Paper Group ANR 235
Learning Graphical Games from Behavioral Data: Sufficient and Necessary Conditions. Temporal Non-Volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition. Supervised Complementary Entity Recognition with Augmented Key-value Pairs of Knowledge. Flexible Prior Distributions for Deep Generative Models. Aerial Spectral Su …
Learning Graphical Games from Behavioral Data: Sufficient and Necessary Conditions
| Title | Learning Graphical Games from Behavioral Data: Sufficient and Necessary Conditions |
| Authors | Asish Ghoshal, Jean Honorio |
| Abstract | In this paper we obtain sufficient and necessary conditions on the number of samples required for exact recovery of the pure-strategy Nash equilibria (PSNE) set of a graphical game from noisy observations of joint actions. We consider sparse linear influence games — a parametric class of graphical games with linear payoffs, and represented by directed graphs of n nodes (players) and in-degree of at most k. We show that one can efficiently recover the PSNE set of a linear influence game with $O(k^2 \log n)$ samples, under very general observation models. On the other hand, we show that $\Omega(k \log n)$ samples are necessary for any procedure to recover the PSNE set from observations of joint actions. |
| Tasks | |
| Published | 2017-03-03 |
| URL | http://arxiv.org/abs/1703.01218v1 |
| http://arxiv.org/pdf/1703.01218v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-graphical-games-from-behavioral-data |
| Repo | |
| Framework | |
Temporal Non-Volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition
| Title | Temporal Non-Volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition |
| Authors | Chi Nhan Duong, Kha Gia Quach, Khoa Luu, T. Hoang Ngan le, Marios Savvides |
| Abstract | Modeling the long-term facial aging process is extremely challenging due to the presence of large and non-linear variations during the face development stages. In order to efficiently address the problem, this work first decomposes the aging process into multiple short-term stages. Then, a novel generative probabilistic model, named Temporal Non-Volume Preserving (TNVP) transformation, is presented to model the facial aging process at each stage. Unlike Generative Adversarial Networks (GANs), which requires an empirical balance threshold, and Restricted Boltzmann Machines (RBM), an intractable model, our proposed TNVP approach guarantees a tractable density function, exact inference and evaluation for embedding the feature transformations between faces in consecutive stages. Our model shows its advantages not only in capturing the non-linear age related variance in each stage but also producing a smooth synthesis in age progression across faces. Our approach can model any face in the wild provided with only four basic landmark points. Moreover, the structure can be transformed into a deep convolutional network while keeping the advantages of probabilistic models with tractable log-likelihood density estimation. Our method is evaluated in both terms of synthesizing age-progressed faces and cross-age face verification and consistently shows the state-of-the-art results in various face aging databases, i.e. FG-NET, MORPH, AginG Faces in the Wild (AGFW), and Cross-Age Celebrity Dataset (CACD). A large-scale face verification on Megaface challenge 1 is also performed to further show the advantages of our proposed approach. |
| Tasks | Age-Invariant Face Recognition, Density Estimation, Face Recognition, Face Verification |
| Published | 2017-03-24 |
| URL | http://arxiv.org/abs/1703.08617v1 |
| http://arxiv.org/pdf/1703.08617v1.pdf | |
| PWC | https://paperswithcode.com/paper/temporal-non-volume-preserving-approach-to |
| Repo | |
| Framework | |
Supervised Complementary Entity Recognition with Augmented Key-value Pairs of Knowledge
| Title | Supervised Complementary Entity Recognition with Augmented Key-value Pairs of Knowledge |
| Authors | Hu Xu, Lei Shu, Philip S. Yu |
| Abstract | Extracting opinion targets is an important task in sentiment analysis on product reviews and complementary entities (products) are one important type of opinion targets that may work together with the reviewed product. In this paper, we address the problem of Complementary Entity Recognition (CER) as a supervised sequence labeling with the capability of expanding domain knowledge as key-value pairs from unlabeled reviews, by automatically learning and enhancing knowledge-based features. We use Conditional Random Field (CRF) as the base learner and augment CRF with knowledge-based features (called the Knowledge-based CRF or KCRF for short). We conduct experiments to show that KCRF effectively improves the performance of supervised CER task. |
