Paper Group ANR 89
Byte-based Language Identification with Deep Convolutional Networks. Hierarchical Conflict Propagation: Sequence Learning in a Recurrent Deep Neural Network. Fine-to-coarse Knowledge Transfer For Low-Res Image Classification. Photographic dataset: random peppercorns. Solving MaxSAT by Successive Calls to a SAT Solver. Variational Autoencoder for De …
Byte-based Language Identification with Deep Convolutional Networks
| Title | Byte-based Language Identification with Deep Convolutional Networks |
| Authors | Johannes Bjerva |
| Abstract | We report on our system for the shared task on discriminating between similar languages (DSL 2016). The system uses only byte representations in a deep residual network (ResNet). The system, named ResIdent, is trained only on the data released with the task (closed training). We obtain 84.88% accuracy on subtask A, 68.80% accuracy on subtask B1, and 69.80% accuracy on subtask B2. A large difference in accuracy on development data can be observed with relatively minor changes in our network’s architecture and hyperparameters. We therefore expect fine-tuning of these parameters to yield higher accuracies. |
| Tasks | Language Identification |
| Published | 2016-09-28 |
| URL | http://arxiv.org/abs/1609.09004v2 |
| http://arxiv.org/pdf/1609.09004v2.pdf | |
| PWC | https://paperswithcode.com/paper/byte-based-language-identification-with-deep |
| Repo | |
| Framework | |
Hierarchical Conflict Propagation: Sequence Learning in a Recurrent Deep Neural Network
| Title | Hierarchical Conflict Propagation: Sequence Learning in a Recurrent Deep Neural Network |
| Authors | Andrew J. R. Simpson |
| Abstract | Recurrent neural networks (RNN) are capable of learning to encode and exploit activation history over an arbitrary timescale. However, in practice, state of the art gradient descent based training methods are known to suffer from difficulties in learning long term dependencies. Here, we describe a novel training method that involves concurrent parallel cloned networks, each sharing the same weights, each trained at different stimulus phase and each maintaining independent activation histories. Training proceeds by recursively performing batch-updates over the parallel clones as activation history is progressively increased. This allows conflicts to propagate hierarchically from short-term contexts towards longer-term contexts until they are resolved. We illustrate the parallel clones method and hierarchical conflict propagation with a character-level deep RNN tasked with memorizing a paragraph of Moby Dick (by Herman Melville). |
| Tasks | |
| Published | 2016-02-25 |
| URL | http://arxiv.org/abs/1602.08118v1 |
| http://arxiv.org/pdf/1602.08118v1.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-conflict-propagation-sequence |
| Repo | |
| Framework | |
Fine-to-coarse Knowledge Transfer For Low-Res Image Classification
| Title | Fine-to-coarse Knowledge Transfer For Low-Res Image Classification |
| Authors | Xingchao Peng, Judy Hoffman, Stella X. Yu, Kate Saenko |
| Abstract | We address the difficult problem of distinguishing fine-grained object categories in low resolution images. Wepropose a simple an effective deep learning approach that transfers fine-grained knowledge gained from high resolution training data to the coarse low-resolution test scenario. Such fine-to-coarse knowledge transfer has many real world applications, such as identifying objects in surveillance photos or satellite images where the image resolution at the test time is very low but plenty of high resolution photos of similar objects are available. Our extensive experiments on two standard benchmark datasets containing fine-grained car models and bird species demonstrate that our approach can effectively transfer fine-detail knowledge to coarse-detail imagery. |
| Tasks | Image Classification, Transfer Learning |
| Published | 2016-05-21 |
| URL | http://arxiv.org/abs/1605.06695v1 |
| http://arxiv.org/pdf/1605.06695v1.pdf | |
| PWC | https://paperswithcode.com/paper/fine-to-coarse-knowledge-transfer-for-low-res |
| Repo | |
| Framework | |
Photographic dataset: random peppercorns
| Title | Photographic dataset: random peppercorns |
| Authors | Teemu Helenius, Samuli Siltanen |
