Paper Group ANR 517
Herding Generalizes Diverse M -Best Solutions. Deep unsupervised learning through spatial contrasting. WEPSAM: Weakly Pre-Learnt Saliency Model. A heuristic algorithm for a single vehicle static bike sharing rebalancing problem. Deep Tracking on the Move: Learning to Track the World from a Moving Vehicle using Recurrent Neural Networks. deepTarget: …
Herding Generalizes Diverse M -Best Solutions
| Title | Herding Generalizes Diverse M -Best Solutions |
| Authors | Ece Ozkan, Gemma Roig, Orcun Goksel, Xavier Boix |
| Abstract | We show that the algorithm to extract diverse M -solutions from a Conditional Random Field (called divMbest [1]) takes exactly the form of a Herding procedure [2], i.e. a deterministic dynamical system that produces a sequence of hypotheses that respect a set of observed moment constraints. This generalization enables us to invoke properties of Herding that show that divMbest enforces implausible constraints which may yield wrong assumptions for some problem settings. Our experiments in semantic segmentation demonstrate that seeing divMbest as an instance of Herding leads to better alternatives for the implausible constraints of divMbest. |
| Tasks | Semantic Segmentation |
| Published | 2016-11-14 |
| URL | http://arxiv.org/abs/1611.04353v2 |
| http://arxiv.org/pdf/1611.04353v2.pdf | |
| PWC | https://paperswithcode.com/paper/herding-generalizes-diverse-m-best-solutions |
| Repo | |
| Framework | |
Deep unsupervised learning through spatial contrasting
| Title | Deep unsupervised learning through spatial contrasting |
| Authors | Elad Hoffer, Itay Hubara, Nir Ailon |
| Abstract | Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have been made to use unlabeled data to improve model performance by applying unsupervised techniques. These attempts require different architectures and training methods. In this work we present a novel approach for unsupervised training of Convolutional networks that is based on contrasting between spatial regions within images. This criterion can be employed within conventional neural networks and trained using standard techniques such as SGD and back-propagation, thus complementing supervised methods. |
| Tasks | |
| Published | 2016-10-02 |
| URL | http://arxiv.org/abs/1610.00243v2 |
| http://arxiv.org/pdf/1610.00243v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-unsupervised-learning-through-spatial |
| Repo | |
| Framework | |
WEPSAM: Weakly Pre-Learnt Saliency Model
| Title | WEPSAM: Weakly Pre-Learnt Saliency Model |
| Authors | Avisek Lahiri, Sourya Roy, Anirban Santara, Pabitra Mitra, Prabir Kumar Biswas |
| Abstract | Visual saliency detection tries to mimic human vision psychology which concentrates on sparse, important areas in natural image. Saliency prediction research has been traditionally based on low level features such as contrast, edge, etc. Recent thrust in saliency prediction research is to learn high level semantics using ground truth eye fixation datasets. In this paper we present, WEPSAM : Weakly Pre-Learnt Saliency Model as a pioneering effort of using domain specific pre-learing on ImageNet for saliency prediction using a light weight CNN architecture. The paper proposes a two step hierarchical learning, in which the first step is to develop a framework for weakly pre-training on a large scale dataset such as ImageNet which is void of human eye fixation maps. The second step refines the pre-trained model on a limited set of ground truth fixations. Analysis of loss on iSUN and SALICON datasets reveal that pre-trained network converges much faster compared to randomly initialized network. WEPSAM also outperforms some recent state-of-the-art saliency prediction models on the challenging MIT300 dataset. |
| Tasks | Saliency Detection, Saliency Prediction |
| Published | 2016-05-03 |
| URL | http://arxiv.org/abs/1605.01101v1 |
| http://arxiv.org/pdf/1605.01101v1.pdf | |
| PWC | https://paperswithcode.com/paper/wepsam-weakly-pre-learnt-saliency-model |
| Repo | |
| Framework | |
A heuristic algorithm for a single vehicle static bike sharing rebalancing problem
| Title | A heuristic algorithm for a single vehicle static bike sharing rebalancing problem |
| Authors | Fábio Cruz, Anand Subramanian, Bruno P. Bruck, Manuel Iori |