| Tasks | Sentiment Analysis |
| Published | 2017-05-29 |
| URL | http://arxiv.org/abs/1705.10030v1 |
| http://arxiv.org/pdf/1705.10030v1.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-complementary-entity-recognition |
| Repo | |
| Framework | |
Flexible Prior Distributions for Deep Generative Models
| Title | Flexible Prior Distributions for Deep Generative Models |
| Authors | Yannic Kilcher, Aurelien Lucchi, Thomas Hofmann |
| Abstract | We consider the problem of training generative models with deep neural networks as generators, i.e. to map latent codes to data points. Whereas the dominant paradigm combines simple priors over codes with complex deterministic models, we argue that it might be advantageous to use more flexible code distributions. We demonstrate how these distributions can be induced directly from the data. The benefits include: more powerful generative models, better modeling of latent structure and explicit control of the degree of generalization. |
| Tasks | |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1710.11383v2 |
| http://arxiv.org/pdf/1710.11383v2.pdf | |
| PWC | https://paperswithcode.com/paper/flexible-prior-distributions-for-deep |
| Repo | |
| Framework | |
Aerial Spectral Super-Resolution using Conditional Adversarial Networks
| Title | Aerial Spectral Super-Resolution using Conditional Adversarial Networks |
| Authors | Aneesh Rangnekar, Nilay Mokashi, Emmett Ientilucci, Christopher Kanan, Matthew Hoffman |
| Abstract | Inferring spectral signatures from ground based natural images has acquired a lot of interest in applied deep learning. In contrast to the spectra of ground based images, aerial spectral images have low spatial resolution and suffer from higher noise interference. In this paper, we train a conditional adversarial network to learn an inverse mapping from a trichromatic space to 31 spectral bands within 400 to 700 nm. The network is trained on AeroCampus, a first of its kind aerial hyperspectral dataset. AeroCampus consists of high spatial resolution color images and low spatial resolution hyperspectral images (HSI). Color images synthesized from 31 spectral bands are used to train our network. With a baseline root mean square error of 2.48 on the synthesized RGB test data, we show that it is possible to generate spectral signatures in aerial imagery. |
| Tasks | Super-Resolution |
| Published | 2017-12-23 |
| URL | http://arxiv.org/abs/1712.08690v1 |
| http://arxiv.org/pdf/1712.08690v1.pdf | |
| PWC | https://paperswithcode.com/paper/aerial-spectral-super-resolution-using |
| Repo | |
| Framework | |
Energy Saving Additive Neural Network
| Title | Energy Saving Additive Neural Network |
| Authors | Arman Afrasiyabi, Ozan Yildiz, Baris Nasir, Fatos T. Yarman Vural, A. Enis Cetin |
| Abstract | In recent years, machine learning techniques based on neural networks for mobile computing become increasingly popular. Classical multi-layer neural networks require matrix multiplications at each stage. Multiplication operation is not an energy efficient operation and consequently it drains the battery of the mobile device. In this paper, we propose a new energy efficient neural network with the universal approximation property over space of Lebesgue integrable functions. This network, called, additive neural network, is very suitable for mobile computing. The neural structure is based on a novel vector product definition, called ef-operator, that permits a multiplier-free implementation. In ef-operation, the “product” of two real numbers is defined as the sum of their absolute values, with the sign determined by the sign of the product of the numbers. This “product” is used to construct a vector product in $R^N$. The vector product induces the $l_1$ norm. The proposed additive neural network successfully solves the XOR problem. The experiments on MNIST dataset show that the classification performances of the proposed additive neural networks are very similar to the corresponding multi-layer perceptron and convolutional neural networks (LeNet). |
| Tasks | |
| Published | 2017-02-09 |
| URL | http://arxiv.org/abs/1702.02676v1 |
| http://arxiv.org/pdf/1702.02676v1.pdf | |
| PWC | https://paperswithcode.com/paper/energy-saving-additive-neural-network |
| Repo | |