| Abstract | This is a photographic dataset collected for testing image processing algorithms. The idea is to have sets of different but statistically similar images. In this work the images show randomly distributed peppercorns. The dataset is made available at www.fips.fi/photographic_dataset.php . |
| Tasks | |
| Published | 2016-03-03 |
| URL | http://arxiv.org/abs/1603.01046v1 |
| http://arxiv.org/pdf/1603.01046v1.pdf | |
| PWC | https://paperswithcode.com/paper/photographic-dataset-random-peppercorns |
| Repo | |
| Framework | |
Solving MaxSAT by Successive Calls to a SAT Solver
| Title | Solving MaxSAT by Successive Calls to a SAT Solver |
| Authors | Mohamed El Halaby |
| Abstract | The Maximum Satisfiability (MaxSAT) problem is the problem of finding a truth assignment that maximizes the number of satisfied clauses of a given Boolean formula in Conjunctive Normal Form (CNF). Many exact solvers for MaxSAT have been developed during recent years, and many of them were presented in the well-known SAT conference. Algorithms for MaxSAT generally fall into two categories: (1) branch and bound algorithms and (2) algorithms that use successive calls to a SAT solver (SAT- based), which this paper in on. In practical problems, SAT-based algorithms have been shown to be more efficient. This paper provides an experimental investigation to compare the performance of recent SAT-based and branch and bound algorithms on the benchmarks of the MaxSAT Evaluations. |
| Tasks | |
| Published | 2016-03-11 |
| URL | http://arxiv.org/abs/1603.03814v1 |
| http://arxiv.org/pdf/1603.03814v1.pdf | |
| PWC | https://paperswithcode.com/paper/solving-maxsat-by-successive-calls-to-a-sat |
| Repo | |
| Framework | |
Variational Autoencoder for Deep Learning of Images, Labels and Captions
| Title | Variational Autoencoder for Deep Learning of Images, Labels and Captions |
| Authors | Yunchen Pu, Zhe Gan, Ricardo Henao, Xin Yuan, Chunyuan Li, Andrew Stevens, Lawrence Carin |
| Abstract | A novel variational autoencoder is developed to model images, as well as associated labels or captions. The Deep Generative Deconvolutional Network (DGDN) is used as a decoder of the latent image features, and a deep Convolutional Neural Network (CNN) is used as an image encoder; the CNN is used to approximate a distribution for the latent DGDN features/code. The latent code is also linked to generative models for labels (Bayesian support vector machine) or captions (recurrent neural network). When predicting a label/caption for a new image at test, averaging is performed across the distribution of latent codes; this is computationally efficient as a consequence of the learned CNN-based encoder. Since the framework is capable of modeling the image in the presence/absence of associated labels/captions, a new semi-supervised setting is manifested for CNN learning with images; the framework even allows unsupervised CNN learning, based on images alone. |
| Tasks | |
| Published | 2016-09-28 |
| URL | http://arxiv.org/abs/1609.08976v1 |
| http://arxiv.org/pdf/1609.08976v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-autoencoder-for-deep-learning-of |
| Repo | |
| Framework | |
CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation Tasks
| Title | CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation Tasks |
| Authors | Jindřich Libovický, Jindřich Helcl, Marek Tlustý, Pavel Pecina, Ondřej Bojar |
| Abstract | Neural sequence to sequence learning recently became a very promising paradigm in machine translation, achieving competitive results with statistical phrase-based systems. In this system description paper, we attempt to utilize several recently published methods used for neural sequential learning in order to build systems for WMT 2016 shared tasks of Automatic Post-Editing and Multimodal Machine Translation. |
| Tasks | Automatic Post-Editing, Machine Translation, Multimodal Machine Translation |
| Published | 2016-06-23 |
| URL | http://arxiv.org/abs/1606.07481v1 |
| http://arxiv.org/pdf/1606.07481v1.pdf | |
| PWC | https://paperswithcode.com/paper/cuni-system-for-wmt16-automatic-post-editing |
| Repo | |
| Framework | |
Psychologically based Virtual-Suspect for Interrogative Interview Training
| Title | Psychologically based Virtual-Suspect for Interrogative Interview Training |
