3298 results (BibTeX)

2017


Automatic detection of motion artifacts in MR images using CNNS

Meding, K., Loktyushin, A., Hirsch, M.

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017), pages: 811-815, 2017 (conference)

ei

DOI [BibTex]

2017


DOI [BibTex]


Thumb md teaser iccv2017
Bounding Boxes, Segmentations and Object Coordinates: How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?

Behl, A., Hosseini Jafari, O., Karthik Mustikovela, S., Abu Alhaija, H., Rother, C., Geiger, A.

In IEEE International Conference on Computer Vision (ICCV), 2017, 2017 (inproceedings)

Abstract
Existing methods for 3D scene flow estimation often fail in the presence of large displacement or local ambiguities, e.g., at texture-less or reflective surfaces. However, these challenges are omnipresent in dynamic road scenes, which is the focus of this work. Our main contribution is to overcome these 3D motion estimation problems by exploiting recognition. In particular, we investigate the importance of recognition granularity, from coarse 2D bounding box estimates over 2D instance segmentations to fine-grained 3D object part predictions. We compute these cues using CNNs trained on a newly annotated dataset of stereo images and integrate them into a CRF-based model for robust 3D scene flow estimation - an approach we term Instance Scene Flow. We analyze the importance of each recognition cue in an ablation study and observe that the instance segmentation cue is by far strongest, in our setting. We demonstrate the effectiveness of our method on the challenging KITTI 2015 scene flow benchmark where we achieve state-of-the-art performance at the time of submission.

avg

pdf suppmat [BibTex]

pdf suppmat [BibTex]


On the Design of LQR Kernels for Efficient Controller Learning

Marco, A., Hennig, P., Schaal, S., Trimpe, S.

Proceedings of the 56th IEEE Conference on Decision and Control, 2017 (conference) Accepted

am pn

[BibTex]

[BibTex]


Distributed Event-Based State Estimation for Networked Systems: An LMI Approach

Muehlebach, M., Trimpe, S.

IEEE Transactions on Automatic Control, 2017 (article) In press

am

arXiv (extended version) DOI [BibTex]

arXiv (extended version) DOI [BibTex]


Thumb md screen shot 2017 08 09 at 12.54.00
A simple yet effective baseline for 3d human pose estimation

Martinez, J., Hossain, R., Romero, J., J. Little, J.

In IEEE International Conference on Computer Vision (ICCV), 2017 (inproceedings)

Abstract
Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels. Despite their excellent performance, it is often not easy to understand whether their remaining error stems from a limited 2d pose (visual) understanding, or from a failure to map 2d poses into 3-dimensional positions. With the goal of understanding these sources of error, we set out to build a system that given 2d joint locations predicts 3d positions. Much to our surprise, we have found that, with current technology, "lifting" ground truth 2d joint locations to 3d space is a task that can be solved with a remarkably low error rate: a relatively simple deep feed-forward network outperforms the best reported result by about 30\% on Human3.6M, the largest publicly available 3d pose estimation benchmark. Furthermore, training our system on the output of an off-the-shelf state-of-the-art 2d detector (\ie, using images as input) yields state of the art results -- this includes an array of systems that have been trained end-to-end specifically for this task. Our results indicate that a large portion of the error of modern deep 3d pose estimation systems stems from their visual analysis, and suggests directions to further advance the state of the art in 3d human pose estimation.

ps

video code arxiv pdf preprint [BibTex]

video code arxiv pdf preprint [BibTex]


Thumb md screen shot 2017 08 01 at 15.41.10
On the relevance of grasp metrics for predicting grasp success

Rubert, C., Kappler, D., Morales, A., Schaal, S., Bohg, J.