| Framework | |
Modality-bridge Transfer Learning for Medical Image Classification
| Title | Modality-bridge Transfer Learning for Medical Image Classification |
| Authors | Hak Gu Kim, Yeoreum Choi, Yong Man Ro |
| Abstract | This paper presents a new approach of transfer learning-based medical image classification to mitigate insufficient labeled data problem in medical domain. Instead of direct transfer learning from source to small number of labeled target data, we propose a modality-bridge transfer learning which employs the bridge database in the same medical imaging acquisition modality as target database. By learning the projection function from source to bridge and from bridge to target, the domain difference between source (e.g., natural images) and target (e.g., X-ray images) can be mitigated. Experimental results show that the proposed method can achieve a high classification performance even for a small number of labeled target medical images, compared to various transfer learning approaches. |
| Tasks | Image Classification, Transfer Learning |
| Published | 2017-08-10 |
| URL | http://arxiv.org/abs/1708.03111v1 |
| http://arxiv.org/pdf/1708.03111v1.pdf | |
| PWC | https://paperswithcode.com/paper/modality-bridge-transfer-learning-for-medical |
| Repo | |
| Framework | |
Truncated Variational Sampling for “Black Box” Optimization of Generative Models
| Title | Truncated Variational Sampling for “Black Box” Optimization of Generative Models |
| Authors | Jörg Lücke, Zhenwen Dai, Georgios Exarchakis |
| Abstract | We investigate the optimization of two probabilistic generative models with binary latent variables using a novel variational EM approach. The approach distinguishes itself from previous variational approaches by using latent states as variational parameters. Here we use efficient and general purpose sampling procedures to vary the latent states, and investigate the “black box” applicability of the resulting optimization procedure. For general purpose applicability, samples are drawn from approximate marginal distributions of the considered generative model as well as from the model’s prior distribution. As such, variational sampling is defined in a generic form, and is directly executable for a given model. As a proof of concept, we then apply the novel procedure (A) to Binary Sparse Coding (a model with continuous observables), and (B) to basic Sigmoid Belief Networks (which are models with binary observables). Numerical experiments verify that the investigated approach efficiently as well as effectively increases a variational free energy objective without requiring any additional analytical steps. |
| Tasks | |
| Published | 2017-12-21 |
| URL | http://arxiv.org/abs/1712.08104v2 |
| http://arxiv.org/pdf/1712.08104v2.pdf | |
| PWC | https://paperswithcode.com/paper/truncated-variational-sampling-for-black-box |
| Repo | |
| Framework | |
Feature Extraction via Recurrent Random Deep Ensembles and its Application in Gruop-level Happiness Estimation
| Title | Feature Extraction via Recurrent Random Deep Ensembles and its Application in Gruop-level Happiness Estimation |
| Authors | Shitao Tang, Yichen Pan |
| Abstract | This paper presents a novel ensemble framework to extract highly discriminative feature representation of image and its application for group-level happpiness intensity prediction in wild. In order to generate enough diversity of decisions, n convolutional neural networks are trained by bootstrapping the training set and extract n features for each image from them. A recurrent neural network (RNN) is then used to remember which network extracts better feature and generate the final feature representation for one individual image. Several group emotion models (GEM) are used to aggregate face fea- tures in a group and use parameter-optimized support vector regressor (SVR) to get the final results. Through extensive experiments, the great effectiveness of the proposed recurrent random deep ensembles (RRDE) is demonstrated in both structural and decisional ways. The best result yields a 0.55 root-mean-square error (RMSE) on validation set of HAPPEI dataset, significantly better than the baseline of 0.78. |
| Tasks | |
| Published | 2017-07-24 |
| URL | http://arxiv.org/abs/1707.09871v1 |
| http://arxiv.org/pdf/1707.09871v1.pdf | |
| PWC | https://paperswithcode.com/paper/feature-extraction-via-recurrent-random-deep |
| Repo | |
| Framework | |
Improving the Expected Improvement Algorithm