| Abstract | The static bike rebalancing problem (SBRP) concerns the task of repositioning bikes among stations in self-service bike-sharing systems. This problem can be seen as a variant of the one-commodity pickup and delivery vehicle routing problem, where multiple visits are allowed to be performed at each station, i.e., the demand of a station is allowed to be split. Moreover, a vehicle may temporarily drop its load at a station, leaving it in excess or, alternatively, collect more bikes from a station (even all of them), thus leaving it in default. Both cases require further visits in order to meet the actual demands of such station. This paper deals with a particular case of the SBRP, in which only a single vehicle is available and the objective is to find a least-cost route that meets the demand of all stations and does not violate the minimum (zero) and maximum (vehicle capacity) load limits along the tour. Therefore, the number of bikes to be collected or delivered at each station should be appropriately determined in order to respect such constraints. We propose an iterated local search (ILS) based heuristic to solve the problem. The ILS algorithm was tested on 980 benchmark instances from the literature and the results obtained are quite competitive when compared to other existing methods. Moreover, our heuristic was capable of finding most of the known optimal solutions and also of improving the results on a number of open instances. |
| Tasks | |
| Published | 2016-05-02 |
| URL | http://arxiv.org/abs/1605.00702v2 |
| http://arxiv.org/pdf/1605.00702v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-heuristic-algorithm-for-a-single-vehicle |
| Repo | |
| Framework | |
Deep Tracking on the Move: Learning to Track the World from a Moving Vehicle using Recurrent Neural Networks
| Title | Deep Tracking on the Move: Learning to Track the World from a Moving Vehicle using Recurrent Neural Networks |
| Authors | Julie Dequaire, Dushyant Rao, Peter Ondruska, Dominic Wang, Ingmar Posner |
| Abstract | This paper presents an end-to-end approach for tracking static and dynamic objects for an autonomous vehicle driving through crowded urban environments. Unlike traditional approaches to tracking, this method is learned end-to-end, and is able to directly predict a full unoccluded occupancy grid map from raw laser input data. Inspired by the recently presented DeepTracking approach [Ondruska, 2016], we employ a recurrent neural network (RNN) to capture the temporal evolution of the state of the environment, and propose to use Spatial Transformer modules to exploit estimates of the egomotion of the vehicle. Our results demonstrate the ability to track a range of objects, including cars, buses, pedestrians, and cyclists through occlusion, from both moving and stationary platforms, using a single learned model. Experimental results demonstrate that the model can also predict the future states of objects from current inputs, with greater accuracy than previous work. |
| Tasks | |
| Published | 2016-09-29 |
| URL | http://arxiv.org/abs/1609.09365v3 |
| http://arxiv.org/pdf/1609.09365v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-tracking-on-the-move-learning-to-track |
| Repo | |
| Framework | |
deepTarget: End-to-end Learning Framework for microRNA Target Prediction using Deep Recurrent Neural Networks
| Title | deepTarget: End-to-end Learning Framework for microRNA Target Prediction using Deep Recurrent Neural Networks |
| Authors | Byunghan Lee, Junghwan Baek, Seunghyun Park, Sungroh Yoon |
| Abstract | MicroRNAs (miRNAs) are short sequences of ribonucleic acids that control the expression of target messenger RNAs (mRNAs) by binding them. Robust prediction of miRNA-mRNA pairs is of utmost importance in deciphering gene regulations but has been challenging because of high false positive rates, despite a deluge of computational tools that normally require laborious manual feature extraction. This paper presents an end-to-end machine learning framework for miRNA target prediction. Leveraged by deep recurrent neural networks-based auto-encoding and sequence-sequence interaction learning, our approach not only delivers an unprecedented level of accuracy but also eliminates the need for manual feature extraction. The performance gap between the proposed method and existing alternatives is substantial (over 25% increase in F-measure), and deepTarget delivers a quantum leap in the long-standing challenge of robust miRNA target prediction. |
| Tasks | |
| Published | 2016-03-30 |
| URL | http://arxiv.org/abs/1603.09123v2 |
| http://arxiv.org/pdf/1603.09123v2.pdf | |
| PWC | https://paperswithcode.com/paper/deeptarget-end-to-end-learning-framework-for |
| Repo | |
| Framework | |
Opinion Mining in Online Reviews About Distance Education Programs
| Title | Opinion Mining in Online Reviews About Distance Education Programs |
| Authors | Janik Jaskolski, Fabian Siegberg, Thomas Tibroni, Philipp Cimiano, Roman Klinger |