| Authors | Moshe Bitan, Galit Nahari, Zvi Nisin, Ariel Roth, Sarit Kraus |
| Abstract | In this paper, we present a Virtual-Suspect system which can be used to train inexperienced law enforcement personnel in interrogation strategies. The system supports different scenario configurations based on historical data. The responses presented by the Virtual-Suspect are selected based on the psychological state of the suspect, which can be configured as well. Furthermore, each interrogator’s statement affects the Virtual-Suspect’s current psychological state, which may lead the interrogation in different directions. In addition, the model takes into account the context in which the statements are made. Experiments with 24 subjects demonstrate that the Virtual-Suspect’s behavior is similar to that of a human who plays the role of the suspect. |
| Tasks | |
| Published | 2016-05-31 |
| URL | http://arxiv.org/abs/1605.09505v1 |
| http://arxiv.org/pdf/1605.09505v1.pdf | |
| PWC | https://paperswithcode.com/paper/psychologically-based-virtual-suspect-for |
| Repo | |
| Framework | |
Collaborative Learning of Stochastic Bandits over a Social Network
| Title | Collaborative Learning of Stochastic Bandits over a Social Network |
| Authors | Ravi Kumar Kolla, Krishna Jagannathan, Aditya Gopalan |
| Abstract | We consider a collaborative online learning paradigm, wherein a group of agents connected through a social network are engaged in playing a stochastic multi-armed bandit game. Each time an agent takes an action, the corresponding reward is instantaneously observed by the agent, as well as its neighbours in the social network. We perform a regret analysis of various policies in this collaborative learning setting. A key finding of this paper is that natural extensions of widely-studied single agent learning policies to the network setting need not perform well in terms of regret. In particular, we identify a class of non-altruistic and individually consistent policies, and argue by deriving regret lower bounds that they are liable to suffer a large regret in the networked setting. We also show that the learning performance can be substantially improved if the agents exploit the structure of the network, and develop a simple learning algorithm based on dominating sets of the network. Specifically, we first consider a star network, which is a common motif in hierarchical social networks, and show analytically that the hub agent can be used as an information sink to expedite learning and improve the overall regret. We also derive networkwide regret bounds for the algorithm applied to general networks. We conduct numerical experiments on a variety of networks to corroborate our analytical results. |
| Tasks | |
| Published | 2016-02-29 |
| URL | http://arxiv.org/abs/1602.08886v2 |
| http://arxiv.org/pdf/1602.08886v2.pdf | |
| PWC | https://paperswithcode.com/paper/collaborative-learning-of-stochastic-bandits |
| Repo | |
| Framework | |
Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking
| Title | Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking |
| Authors | Wenhui Li, Yongkang Wong, An-An Liu, Yang Li, Yu-Ting Su, Mohan Kankanhalli |
| Abstract | Action recognition has received increasing attention from the computer vision and machine learning communities in the last decade. To enable the study of this problem, there exist a vast number of action datasets, which are recorded under controlled laboratory settings, real-world surveillance environments, or crawled from the Internet. Apart from the “in-the-wild” datasets, the training and test split of conventional datasets often possess similar environments conditions, which leads to close to perfect performance on constrained datasets. In this paper, we introduce a new dataset, namely Multi-Camera Action Dataset (MCAD), which is designed to evaluate the open view classification problem under the surveillance environment. In total, MCAD contains 14,298 action samples from 18 action categories, which are performed by 20 subjects and independently recorded with 5 cameras. Inspired by the well received evaluation approach on the LFW dataset, we designed a standard evaluation protocol and benchmarked MCAD under several scenarios. The benchmark shows that while an average of 85% accuracy is achieved under the closed-view scenario, the performance suffers from a significant drop under the cross-view scenario. In the worst case scenario, the performance of 10-fold cross validation drops from 87.0% to 47.4%. |