| Title | Improving the Expected Improvement Algorithm |
| Authors | Chao Qin, Diego Klabjan, Daniel Russo |
| Abstract | The expected improvement (EI) algorithm is a popular strategy for information collection in optimization under uncertainty. The algorithm is widely known to be too greedy, but nevertheless enjoys wide use due to its simplicity and ability to handle uncertainty and noise in a coherent decision theoretic framework. To provide rigorous insight into EI, we study its properties in a simple setting of Bayesian optimization where the domain consists of a finite grid of points. This is the so-called best-arm identification problem, where the goal is to allocate measurement effort wisely to confidently identify the best arm using a small number of measurements. In this framework, one can show formally that EI is far from optimal. To overcome this shortcoming, we introduce a simple modification of the expected improvement algorithm. Surprisingly, this simple change results in an algorithm that is asymptotically optimal for Gaussian best-arm identification problems, and provably outperforms standard EI by an order of magnitude. |
| Tasks | |
| Published | 2017-05-29 |
| URL | http://arxiv.org/abs/1705.10033v1 |
| http://arxiv.org/pdf/1705.10033v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-the-expected-improvement-algorithm |
| Repo | |
| Framework | |
Towards Smart Proof Search for Isabelle
| Title | Towards Smart Proof Search for Isabelle |
| Authors | Yutaka Nagashima |
| Abstract | Despite the recent progress in automatic theorem provers, proof engineers are still suffering from the lack of powerful proof automation. In this position paper we first report our proof strategy language based on a meta-tool approach. Then, we propose an AI-based approach to drastically improve proof automation for Isabelle, while identifying three major challenges we plan to address for this objective. |
| Tasks | |
| Published | 2017-01-10 |
| URL | http://arxiv.org/abs/1701.03037v1 |
| http://arxiv.org/pdf/1701.03037v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-smart-proof-search-for-isabelle |
| Repo | |
| Framework | |
DeepRebirth: Accelerating Deep Neural Network Execution on Mobile Devices
| Title | DeepRebirth: Accelerating Deep Neural Network Execution on Mobile Devices |
| Authors | Dawei Li, Xiaolong Wang, Deguang Kong |
| Abstract | Deploying deep neural networks on mobile devices is a challenging task. Current model compression methods such as matrix decomposition effectively reduce the deployed model size, but still cannot satisfy real-time processing requirement. This paper first discovers that the major obstacle is the excessive execution time of non-tensor layers such as pooling and normalization without tensor-like trainable parameters. This motivates us to design a novel acceleration framework: DeepRebirth through “slimming” existing consecutive and parallel non-tensor and tensor layers. The layer slimming is executed at different substructures: (a) streamline slimming by merging the consecutive non-tensor and tensor layer vertically; (b) branch slimming by merging non-tensor and tensor branches horizontally. The proposed optimization operations significantly accelerate the model execution and also greatly reduce the run-time memory cost since the slimmed model architecture contains less hidden layers. To maximally avoid accuracy loss, the parameters in new generated layers are learned with layer-wise fine-tuning based on both theoretical analysis and empirical verification. As observed in the experiment, DeepRebirth achieves more than 3x speed-up and 2.5x run-time memory saving on GoogLeNet with only 0.4% drop of top-5 accuracy on ImageNet. Furthermore, by combining with other model compression techniques, DeepRebirth offers an average of 65ms inference time on the CPU of Samsung Galaxy S6 with 86.5% top-5 accuracy, 14% faster than SqueezeNet which only has a top-5 accuracy of 80.5%. |
| Tasks | Model Compression |
| Published | 2017-08-16 |
| URL | http://arxiv.org/abs/1708.04728v2 |
| http://arxiv.org/pdf/1708.04728v2.pdf | |
| PWC | https://paperswithcode.com/paper/deeprebirth-accelerating-deep-neural-network |
| Repo | |
| Framework | |
Offline signature authenticity verification through unambiguously connected skeleton segments
| Title | Offline signature authenticity verification through unambiguously connected skeleton segments |
| Authors | Jugurta Montalvão, Luiz Miranda, Jânio Canuto |
