Paper Group ANR 512
The subset-matched Jaccard index for evaluation of Segmentation for Plant Images. UTA-poly and UTA-splines: additive value functions with polynomial marginals. The polysemy of the words that children learn over time. Relevant sparse codes with variational information bottleneck. A Self-Paced Regularization Framework for Multi-Label Learning. Learni …
The subset-matched Jaccard index for evaluation of Segmentation for Plant Images
| Title | The subset-matched Jaccard index for evaluation of Segmentation for Plant Images |
| Authors | Jonathan Bell, Hannah M. Dee |
| Abstract | We describe a new measure for the evaluation of region level segmentation of objects, as applied to evaluating the accuracy of leaf-level segmentation of plant images. The proposed approach enforces the rule that a region (e.g. a leaf) in either the image being evaluated or the ground truth image evaluated against can be mapped to no more than one region in the other image. We call this measure the subset-matched Jaccard index. |
| Tasks | |
| Published | 2016-11-21 |
| URL | http://arxiv.org/abs/1611.06880v1 |
| http://arxiv.org/pdf/1611.06880v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-subset-matched-jaccard-index-for |
| Repo | |
| Framework | |
UTA-poly and UTA-splines: additive value functions with polynomial marginals
| Title | UTA-poly and UTA-splines: additive value functions with polynomial marginals |
| Authors | Olivier Sobrie, Nicolas Gillis, Vincent Mousseau, Marc Pirlot |
| Abstract | Additive utility function models are widely used in multiple criteria decision analysis. In such models, a numerical value is associated to each alternative involved in the decision problem. It is computed by aggregating the scores of the alternative on the different criteria of the decision problem. The score of an alternative is determined by a marginal value function that evolves monotonically as a function of the performance of the alternative on this criterion. Determining the shape of the marginals is not easy for a decision maker. It is easier for him/her to make statements such as “alternative $a$ is preferred to $b$”. In order to help the decision maker, UTA disaggregation procedures use linear programming to approximate the marginals by piecewise linear functions based only on such statements. In this paper, we propose to infer polynomials and splines instead of piecewise linear functions for the marginals. In this aim, we use semidefinite programming instead of linear programming. We illustrate this new elicitation method and present some experimental results. |
| Tasks | |
| Published | 2016-03-05 |
| URL | http://arxiv.org/abs/1603.02626v2 |
| http://arxiv.org/pdf/1603.02626v2.pdf | |
| PWC | https://paperswithcode.com/paper/uta-poly-and-uta-splines-additive-value |
| Repo | |
| Framework | |
The polysemy of the words that children learn over time
| Title | The polysemy of the words that children learn over time |
| Authors | Bernardino Casas, Neus Català, Ramon Ferrer-i-Cancho, Antoni Hernández-Fernández, Jaume Baixeries |
| Abstract | Here we study polysemy as a potential learning bias in vocabulary learning in children. Words of low polysemy could be preferred as they reduce the disambiguation effort for the listener. However, such preference could be a side-effect of another bias: the preference of children for nouns in combination with the lower polysemy of nouns with respect to other part-of-speech categories. Our results show that mean polysemy in children increases over time in two phases, i.e. a fast growth till the 31st month followed by a slower tendency towards adult speech. In contrast, this evolution is not found in adults interacting with children. This suggests that children have a preference for non-polysemous words in their early stages of vocabulary acquisition. Interestingly, the evolutionary pattern described above weakens when controlling for syntactic category (noun, verb, adjective or adverb) but it does not disappear completely, suggesting that it could result from acombination of a standalone bias for low polysemy and a preference for nouns. |
| Tasks | |
| Published | 2016-11-27 |
| URL | http://arxiv.org/abs/1611.08807v2 |
| http://arxiv.org/pdf/1611.08807v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-polysemy-of-the-words-that-children-learn |
| Repo | |
| Framework | |
Relevant sparse codes with variational information bottleneck
| Title | Relevant sparse codes with variational information bottleneck |
| Authors | Matthew Chalk, Olivier Marre, Gasper Tkacik |