In Proceedings of the IEEE/RSJ International Conference of Intelligent Robots and Systems, September 2017 (inproceedings) Accepted

Abstract
We aim to reliably predict whether a grasp on a known object is successful before it is executed in the real world. There is an entire suite of grasp metrics that has already been developed which rely on precisely known contact points between object and hand. However, it remains unclear whether and how they may be combined into a general purpose grasp stability predictor. In this paper, we analyze these questions by leveraging a large scale database of simulated grasps on a wide variety of objects. For each grasp, we compute the value of seven metrics. Each grasp is annotated by human subjects with ground truth stability labels. Given this data set, we train several classification methods to find out whether there is some underlying, non-trivial structure in the data that is difficult to model manually but can be learned. Quantitative and qualitative results show the complexity of the prediction problem. We found that a good prediction performance critically depends on using a combination of metrics as input features. Furthermore, non-parametric and non-linear classifiers best capture the structure in the data.

am

[BibTex]

[BibTex]


Ecological feedback in quorum-sensing microbial populations can induce heterogeneous production of autoinducers

Bauer*, M., Knebel*, J., Lechner, M., Pickl, P., Frey, E.

{eLife}, July 2017, *equal contribution (article)

ei

DOI [BibTex]

DOI [BibTex]


Minimax Estimation of Kernel Mean Embeddings

Tolstikhin, I., Sriperumbudur, B., Muandet, K.

Journal of Machine Learning Research, 18, pages: 1-47, 2017 (article) To be published

ei

[BibTex]

[BibTex]


Lost Relatives of the Gumbel Trick

Balog, M., Tripuraneni, N., Ghahramani, Z., Weller, A.

Proceedings of the 34th International Conference on Machine Learning (ICML 2017), 70, pages: 371-379, Proceedings of Machine Learning Research, (Editors: Doina Precup and Yee Whye Teh), PMLR, 2017 (conference)

ei

Code link (url) [BibTex]

Code link (url) [BibTex]


Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates

Gu*, S., Holly*, E., Lillicrap, T., Levine, S.

IEEE International Conference on Robotics and Automation (ICRA 2017), 2017, *equal contribution (conference)

ei

Arxiv [BibTex]

Arxiv [BibTex]


Categorical Reparametrization with Gumble-Softmax

Jang, E., Gu, S., Poole, B.

5th International Conference on Learning Representations (ICLR 2017), 2017 (conference)

ei

link (url) [BibTex]

link (url) [BibTex]


Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic

Gu, S., Lillicrap, T., Ghahramani, Z., Turner, R., Levine, S.

5th International Conference on Learning Representations (ICLR 2017), 2017 (conference)

ei

PDF [BibTex]

PDF [BibTex]


Sequence Tutor: Conservative fine-tuning of sequence generation models with KL-control

Jaques, N., Gu, S., Bahdanau, D., Hernández-Lobato, J., Turner, R., Eck, D.

Proceedings of the 34th International Conference on Machine Learning (ICML 2017), 70, pages: 1645-1654, Proceedings of Machine Learning Research, (Editors: Doina Precup and Yee Whye Te), PMLR, 2017 (conference)

ei

Arxiv link (url) [BibTex]

Arxiv link (url) [BibTex]


Behind Distribution Shift: Mining Driving Forces of Changes and Causal Arrows

Huang, B., Zhang, K., Zhang, J., Glymour, C., Schölkopf, B.

IEEE 17th International Conference on Data Mining (ICDM 2017), 2017 (conference) Accepted

ei

[BibTex]

[BibTex]


The effect of a wider initial separation on common envelope binary interaction simulations

Iaconi, R., Reichardt, T., Staff, J., De Marco, O., Passy, J., Price, D., Wurster, J., Herwig, F.

Monthly Notices of the Royal Astronomical Society, 464, pages: 4028-4044, 2017 (article)

DOI [BibTex]

DOI [BibTex]


Common Envelope Light Curves. I. Grid-code Module Calibration

Galaviz, P., De Marco, O., Passy, J., Staff, J., Iaconi, R.

Astrophysical Journal, Supplement, 229, pages: 36, 2017 (article)

DOI [BibTex]

DOI [BibTex]


Thumb md hassan paper teasere
Augmented Reality Meets Deep Learning for Car Instance Segmentation in Urban Scenes

Abu Alhaija, H., Karthik Mustikovela, S., Mescheder, L., Geiger, A., Rother, C.