| Abstract | A method for offline signature verification is presented in this paper. It is based on the segmentation of the signature skeleton (through standard image skeletonization) into unambiguous sequences of points, or unambiguously connected skeleton segments corresponding to vectorial representations of signature portions. These segments are assumed to be the fundamental carriers of useful information for authenticity verification, and are compactly encoded as sets of 9 scalars (4 sampled coordinates and 1 length measure). Thus signature authenticity is inferred through Euclidean distance based comparisons between pairs of such compact representations. The average performance of this method is evaluated through experiments with offline versions of signatures from the MCYT-100 database. For comparison purposes, three other approaches are applied to the same set of signatures, namely: (1) a straightforward approach based on Dynamic Time Warping distances between segments, (2) a published method by [shanker2007], also based on DTW, and (3) the average human performance under equivalent experimental protocol. Results suggest that if human performance is taken as a goal for automatic verification, then we should discard signature shape details to approach this goal. Moreover, our best result – close to human performance – was obtained by the simplest strategy, where equal weights were given to segment shape and length. |
| Tasks | |
| Published | 2017-11-08 |
| URL | http://arxiv.org/abs/1711.03082v1 |
| http://arxiv.org/pdf/1711.03082v1.pdf | |
| PWC | https://paperswithcode.com/paper/offline-signature-authenticity-verification |
| Repo | |
| Framework | |
Evaluating Music Recommender Systems for Groups
| Title | Evaluating Music Recommender Systems for Groups |
| Authors | Zsolt Mezei, Carsten Eickhoff |
| Abstract | Recommendation to groups of users is a challenging and currently only passingly studied task. Especially the evaluation aspect often appears ad-hoc and instead of truly evaluating on groups of users, synthesizes groups by merging individual preferences. In this paper, we present a user study, recording the individual and shared preferences of actual groups of participants, resulting in a robust, standardized evaluation benchmark. Using this benchmarking dataset, that we share with the research community, we compare the respective performance of a wide range of music group recommendation techniques proposed in the |
| Tasks | Recommendation Systems |
| Published | 2017-07-31 |
| URL | http://arxiv.org/abs/1707.09790v1 |
| http://arxiv.org/pdf/1707.09790v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-music-recommender-systems-for |
| Repo | |
| Framework | |
3D tracking of water hazards with polarized stereo cameras
| Title | 3D tracking of water hazards with polarized stereo cameras |
| Authors | Chuong V. Nguyen, Michael Milford, Robert Mahony |
| Abstract | Current self-driving car systems operate well in sunny weather but struggle in adverse conditions. One of the most commonly encountered adverse conditions involves water on the road caused by rain, sleet, melting snow or flooding. While some advances have been made in using conventional RGB camera and LIDAR technology for detecting water hazards, other sources of information such as polarization offer a promising and potentially superior approach to this problem in terms of performance and cost. In this paper, we present a novel stereo-polarization system for detecting and tracking water hazards based on polarization and color variation of reflected light, with consideration of the effect of polarized light from sky as function of reflection and azimuth angles. To evaluate this system, we present a new large `water on road’ datasets spanning approximately 2 km of driving in various on-road and off-road conditions and demonstrate for the first time reliable water detection and tracking over a wide range of realistic car driving water conditions using polarized vision as the primary sensing modality. Our system successfully detects water hazards up to more than 100m. Finally, we discuss several interesting challenges and propose future research directions for further improving robust autonomous car perception in hazardous wet conditions using polarization sensors. | |
| Tasks | |
| Published | 2017-01-16 |
| URL | http://arxiv.org/abs/1701.04175v2 |
| http://arxiv.org/pdf/1701.04175v2.pdf | |
| PWC | https://paperswithcode.com/paper/3d-tracking-of-water-hazards-with-polarized |
| Repo | |
| Framework | |