| Abstract | In many applications, it is desirable to extract only the relevant aspects of data. A principled way to do this is the information bottleneck (IB) method, where one seeks a code that maximizes information about a ‘relevance’ variable, Y, while constraining the information encoded about the original data, X. Unfortunately however, the IB method is computationally demanding when data are high-dimensional and/or non-gaussian. Here we propose an approximate variational scheme for maximizing a lower bound on the IB objective, analogous to variational EM. Using this method, we derive an IB algorithm to recover features that are both relevant and sparse. Finally, we demonstrate how kernelized versions of the algorithm can be used to address a broad range of problems with non-linear relation between X and Y. |
| Tasks | |
| Published | 2016-05-24 |
| URL | http://arxiv.org/abs/1605.07332v2 |
| http://arxiv.org/pdf/1605.07332v2.pdf | |
| PWC | https://paperswithcode.com/paper/relevant-sparse-codes-with-variational |
| Repo | |
| Framework | |
A Self-Paced Regularization Framework for Multi-Label Learning
| Title | A Self-Paced Regularization Framework for Multi-Label Learning |
| Authors | Changsheng Li, Fan Wei, Junchi Yan, Weishan Dong, Qingshan Liu, Xiaoyu Zhang, Hongyuan Zha |
| Abstract | In this paper, we propose a novel multi-label learning framework, called Multi-Label Self-Paced Learning (MLSPL), in an attempt to incorporate the self-paced learning strategy into multi-label learning regime. In light of the benefits of adopting the easy-to-hard strategy proposed by self-paced learning, the devised MLSPL aims to learn multiple labels jointly by gradually including label learning tasks and instances into model training from the easy to the hard. We first introduce a self-paced function as a regularizer in the multi-label learning formulation, so as to simultaneously rank priorities of the label learning tasks and the instances in each learning iteration. Considering that different multi-label learning scenarios often need different self-paced schemes during optimization, we thus propose a general way to find the desired self-paced functions. Experimental results on three benchmark datasets suggest the state-of-the-art performance of our approach. |
| Tasks | Multi-Label Learning |
| Published | 2016-03-22 |
| URL | http://arxiv.org/abs/1603.06708v2 |
| http://arxiv.org/pdf/1603.06708v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-self-paced-regularization-framework-for |
| Repo | |
| Framework | |
Learning to Abstain from Binary Prediction
| Title | Learning to Abstain from Binary Prediction |
| Authors | Akshay Balsubramani |
| Abstract | A binary classifier capable of abstaining from making a label prediction has two goals in tension: minimizing errors, and avoiding abstaining unnecessarily often. In this work, we exactly characterize the best achievable tradeoff between these two goals in a general semi-supervised setting, given an ensemble of predictors of varying competence as well as unlabeled data on which we wish to predict or abstain. We give an algorithm for learning a classifier in this setting which trades off its errors with abstentions in a minimax optimal manner, is as efficient as linear learning and prediction, and is demonstrably practical. Our analysis extends to a large class of loss functions and other scenarios, including ensembles comprised of specialists that can themselves abstain. |
| Tasks | |
| Published | 2016-02-25 |
| URL | http://arxiv.org/abs/1602.08151v2 |
| http://arxiv.org/pdf/1602.08151v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-abstain-from-binary-prediction |
| Repo | |
| Framework | |
Cross-Modal Manifold Learning for Cross-modal Retrieval
| Title | Cross-Modal Manifold Learning for Cross-modal Retrieval |
| Authors | Sailesh Conjeti, Anees Kazi, Nassir Navab, Amin Katouzian |
| Abstract | This paper presents a new scalable algorithm for cross-modal similarity preserving retrieval in a learnt manifold space. Unlike existing approaches that compromise between preserving global and local geometries, the proposed technique respects both simultaneously during manifold alignment. The global topologies are maintained by recovering underlying mapping functions in the joint manifold space by deploying partially corresponding instances. The inter-, and intra-modality affinity matrices are then computed to reinforce original data skeleton using perturbed minimum spanning tree (pMST), and maximizing the affinity among similar cross-modal instances, respectively. The performance of proposed algorithm is evaluated upon two multimodal image datasets (coronary atherosclerosis histology and brain MRI) for two applications: classification, and regression. Our exhaustive validations and results demonstrate the superiority of our technique over comparative methods and its feasibility for improving computer-assisted diagnosis systems, where disease-specific complementary information shall be aggregated and interpreted across modalities to form the final decision. |
| Tasks | Cross-Modal Retrieval |
| Published | 2016-12-19 |
| URL | http://arxiv.org/abs/1612.06098v1 |
| http://arxiv.org/pdf/1612.06098v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-modal-manifold-learning-for-cross-modal |
| Repo | |
| Framework | |
Can Co-robots Learn to Teach?