In Proceedings of the British Machine Vision Conference 2017, Proceedings of the British Machine Vision Conference, September 2017 (inproceedings)

Abstract
The success of deep learning in computer vision is based on the availability of large annotated datasets. To lower the need for hand labeled images, virtually rendered 3D worlds have recently gained popularity. Unfortunately, creating realistic 3D content is challenging on its own and requires significant human effort. In this work, we propose an alternative paradigm which combines real and synthetic data for learning semantic instance segmentation models. Exploiting the fact that not all aspects of the scene are equally important for this task, we propose to augment real-world imagery with virtual objects of the target category. Capturing real-world images at large scale is easy and cheap, and directly provides real background appearances without the need for creating complex 3D models of the environment. We present an efficient procedure to augment these images with virtual objects. This allows us to create realistic composite images which exhibit both realistic background appearance as well as a large number of complex object arrangements. In contrast to modeling complete 3D environments, our data augmentation approach requires only a few user interactions in combination with 3D shapes of the target object category. We demonstrate the utility of the proposed approach for training a state-of-the-art high-capacity deep model for semantic instance segmentation. In particular, we consider the task of segmenting car instances on the KITTI dataset which we have annotated with pixel-accurate ground truth. Our experiments demonstrate that models trained on augmented imagery generalize better than those trained on synthetic data or models trained on limited amounts of annotated real data.

avg

pdf [BibTex]

pdf [BibTex]


Thumb md probls sketch n3 0 ei0
Probabilistic Line Searches for Stochastic Optimization

Mahsereci, M., Hennig, P.

arXiv preprint arXiv:1703.10034, 2017 (article)

pn

link (url) [BibTex]


Personalized Brain-Computer Interface Models for Motor Rehabilitation

Mastakouri, A., Weichwald, S., Ozdenizci, O., Meyer, T., Schölkopf, B., Grosse-Wentrup, M.

Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC 2017), 2017 (conference) Accepted

ei

[BibTex]

[BibTex]


Learning Blind Motion Deblurring

Wieschollek, P., Hirsch, M., Schölkopf, B., Lensch, H.

IEEE International Conference on Computer Vision (ICCV 2017), 2017 (conference) Accepted

ei

[BibTex]

[BibTex]


Online Video Deblurring via Dynamic Temporal Blending Network

Kim, T., Lee, K., Schölkopf, B., Hirsch, M.

IEEE International Conference on Computer Vision (ICCV 2017), 2017 (conference) Accepted

ei

[BibTex]

[BibTex]


Thumb md website teaser
Semantic Video CNNs through Representation Warping

Gadde, R., Jampani, V., Gehler, P.

In IEEE International Conference on Computer Vision (ICCV), 2017 (inproceedings) Accepted

Abstract
In this work, we propose a technique to convert CNN models for semantic segmentation of static images into CNNs for video data. We describe a warping method that can be used to augment existing architectures with very lit- tle extra computational cost. This module is called Net- Warp and we demonstrate its use for a range of network architectures. The main design principle is to use optical flow of adjacent frames for warping internal network repre- sentations across time. A key insight of this work is that fast optical flow methods can be combined with many different CNN architectures for improved performance and end-to- end training. Experiments validate that the proposed ap- proach incurs only little extra computational cost, while im- proving performance, when video streams are available. We achieve new state-of-the-art results on the standard CamVid and Cityscapes benchmark datasets and show reliable im- provements over different baseline networks. Our code and models are available at http://segmentation.is. tue.mpg.de

ps

pdf Supplementary [BibTex]

pdf Supplementary [BibTex]


Causal Consistency of Structural Equation Models

Rubenstein*, P., Weichwald*, S., Bongers, S., Mooij, J., Janzing, D., Grosse-Wentrup, M., Schölkopf, B.