| Abstract | The popularity of distance education programs is increasing at a fast pace. En par with this development, online communication in fora, social media and reviewing platforms between students is increasing as well. Exploiting this information to support fellow students or institutions requires to extract the relevant opinions in order to automatically generate reports providing an overview of pros and cons of different distance education programs. We report on an experiment involving distance education experts with the goal to develop a dataset of reviews annotated with relevant categories and aspects in each category discussed in the specific review together with an indication of the sentiment. Based on this experiment, we present an approach to extract general categories and specific aspects under discussion in a review together with their sentiment. We frame this task as a multi-label hierarchical text classification problem and empirically investigate the performance of different classification architectures to couple the prediction of a category with the prediction of particular aspects in this category. We evaluate different architectures and show that a hierarchical approach leads to superior results in comparison to a flat model which makes decisions independently. |
| Tasks | Opinion Mining, Text Classification |
| Published | 2016-07-21 |
| URL | http://arxiv.org/abs/1607.06299v1 |
| http://arxiv.org/pdf/1607.06299v1.pdf | |
| PWC | https://paperswithcode.com/paper/opinion-mining-in-online-reviews-about |
| Repo | |
| Framework | |
Deep Learning for Saliency Prediction in Natural Video
| Title | Deep Learning for Saliency Prediction in Natural Video |
| Authors | Souad Chaabouni, Jenny Benois-Pineau, Ofer Hadar, Chokri Ben Amar |
| Abstract | The purpose of this paper is the detection of salient areas in natural video by using the new deep learning techniques. Salient patches in video frames are predicted first. Then the predicted visual fixation maps are built upon them. We design the deep architecture on the basis of CaffeNet implemented with Caffe toolkit. We show that changing the way of data selection for optimisation of network parameters, we can save computation cost up to 12 times. We extend deep learning approaches for saliency prediction in still images with RGB values to specificity of video using the sensitivity of the human visual system to residual motion. Furthermore, we complete primary colour pixel values by contrast features proposed in classical visual attention prediction models. The experiments are conducted on two publicly available datasets. The first is IRCCYN video database containing 31 videos with an overall amount of 7300 frames and eye fixations of 37 subjects. The second one is HOLLYWOOD2 provided 2517 movie clips with the eye fixations of 19 subjects. On IRCYYN dataset, the accuracy obtained is of 89.51%. On HOLLYWOOD2 dataset, results in prediction of saliency of patches show the improvement up to 2% with regard to RGB use only. The resulting accuracy of 76, 6% is obtained. The AUC metric in comparison of predicted saliency maps with visual fixation maps shows the increase up to 16% on a sample of video clips from this dataset. |
| Tasks | Saliency Prediction |
| Published | 2016-04-27 |
| URL | http://arxiv.org/abs/1604.08010v1 |
| http://arxiv.org/pdf/1604.08010v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-saliency-prediction-in |
| Repo | |
| Framework | |
Confidence-Weighted Bipartite Ranking
| Title | Confidence-Weighted Bipartite Ranking |
| Authors | Majdi Khalid, Indrakshi Ray, Hamidreza Chitsaz |
| Abstract | Bipartite ranking is a fundamental machine learning and data mining problem. It commonly concerns the maximization of the AUC metric. Recently, a number of studies have proposed online bipartite ranking algorithms to learn from massive streams of class-imbalanced data. These methods suggest both linear and kernel-based bipartite ranking algorithms based on first and second-order online learning. Unlike kernelized ranker, linear ranker is more scalable learning algorithm. The existing linear online bipartite ranking algorithms lack either handling non-separable data or constructing adaptive large margin. These limitations yield unreliable bipartite ranking performance. In this work, we propose a linear online confidence-weighted bipartite ranking algorithm (CBR) that adopts soft confidence-weighted learning. The proposed algorithm leverages the same properties of soft confidence-weighted learning in a framework for bipartite ranking. We also develop a diagonal variation of the proposed confidence-weighted bipartite ranking algorithm to deal with high-dimensional data by maintaining only the diagonal elements of the covariance matrix. We empirically evaluate the effectiveness of the proposed algorithms on several benchmark and high-dimensional datasets. The experimental results validate the reliability of the proposed algorithms. The results also show that our algorithms outperform or are at least comparable to the competing online AUC maximization methods. |
| Tasks | |
| Published | 2016-07-04 |
| URL | http://arxiv.org/abs/1607.00847v9 |
| http://arxiv.org/pdf/1607.00847v9.pdf | |
| PWC | https://paperswithcode.com/paper/confidence-weighted-bipartite-ranking |
| Repo | |