| Tasks | Temporal Action Localization |
| Published | 2016-07-21 |
| URL | http://arxiv.org/abs/1607.06408v3 |
| http://arxiv.org/pdf/1607.06408v3.pdf | |
| PWC | https://paperswithcode.com/paper/multi-camera-action-dataset-for-cross-camera |
| Repo | |
| Framework | |
Leveraging Over Priors for Boosting Control of Prosthetic Hands
| Title | Leveraging Over Priors for Boosting Control of Prosthetic Hands |
| Authors | Valentina Gregori |
| Abstract | The Electromyography (EMG) signal is the electrical activity produced by cells of skeletal muscles in order to provide a movement. The non-invasive prosthetic hand works with several electrodes, placed on the stump of an amputee, that record this signal. In order to favour the control of prosthesis, the EMG signal is analyzed with algorithms based on machine learning theory to decide the movement that the subject is going to do. In order to obtain a significant control of the prosthesis and avoid mismatch between desired and performed movements, a long training period is needed when we use the traditional algorithm of machine learning (i.e. Support Vector Machines). An actual challenge in this field concerns the reduction of the time necessary for an amputee to learn how to use the prosthesis. Recently, several algorithms that exploit a form of prior knowledge have been proposed. In general, we refer to prior knowledge as a past experience available in the form of models. In our case an amputee, that attempts to perform some movements with the prosthesis, could use experience from different subjects that are already able to perform those movements. The aim of this work is to verify, with a computational investigation, if for an amputee this kind of previous experience is useful in order to reduce the training time and boost the prosthetic control. Furthermore, we want to understand if and how the final results change when the previous knowledge of intact or amputated subjects is used for a new amputee. Our experiments indicate that: (1) the use of experience, from other subjects already trained to perform a task, makes us able to reduce the training time of about an order of magnitude; (2) it seems that an amputee that tries to learn to use the prosthesis doesn’t reach different results when he/she exploits previous experience of amputees or intact. |
| Tasks | Electromyography (EMG) |
| Published | 2016-05-24 |
| URL | http://arxiv.org/abs/1605.07498v1 |
| http://arxiv.org/pdf/1605.07498v1.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-over-priors-for-boosting-control |
| Repo | |
| Framework | |
Revisiting Winner Take All (WTA) Hashing for Sparse Datasets
| Title | Revisiting Winner Take All (WTA) Hashing for Sparse Datasets |
| Authors | Beidi Chen, Anshumali Shrivastava |
| Abstract | WTA (Winner Take All) hashing has been successfully applied in many large scale vision applications. This hashing scheme was tailored to take advantage of the comparative reasoning (or order based information), which showed significant accuracy improvements. In this paper, we identify a subtle issue with WTA, which grows with the sparsity of the datasets. This issue limits the discriminative power of WTA. We then propose a solution for this problem based on the idea of Densification which provably fixes the issue. Our experiments show that Densified WTA Hashing outperforms Vanilla WTA both in image classification and retrieval tasks consistently and significantly. |
| Tasks | Image Classification |
| Published | 2016-12-06 |
| URL | http://arxiv.org/abs/1612.01834v2 |
| http://arxiv.org/pdf/1612.01834v2.pdf | |
| PWC | https://paperswithcode.com/paper/revisiting-winner-take-all-wta-hashing-for |
| Repo | |
| Framework | |
Alternating Back-Propagation for Generator Network
| Title | Alternating Back-Propagation for Generator Network |
| Authors | Tian Han, Yang Lu, Song-Chun Zhu, Ying Nian Wu |