Proceedings of the Thirty-Third Conference on Uncertainty in Artificial Intelligence (UAI 2017), 2017, *equal contribution (conference) Accepted

ei

Arxiv [BibTex]

Arxiv [BibTex]


Krylov Subspace Recycling for Fast Iterative Least-Squares in Machine Learning

de Roos, F., Hennig, P.

arXiv preprint arXiv:1706.00241, 2017 (article)

Abstract
Solving symmetric positive definite linear problems is a fundamental computational task in machine learning. The exact solution, famously, is cubicly expensive in the size of the matrix. To alleviate this problem, several linear-time approximations, such as spectral and inducing-point methods, have been suggested and are now in wide use. These are low-rank approximations that choose the low-rank space a priori and do not refine it over time. While this allows linear cost in the data-set size, it also causes a finite, uncorrected approximation error. Authors from numerical linear algebra have explored ways to iteratively refine such low-rank approximations, at a cost of a small number of matrix-vector multiplications. This idea is particularly interesting in the many situations in machine learning where one has to solve a sequence of related symmetric positive definite linear problems. From the machine learning perspective, such deflation methods can be interpreted as transfer learning of a low-rank approximation across a time-series of numerical tasks. We study the use of such methods for our field. Our empirical results show that, on regression and classification problems of intermediate size, this approach can interpolate between low computational cost and numerical precision.

pn

link (url) [BibTex]


Efficiency of analytical and sampling-based uncertainty propagation in intensity-modulated proton therapy

Wahl, N., Hennig, P., Wieser, H., Bangert, M.

Physics in Medicine & Biology, 62(14):5790-5807, 2017 (article)

Abstract
The sensitivity of intensity-modulated proton therapy (IMPT) treatment plans to uncertainties can be quantified and mitigated with robust/min-max and stochastic/probabilistic treatment analysis and optimization techniques. Those methods usually rely on sparse random, importance, or worst-case sampling. Inevitably, this imposes a trade-off between computational speed and accuracy of the uncertainty propagation. Here, we investigate analytical probabilistic modeling (APM) as an alternative for uncertainty propagation and minimization in IMPT that does not rely on scenario sampling. APM propagates probability distributions over range and setup uncertainties via a Gaussian pencil-beam approximation into moments of the probability distributions over the resulting dose in closed form. It supports arbitrary correlation models and allows for efficient incorporation of fractionation effects regarding random and systematic errors. We evaluate the trade-off between run-time and accuracy of APM uncertainty computations on three patient datasets. Results are compared against reference computations facilitating importance and random sampling. Two approximation techniques to accelerate uncertainty propagation and minimization based on probabilistic treatment plan optimization are presented. Runtimes are measured on CPU and GPU platforms, dosimetric accuracy is quantified in comparison to a sampling-based benchmark (5000 random samples). APM accurately propagates range and setup uncertainties into dose uncertainties at competitive run-times (GPU ##IMG## [http://ej.iop.org/images/0031-9155/62/14/5790/pmbaa6ec5ieqn001.gif] {$\leqslant {5}$} min). The resulting standard deviation (expectation value) of dose show average global ##IMG## [http://ej.iop.org/images/0031-9155/62/14/5790/pmbaa6ec5ieqn002.gif] {$\gamma_{{3}\% / {3}~{\rm mm}}$} pass rates between 94.2% and 99.9% (98.4% and 100.0%). All investigated importance sampling strategies provided less accuracy at higher run-times considering only a single fraction. Considering fractionation, APM uncertainty propagation and treatment plan optimization was proven to be possible at constant time complexity, while run-times of sampling-based computations are linear in the number of fractions. Using sum sampling within APM, uncertainty propagation can only be accelerated at the cost of reduced accuracy in variance calculations. For probabilistic plan optimization, we were able to approximate the necessary pre-computations within seconds, yielding treatment plans of similar quality as gained from exact uncertainty propagation. APM is suited to enhance the trade-off between speed and accuracy in uncertainty propagation and probabilistic treatment plan optimization, especially in the context of fractionation. This brings fully-fledged APM computations within reach of clinical application.

pn

link (url) [BibTex]

link (url) [BibTex]


Likelihood-based parameter estimation and comparison of dynamical cognitive models

Schütt, H., Rothkegel, L., Trukenbrod, H., Reich, S., Wichmann, F., Engbert, R.

Psychological Review, 124(4):505-524, 2017 (article)

DOI [BibTex]

DOI [BibTex]


Comparing sensitivity estimates from MLDS and forced-choice methods in a slant-from-texture experiment

Aguilar, G., Wichmann, F., Maertens, M.