| Framework | |
Visual saliency detection: a Kalman filter based approach
| Title | Visual saliency detection: a Kalman filter based approach |
| Authors | Sourya Roy, Pabitra Mitra |
| Abstract | In this paper we propose a Kalman filter aided saliency detection model which is based on the conjecture that salient regions are considerably different from our “visual expectation” or they are “visually surprising” in nature. In this work, we have structured our model with an immediate objective to predict saliency in static images. However, the proposed model can be easily extended for space-time saliency prediction. Our approach was evaluated using two publicly available benchmark data sets and results have been compared with other existing saliency models. The results clearly illustrate the superior performance of the proposed model over other approaches. |
| Tasks | Saliency Detection, Saliency Prediction |
| Published | 2016-04-17 |
| URL | http://arxiv.org/abs/1604.04825v1 |
| http://arxiv.org/pdf/1604.04825v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-saliency-detection-a-kalman-filter |
| Repo | |
| Framework | |
Adaptive Task Assignment in Online Learning Environments
| Title | Adaptive Task Assignment in Online Learning Environments |
| Authors | Per-Arne Andersen, Christian Kråkevik, Morten Goodwin, Anis Yazidi |
| Abstract | With the increasing popularity of online learning, intelligent tutoring systems are regaining increased attention. In this paper, we introduce adaptive algorithms for personalized assignment of learning tasks to student so that to improve his performance in online learning environments. As main contribution of this paper, we propose a a novel Skill-Based Task Selector (SBTS) algorithm which is able to approximate a student’s skill level based on his performance and consequently suggest adequate assignments. The SBTS is inspired by the class of multi-armed bandit algorithms. However, in contrast to standard multi-armed bandit approaches, the SBTS aims at acquiring two criteria related to student learning, namely: which topics should the student work on, and what level of difficulty should the task be. The SBTS centers on innovative reward and punishment schemes in a task and skill matrix based on the student behaviour. To verify the algorithm, the complex student behaviour is modelled using a neighbour node selection approach based on empirical estimations of a students learning curve. The algorithm is evaluated with a practical scenario from a basic java programming course. The SBTS is able to quickly and accurately adapt to the composite student competency — even with a multitude of student models. |
| Tasks | |
| Published | 2016-06-23 |
| URL | http://arxiv.org/abs/1606.07233v1 |
| http://arxiv.org/pdf/1606.07233v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-task-assignment-in-online-learning |
| Repo | |
| Framework | |
The Effect of Distortions on the Prediction of Visual Attention
| Title | The Effect of Distortions on the Prediction of Visual Attention |
| Authors | Milind S. Gide, Samuel F. Dodge, Lina J. Karam |
| Abstract | Existing saliency models have been designed and evaluated for predicting the saliency in distortion-free images. However, in practice, the image quality is affected by a host of factors at several stages of the image processing pipeline such as acquisition, compression and transmission. Several studies have explored the effect of distortion on human visual attention; however, none of them have considered the performance of visual saliency models in the presence of distortion. Furthermore, given that one potential application of visual saliency prediction is to aid pooling of objective visual quality metrics, it is important to compare the performance of existing saliency models on distorted images. In this paper, we evaluate several state-of-the-art visual attention models over different databases consisting of distorted images with various types of distortions such as blur, noise and compression with varying levels of distortion severity. This paper also introduces new improved performance evaluation metrics that are shown to overcome shortcomings in existing performance metrics. We find that the performance of most models improves with moderate and high levels of distortions as compared to the near distortion-free case. In addition, model performance is also found to decrease with an increase in image complexity. |
| Tasks | Saliency Prediction |
| Published | 2016-04-13 |
| URL | http://arxiv.org/abs/1604.03882v1 |
| http://arxiv.org/pdf/1604.03882v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-effect-of-distortions-on-the-prediction |
| Repo | |
| Framework | |
A Novel Method to Study Bottom-up Visual Saliency and its Neural Mechanism
| Title | A Novel Method to Study Bottom-up Visual Saliency and its Neural Mechanism |