| Abstract | This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a non-linear generalization of factor analysis. In this model, the mapping from the continuous latent factors to the observed signal is parametrized by a convolutional neural network. The alternating back-propagation algorithm iterates the following two steps: (1) Inferential back-propagation, which infers the latent factors by Langevin dynamics or gradient descent. (2) Learning back-propagation, which updates the parameters given the inferred latent factors by gradient descent. The gradient computations in both steps are powered by back-propagation, and they share most of their code in common. We show that the alternating back-propagation algorithm can learn realistic generator models of natural images, video sequences, and sounds. Moreover, it can also be used to learn from incomplete or indirect training data. |
| Tasks | |
| Published | 2016-06-28 |
| URL | http://arxiv.org/abs/1606.08571v4 |
| http://arxiv.org/pdf/1606.08571v4.pdf | |
| PWC | https://paperswithcode.com/paper/alternating-back-propagation-for-generator |
| Repo | |
| Framework | |
Estimation of Fiber Orientations Using Neighborhood Information
| Title | Estimation of Fiber Orientations Using Neighborhood Information |
| Authors | Chuyang Ye, Jiachen Zhuo, Rao P. Gullapalli, Jerry L. Prince |
| Abstract | Data from diffusion magnetic resonance imaging (dMRI) can be used to reconstruct fiber tracts, for example, in muscle and white matter. Estimation of fiber orientations (FOs) is a crucial step in the reconstruction process and these estimates can be corrupted by noise. In this paper, a new method called Fiber Orientation Reconstruction using Neighborhood Information (FORNI) is described and shown to reduce the effects of noise and improve FO estimation performance by incorporating spatial consistency. FORNI uses a fixed tensor basis to model the diffusion weighted signals, which has the advantage of providing an explicit relationship between the basis vectors and the FOs. FO spatial coherence is encouraged using weighted l1-norm regularization terms, which contain the interaction of directional information between neighbor voxels. Data fidelity is encouraged using a squared error between the observed and reconstructed diffusion weighted signals. After appropriate weighting of these competing objectives, the resulting objective function is minimized using a block coordinate descent algorithm, and a straightforward parallelization strategy is used to speed up processing. Experiments were performed on a digital crossing phantom, ex vivo tongue dMRI data, and in vivo brain dMRI data for both qualitative and quantitative evaluation. The results demonstrate that FORNI improves the quality of FO estimation over other state of the art algorithms. |
| Tasks | |
| Published | 2016-01-16 |
| URL | http://arxiv.org/abs/1601.04115v2 |
| http://arxiv.org/pdf/1601.04115v2.pdf | |
| PWC | https://paperswithcode.com/paper/estimation-of-fiber-orientations-using |
| Repo | |
| Framework | |
Double-detector for Sparse Signal Detection from One Bit Compressed Sensing Measurements
| Title | Double-detector for Sparse Signal Detection from One Bit Compressed Sensing Measurements |
| Authors | Hadi Zayyani, Farzan Haddadi, Mehdi Korki |
| Abstract | This letter presents the sparse vector signal detection from one bit compressed sensing measurements, in contrast to the previous works which deal with scalar signal detection. In this letter, available results are extended to the vector case and the GLRT detector and the optimal quantizer design are obtained. Also, a double-detector scheme is introduced in which a sensor level threshold detector is integrated into network level GLRT to improve the performance. The detection criteria of oracle and clairvoyant detectors are also derived. Simulation results show that with careful design of the threshold detector, the overall detection performance of double-detector scheme would be better than the sign-GLRT proposed in [1] and close to oracle and clairvoyant detectors. Also, the proposed detector is applied to spectrum sensing and the results are near the well known energy detector which uses the real valued data while the proposed detector only uses the sign of the data. |
| Tasks | |
| Published | 2016-07-02 |
| URL | http://arxiv.org/abs/1607.00494v1 |
| http://arxiv.org/pdf/1607.00494v1.pdf | |
| PWC | https://paperswithcode.com/paper/double-detector-for-sparse-signal-detection |
| Repo | |
| Framework | |