Journal of Vision, 17(1), 2017 (article)

ei

DOI [BibTex]


Detecting distortions of peripherally presented letter stimuli under crowded conditions

Wallis, T., Tobias, S., Bethge, M., Wichmann, F.

Attention, Perception, & Psychophysics, 79(3):850-862, 2017 (article)

ei

DOI [BibTex]

DOI [BibTex]


Thumb md imgidx 00197
Multi People Tracking with Lifted Multicut and Person Re-identification

Tang, S., Andriluka, M., Andres, B., Schiele, B.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), July 2017 (inproceedings)

ps

[BibTex]

[BibTex]


Thumb md animage2mask3
Assessing body image in anorexia nervosa using biometric self-avatars in virtual reality: Attitudinal components rather than visual body size estimation are distorted

Claire Mölbert, S., Thaler, A., J. Mohler, B., Streuber, S., Romero, J., J. Black, M., Zipfel, S., Karnath, H., Elisabeth Giel, K.

Psychological Medicine, 2017 (article)

Abstract
Background: Body image disturbance (BID) is a core symptom of anorexia nervosa (AN), but as yet distinctive features of BID are unknown. The present study aimed at disentangling perceptual and attitudinal components of BID in AN. Methods: We investigated n=24 women with AN and n=24 controls. Based on a 3D body scan, we created realistic virtual 3D bodies (avatars) for each participant that were varied through a range of ±20% of the participants' weights. Avatars were presented in a virtual reality mirror scenario. Using different psychophysical tasks, participants identified and adjusted their actual and their desired body weight. To test for general perceptual biases in estimating body weight, a second experiment investigated perception of weight and shape matched avatars with another identity. Results: Women with AN and controls underestimated their weight, with a trend that women with AN underestimated more. The average desired body of controls had normal weight while the average desired weight of women with AN corresponded to extreme AN (DSM-5). Correlation analyses revealed that desired body weight, but not accuracy of weight estimation, was associated with eating disorder symptoms. In the second experiment, both groups estimated accurately while the most attractive body was similar to Experiment 1. Conclusions: Our results contradict the widespread assumption that patients with AN overestimate their body weight due to visual distortions. Rather, they illustrate that BID might be driven by distorted attitudes with regard to the desired body. Clinical interventions should aim at helping patients with AN to change their desired weight.

ps

doi pdf [BibTex]


Thumb md teaser image
Follow the Signs for Robust Stochastic Optimization

Balles, L., Hennig, P.

arXiv preprint arXiv:1705.07774, 2017 (article)

Abstract
Stochastic noise on gradients is now a common feature in machine learning. It complicates the design of optimization algorithms, and its effect can be unintuitive: We show that in some settings, particularly those of low signal-to-noise ratio, it can be helpful to discard all but the signs of stochastic gradient elements. In fact, we argue that three popular existing methods already approximate this very paradigm. We devise novel stochastic optimization algorithms that explicitly follow stochastic sign estimates while appropriately accounting for their uncertainty. These methods favorably compare to the state of the art on a number of benchmark problems.

pn

link (url) Project Page [BibTex]


Causal Discovery from Temporally Aggregated Time Series

Gong, M., Zhang, K., Schölkopf, B., Glymour, C., Tao, D.

Proceedings of the Thirty-Third Conference on Uncertainty in Artificial Intelligence (UAI 2017), 2017, ID 269 (conference) Accepted

ei

[BibTex]

[BibTex]


Causal Discovery from Nonstationary/Heterogeneous Data: Skeleton Estimation and Orientation Determination

Zhang, K., Huang, B., Zhang, J., Glymour, C., Schölkopf, B.

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI 2017), 2017 (conference) Accepted

ei

PDF [BibTex]

PDF [BibTex]


Self-Organized Behavior Generation for Musculoskeletal Robots

Der, R., Martius, G.

Frontiers in Neurorobotics, 11, pages: 8, 2017 (article)

al

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Elements of Causal Inference - Foundations and Learning Algorithms

Peters, J., Janzing, D., Schölkopf, B.