| Authors | Cheng Chen, Xilin Zhang, Yizhou Wang, Fang Fang |
| Abstract | In this study, we propose a novel method to measure bottom-up saliency maps of natural images. In order to eliminate the influence of top-down signals, backward masking is used to make stimuli (natural images) subjectively invisible to subjects, however, the bottom-up saliency can still orient the subjects attention. To measure this orientation/attention effect, we adopt the cueing effect paradigm by deploying discrimination tasks at each location of an image, and measure the discrimination performance variation across the image as the attentional effect of the bottom-up saliency. Such attentional effects are combined to construct a final bottomup saliency map. Based on the proposed method, we introduce a new bottom-up saliency map dataset of natural images to benchmark computational models. We compare several state-of-the-art saliency models on the dataset. Moreover, the proposed paradigm is applied to investigate the neural basis of the bottom-up visual saliency map by analyzing psychophysical and fMRI experimental results. Our findings suggest that the bottom-up saliency maps of natural images are constructed in V1. It provides a strong scientific evidence to resolve the long standing dispute in neuroscience about where the bottom-up saliency map is constructed in human brain. |
| Tasks | |
| Published | 2016-04-13 |
| URL | http://arxiv.org/abs/1604.08426v1 |
| http://arxiv.org/pdf/1604.08426v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-method-to-study-bottom-up-visual |
| Repo | |
| Framework | |
Intrinsic normalization and extrinsic denormalization of formant data of vowels
| Title | Intrinsic normalization and extrinsic denormalization of formant data of vowels |
| Authors | T. V. Ananthapadmanabha, A. G. Ramakrishnan |
| Abstract | Using a known speaker-intrinsic normalization procedure, formant data are scaled by the reciprocal of the geometric mean of the first three formant frequencies. This reduces the influence of the talker but results in a distorted vowel space. The proposed speaker-extrinsic procedure re-scales the normalized values by the mean formant values of vowels. When tested on the formant data of vowels published by Peterson and Barney, the combined approach leads to well separated clusters by reducing the spread due to talkers. The proposed procedure performs better than two top-ranked normalization procedures based on the accuracy of vowel classification as the objective measure. |
| Tasks | Vowel Classification |
| Published | 2016-09-16 |
| URL | http://arxiv.org/abs/1609.05104v2 |
| http://arxiv.org/pdf/1609.05104v2.pdf | |
| PWC | https://paperswithcode.com/paper/intrinsic-normalization-and-extrinsic |
| Repo | |
| Framework | |
Max-Information, Differential Privacy, and Post-Selection Hypothesis Testing
| Title | Max-Information, Differential Privacy, and Post-Selection Hypothesis Testing |
| Authors | Ryan Rogers, Aaron Roth, Adam Smith, Om Thakkar |
| Abstract | In this paper, we initiate a principled study of how the generalization properties of approximate differential privacy can be used to perform adaptive hypothesis testing, while giving statistically valid $p$-value corrections. We do this by observing that the guarantees of algorithms with bounded approximate max-information are sufficient to correct the $p$-values of adaptively chosen hypotheses, and then by proving that algorithms that satisfy $(\epsilon,\delta)$-differential privacy have bounded approximate max information when their inputs are drawn from a product distribution. This substantially extends the known connection between differential privacy and max-information, which previously was only known to hold for (pure) $(\epsilon,0)$-differential privacy. It also extends our understanding of max-information as a partially unifying measure controlling the generalization properties of adaptive data analyses. We also show a lower bound, proving that (despite the strong composition properties of max-information), when data is drawn from a product distribution, $(\epsilon,\delta)$-differentially private algorithms can come first in a composition with other algorithms satisfying max-information bounds, but not necessarily second if the composition is required to itself satisfy a nontrivial max-information bound. This, in particular, implies that the connection between $(\epsilon,\delta)$-differential privacy and max-information holds only for inputs drawn from product distributions, unlike the connection between $(\epsilon,0)$-differential privacy and max-information. |
| Tasks | |
| Published | 2016-04-13 |
| URL | http://arxiv.org/abs/1604.03924v2 |
| http://arxiv.org/pdf/1604.03924v2.pdf | |
| PWC | https://paperswithcode.com/paper/max-information-differential-privacy-and-post |
| Repo | |
| Framework | |
