Machine Learning, however, these problems can be integrated into a combined algorithm selection and hyperparameter optimization task, commonly known as the CASH problem. In this work we compare sequential and integrated algorithm selection and configuration approaches for the case of selecting and tuning the best out of 4608 variants of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) tested on the Black Box Optimization Benchmark (BBOB) suite. We first show that the ranking of the modular CMA-ES variants depends to a large extent on the quality of the hyperparameters. This implies that even a sequential approach based on complete enumeration of the algorithm space will likely result in sub-optimal solutions. In fact, we show that the integrated approach manages to provide competitive results at a much smaller computational cost. We also compare two different mixed-integer algorithm configuration techniques, called irace and Mixed-Integer Parallel Efficient Global Optimization (MIP-EGO). While we show that the two methods differ significantly in their treatment of the exploration-exploitation balance, their overall performances are very similar. |
| Tasks | Hyperparameter Optimization |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.05899v2 |
| https://arxiv.org/pdf/1912.05899v2.pdf | |
| PWC | https://paperswithcode.com/paper/sequential-vs-integrated-algorithm-selection |
| Repo | |
| Framework | |
A deep learning framework for quality assessment and restoration in video endoscopy
| Title | A deep learning framework for quality assessment and restoration in video endoscopy |
| Authors | Sharib Ali, Felix Zhou, Adam Bailey, Barbara Braden, James East, Xin Lu, Jens Rittscher |
| Abstract | Endoscopy is a routine imaging technique used for both diagnosis and minimally invasive surgical treatment. Artifacts such as motion blur, bubbles, specular reflections, floating objects and pixel saturation impede the visual interpretation and the automated analysis of endoscopy videos. Given the widespread use of endoscopy in different clinical applications, we contend that the robust and reliable identification of such artifacts and the automated restoration of corrupted video frames is a fundamental medical imaging problem. Existing state-of-the-art methods only deal with the detection and restoration of selected artifacts. However, typically endoscopy videos contain numerous artifacts which motivates to establish a comprehensive solution. We propose a fully automatic framework that can: 1) detect and classify six different primary artifacts, 2) provide a quality score for each frame and 3) restore mildly corrupted frames. To detect different artifacts our framework exploits fast multi-scale, single stage convolutional neural network detector. We introduce a quality metric to assess frame quality and predict image restoration success. Generative adversarial networks with carefully chosen regularization are finally used to restore corrupted frames. Our detector yields the highest mean average precision (mAP at 5% threshold) of 49.0 and the lowest computational time of 88 ms allowing for accurate real-time processing. Our restoration models for blind deblurring, saturation correction and inpainting demonstrate significant improvements over previous methods. On a set of 10 test videos we show that our approach preserves an average of 68.7% which is 25% more frames than that retained from the raw videos. |
| Tasks | Deblurring, Image Restoration |
| Published | 2019-04-15 |
| URL | http://arxiv.org/abs/1904.07073v1 |
| http://arxiv.org/pdf/1904.07073v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-framework-for-quality |
| Repo | |
| Framework | |
Planar Geometry and Latest Scene Recovery from a Single Motion Blurred Image
| Title | Planar Geometry and Latest Scene Recovery from a Single Motion Blurred Image |
| Authors | Kuldeep Purohit, Subeesh Vasu, M. Purnachandra Rao, A. N. Rajagopalan |
| Abstract | Existing works on motion deblurring either ignore the effects of depth-dependent blur or work with the assumption of a multi-layered scene wherein each layer is modeled in the form of fronto-parallel plane. In this work, we consider the case of 3D scenes with piecewise planar structure i.e., a scene that can be modeled as a combination of multiple planes with arbitrary orientations. We first propose an approach for estimation of normal of a planar scene from a single motion blurred observation. We then develop an algorithm for automatic recovery of a number of planes, the parameters corresponding to each plane, and camera motion from a single motion blurred image of a multiplanar 3D scene. Finally, we propose a first-of-its-kind approach to recover the planar geometry and latent image of the scene by adopting an alternating minimization framework built on our findings. Experiments on synthetic and real data reveal that our proposed method achieves state-of-the-art results. |
| Tasks | Deblurring |
| Published | 2019-04-07 |
| URL | http://arxiv.org/abs/1904.03710v2 |
| http://arxiv.org/pdf/1904.03710v2.pdf | |
| PWC | https://paperswithcode.com/paper/planar-geometry-and-latest-scene-recovery |
| Repo | |
| Framework | |
Deep Stacked Hierarchical Multi-patch Network for Image Deblurring
| Title | Deep Stacked Hierarchical Multi-patch Network for Image Deblurring |
| Authors | Hongguang Zhang, Yuchao Dai, Hongdong Li, Piotr Koniusz |
| Abstract | Despite deep end-to-end learning methods have shown their superiority in removing non-uniform motion blur, there still exist major challenges with the current multi-scale and scale-recurrent models: 1) Deconvolution/upsampling operations in the coarse-to-fine scheme result in expensive runtime; 2) Simply increasing the model depth with finer-scale levels cannot improve the quality of deblurring. To tackle the above problems, we present a deep hierarchical multi-patch network inspired by Spatial Pyramid Matching to deal with blurry images via a fine-to-coarse hierarchical representation. To deal with the performance saturation w.r.t. depth, we propose a stacked version of our multi-patch model. Our proposed basic multi-patch model achieves the state-of-the-art performance on the GoPro dataset while enjoying a 40x faster runtime compared to current multi-scale methods. With 30ms to process an image at 1280x720 resolution, it is the first real-time deep motion deblurring model for 720p images at 30fps. For stacked networks, significant improvements (over 1.2dB) are achieved on the GoPro dataset by increasing the network depth. Moreover, by varying the depth of the stacked model, one can adapt the performance and runtime of the same network for different application scenarios. |
| Tasks | Deblurring |
| Published | 2019-04-06 |
| URL | http://arxiv.org/abs/1904.03468v1 |
| http://arxiv.org/pdf/1904.03468v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-stacked-hierarchical-multi-patch-network |
| Repo | |
| Framework | |