Adaptive Computation and Machine Learning Series, The MIT Press, Cambridge, MA, USA, 2017 (book) In press

ei

PDF [BibTex]

PDF [BibTex]


Thumb md image
Human Shape Estimation using Statistical Body Models

Maverick Loper, M.

University of Tübingen, May 2017 (thesis)

Abstract
Human body estimation methods transform real-world observations into predictions about human body state. These estimation methods benefit a variety of health, entertainment, clothing, and ergonomics applications. State may include pose, overall body shape, and appearance. Body state estimation is underconstrained by observations; ambiguity presents itself both in the form of missing data within observations, and also in the form of unknown correspondences between observations. We address this challenge with the use of a statistical body model: a data-driven virtual human. This helps resolve ambiguity in two ways. First, it fills in missing data, meaning that incomplete observations still result in complete shape estimates. Second, the model provides a statistically-motivated penalty for unlikely states, which enables more plausible body shape estimates. Body state inference requires more than a body model; we therefore build obser- vation models whose output is compared with real observations. In this thesis, body state is estimated from three types of observations: 3D motion capture markers, depth and color images, and high-resolution 3D scans. In each case, a forward process is proposed which simulates observations. By comparing observations to the results of the forward process, state can be adjusted to minimize the difference between simulated and observed data. We use gradient-based methods because they are critical to the precise estimation of state with a large number of parameters. The contributions of this work include three parts. First, we propose a method for the estimation of body shape, nonrigid deformation, and pose from 3D markers. Second, we present a concise approach to differentiating through the rendering process, with application to body shape estimation. And finally, we present a statistical body model trained from human body scans, with state-of-the-art fidelity, good runtime performance, and compatibility with existing animation packages.

ps

Official Version [BibTex]


Thumb md cover tro paper
An Online Scalable Approach to Unified Multirobot Cooperative Localization and Object Tracking

Ahmad, A., Lawless, G., Lima, P.

IEEE Transactions on Robotics (T-RO), 2017, Accepted, May 2017 (article)

Abstract
In this article we present a unified approach for multi-robot cooperative simultaneous localization and object tracking based on particle filters. Our approach is scalable with respect to the number of robots in the team. We introduce a method that reduces, from an exponential to a linear growth, the space and computation time requirements with respect to the number of robots in order to maintain a given level of accuracy in the full state estimation. Our method requires no increase in the number of particles with respect to the number of robots. However, in our method each particle represents a full state hypothesis, leading to the linear dependency on the number of robots of both space and time complexity. The derivation of the algorithm implementing our approach from a standard particle filter algorithm and its complexity analysis are presented. Through an extensive set of simulation experiments on a large number of randomized datasets, we demonstrate the correctness and efficacy of our approach. Through real robot experiments on a standardized open dataset of a team of four soccer playing robots tracking a ball, we evaluate our method's estimation accuracy with respect to the ground truth values. Through comparisons with other methods based on i) nonlinear least squares minimization and ii) joint extended Kalman filter, we further highlight our method's advantages. Finally, we also present a robustness test for our approach by evaluating it under scenarios of communication and vision failure in teammate robots.

ps

accepted pre-print version [BibTex]


Thumb md phd thesis teaser
Learning Inference Models for Computer Vision

Jampani, V.

MPI for Intelligent Systems and University of Tübingen, 2017 (phdthesis)