| Title | Can Co-robots Learn to Teach? |
| Authors | Harshal Maske, Emily Kieson, Girish Chowdhary, Charles Abramson |
| Abstract | We explore beyond existing work on learning from demonstration by asking the question: Can robots learn to teach?, that is, can a robot autonomously learn an instructional policy from expert demonstration and use it to instruct or collaborate with humans in executing complex tasks in uncertain environments? In this paper we pursue a solution to this problem by leveraging the idea that humans often implicitly decompose a higher level task into several subgoals whose execution brings the task closer to completion. We propose Dirichlet process based non-parametric Inverse Reinforcement Learning (DPMIRL) approach for reward based unsupervised clustering of task space into subgoals. This approach is shown to capture the latent subgoals that a human teacher would have utilized to train a novice. The notion of action primitive is introduced as the means to communicate instruction policy to humans in the least complicated manner, and as a computationally efficient tool to segment demonstration data. We evaluate our approach through experiments on hydraulic actuated scaled model of an excavator and evaluate and compare different teaching strategies utilized by the robot. |
| Tasks | |
| Published | 2016-11-22 |
| URL | http://arxiv.org/abs/1611.07490v1 |
| http://arxiv.org/pdf/1611.07490v1.pdf | |
| PWC | https://paperswithcode.com/paper/can-co-robots-learn-to-teach |
| Repo | |
| Framework | |
Cast and Self Shadow Segmentation in Video Sequences using Interval based Eigen Value Representation
| Title | Cast and Self Shadow Segmentation in Video Sequences using Interval based Eigen Value Representation |
| Authors | Chandrajit M, Girisha R, Vasudev T, Ashok C B |
| Abstract | Tracking of motion objects in the surveillance videos is useful for the monitoring and analysis. The performance of the surveillance system will deteriorate when shadows are detected as moving objects. Therefore, shadow detection and elimination usually benefits the next stages. To overcome this issue, a method for detection and elimination of shadows is proposed. This paper presents a method for segmenting moving objects in video sequences based on determining the Euclidian distance between two pixels considering neighborhood values in temporal domain. Further, a method that segments cast and self shadows in video sequences by computing the Eigen values for the neighborhood of each pixel is proposed. The dual-map for cast and self shadow pixels is represented based on the interval of Eigen values. The proposed methods are tested on the benchmark IEEE CHANGE DETECTION 2014 dataset. |
| Tasks | Shadow Detection |
| Published | 2016-08-28 |
| URL | http://arxiv.org/abs/1608.07807v1 |
| http://arxiv.org/pdf/1608.07807v1.pdf | |
| PWC | https://paperswithcode.com/paper/cast-and-self-shadow-segmentation-in-video |
| Repo | |
| Framework | |
A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Examples
| Title | A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Examples |
| Authors | Beilun Wang, Ji Gao, Yanjun Qi |
| Abstract | Most machine learning classifiers, including deep neural networks, are vulnerable to adversarial examples. Such inputs are typically generated by adding small but purposeful modifications that lead to incorrect outputs while imperceptible to human eyes. The goal of this paper is not to introduce a single method, but to make theoretical steps towards fully understanding adversarial examples. By using concepts from topology, our theoretical analysis brings forth the key reasons why an adversarial example can fool a classifier ($f_1$) and adds its oracle ($f_2$, like human eyes) in such analysis. By investigating the topological relationship between two (pseudo)metric spaces corresponding to predictor $f_1$ and oracle $f_2$, we develop necessary and sufficient conditions that can determine if $f_1$ is always robust (strong-robust) against adversarial examples according to $f_2$. Interestingly our theorems indicate that just one unnecessary feature can make $f_1$ not strong-robust, and the right feature representation learning is the key to getting a classifier that is both accurate and strong-robust. |