Abstract
Computer vision can be understood as the ability to perform 'inference' on image data. Breakthroughs in computer vision technology are often marked by advances in inference techniques, as even the model design is often dictated by the complexity of inference in them. This thesis proposes learning based inference schemes and demonstrates applications in computer vision. We propose techniques for inference in both generative and discriminative computer vision models. Despite their intuitive appeal, the use of generative models in vision is hampered by the difficulty of posterior inference, which is often too complex or too slow to be practical. We propose techniques for improving inference in two widely used techniques: Markov Chain Monte Carlo (MCMC) sampling and message-passing inference. Our inference strategy is to learn separate discriminative models that assist Bayesian inference in a generative model. Experiments on a range of generative vision models show that the proposed techniques accelerate the inference process and/or converge to better solutions. A main complication in the design of discriminative models is the inclusion of prior knowledge in a principled way. For better inference in discriminative models, we propose techniques that modify the original model itself, as inference is simple evaluation of the model. We concentrate on convolutional neural network (CNN) models and propose a generalization of standard spatial convolutions, which are the basic building blocks of CNN architectures, to bilateral convolutions. First, we generalize the existing use of bilateral filters and then propose new neural network architectures with learnable bilateral filters, which we call `Bilateral Neural Networks'. We show how the bilateral filtering modules can be used for modifying existing CNN architectures for better image segmentation and propose a neural network approach for temporal information propagation in videos. Experiments demonstrate the potential of the proposed bilateral networks on a wide range of vision tasks and datasets. In summary, we propose learning based techniques for better inference in several computer vision models ranging from inverse graphics to freely parameterized neural networks. In generative vision models, our inference techniques alleviate some of the crucial hurdles in Bayesian posterior inference, paving new ways for the use of model based machine learning in vision. In discriminative CNN models, the proposed filter generalizations aid in the design of new neural network architectures that can handle sparse high-dimensional data as well as provide a way for incorporating prior knowledge into CNNs.

ps

pdf [BibTex]

pdf [BibTex]


Thumb md pilqr cover
Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning

Chebotar, Y., Hausman, K., Zhang, M., Sukhatme, G., Schaal, S., Levine, S.

International Conference on Machine Learning (ICML) 2017, International Conference on Machine Learning (ICML), August 2017 (conference)

am

pdf video [BibTex]

pdf video [BibTex]


Approximate Steepest Coordinate Descent

Stich, S., Raj, A., Jaggi, M.

Proceedings of the 34th International Conference on Machine Learning (ICML 2017), 70, pages: 3251-3259, Proceedings of Machine Learning Research, (Editors: Doina Precup and Yee Whye Teh), PMLR, 2017 (conference)

ei

link (url) [BibTex]

link (url) [BibTex]


Local Group Invariant Representations via Orbit Embeddings

Raj, A., Kumar, A., Mroueh, Y., Fletcher, T., Schölkopf, B.

Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017), 54, pages: 1225-1235, Proceedings of Machine Learning Research, (Editors: Aarti Singh and Jerry Zhu), 2017 (conference)

ei

link (url) [BibTex]

link (url) [BibTex]


Local Bayesian Optimization of Motor Skills

Akrour, R., Sorokin, D., Peters, J., Neumann, G.

Proceedings of the 34th International Conference on Machine Learning (ICML 2017), 2017 (conference) Accepted

am ei

[BibTex]

[BibTex]


Pre-Movement Contralateral EEG Low Beta Power Is Modulated with Motor Adaptation Learning

Ozdenizci, O., Yalcin, M., Erdogan, A., Patoglu, V., Grosse-Wentrup, M., Cetin, M.

Proceedings of the 7th Graz Brain-Computer Interface Conference (GBCIC 2017), 2017 (conference) Accepted

ei

[BibTex]

[BibTex]


Correlations of Motor Adaptation Learning and Modulation of Resting-State Sensorimotor EEG Activity

Ozdenizci, O., Yalcin, M., Erdogan, A., Patoglu, V., Grosse-Wentrup, M., Cetin, M.

Proceedings of the 7th Graz Brain-Computer Interface Conference (GBCIC 2017), 2017 (conference) Accepted

ei

[BibTex]

[BibTex]


Investigating Music Imagery as a Cognitive Paradigm for Low-Cost Brain-Computer Interfaces

Grossberger, L., Hohmann, M., Peters, J., M., G.

Proceedings of the 7th Graz Brain-Computer Interface Conference (GBCIC 2017), 2017 (conference) Accepted

am ei

[BibTex]

[BibTex]


Bayesian Regression for Artifact Correction in Electroencephalography

Fiebig, K., Jayaram, V., Hesse, T., Blank, A., Peters, J., M., G.

Proceedings of the 7th Graz Brain-Computer Interface Conference (GBCIC 2017), 2017 (conference) Accepted

am ei

[BibTex]

[BibTex]