| Tasks | Representation Learning |
| Published | 2016-12-01 |
| URL | http://arxiv.org/abs/1612.00334v12 |
| http://arxiv.org/pdf/1612.00334v12.pdf | |
| PWC | https://paperswithcode.com/paper/a-theoretical-framework-for-robustness-of |
| Repo | |
| Framework | |
Scene-driven Retrieval in Edited Videos using Aesthetic and Semantic Deep Features
| Title | Scene-driven Retrieval in Edited Videos using Aesthetic and Semantic Deep Features |
| Authors | Lorenzo Baraldi, Costantino Grana, Rita Cucchiara |
| Abstract | This paper presents a novel retrieval pipeline for video collections, which aims to retrieve the most significant parts of an edited video for a given query, and represent them with thumbnails which are at the same time semantically meaningful and aesthetically remarkable. Videos are first segmented into coherent and story-telling scenes, then a retrieval algorithm based on deep learning is proposed to retrieve the most significant scenes for a textual query. A ranking strategy based on deep features is finally used to tackle the problem of visualizing the best thumbnail. Qualitative and quantitative experiments are conducted on a collection of edited videos to demonstrate the effectiveness of our approach. |
| Tasks | |
| Published | 2016-04-09 |
| URL | http://arxiv.org/abs/1604.02546v1 |
| http://arxiv.org/pdf/1604.02546v1.pdf | |
| PWC | https://paperswithcode.com/paper/scene-driven-retrieval-in-edited-videos-using |
| Repo | |
| Framework | |
Algorithms for stochastic optimization with functional or expectation constraints
| Title | Algorithms for stochastic optimization with functional or expectation constraints |
| Authors | Guanghui Lan, Zhiqiang Zhou |
| Abstract | This paper considers the problem of minimizing an expectation function over a closed convex set, coupled with a {\color{black} functional or expectation} constraint on either decision variables or problem parameters. We first present a new stochastic approximation (SA) type algorithm, namely the cooperative SA (CSA), to handle problems with the constraint on devision variables. We show that this algorithm exhibits the optimal ${\cal O}(1/\epsilon^2)$ rate of convergence, in terms of both optimality gap and constraint violation, when the objective and constraint functions are generally convex, where $\epsilon$ denotes the optimality gap and infeasibility. Moreover, we show that this rate of convergence can be improved to ${\cal O}(1/\epsilon)$ if the objective and constraint functions are strongly convex. We then present a variant of CSA, namely the cooperative stochastic parameter approximation (CSPA) algorithm, to deal with the situation when the constraint is defined over problem parameters and show that it exhibits similar optimal rate of convergence to CSA. It is worth noting that CSA and CSPA are primal methods which do not require the iterations on the dual space and/or the estimation on the size of the dual variables. To the best of our knowledge, this is the first time that such optimal SA methods for solving functional or expectation constrained stochastic optimization are presented in the literature. |
| Tasks | Stochastic Optimization |
| Published | 2016-04-13 |
| URL | https://arxiv.org/abs/1604.03887v7 |
| https://arxiv.org/pdf/1604.03887v7.pdf | |
| PWC | https://paperswithcode.com/paper/algorithms-for-stochastic-optimization-with |
| Repo | |
| Framework | |
Analysis of the noise in back-projection light field acquisition and its optimization
| Title | Analysis of the noise in back-projection light field acquisition and its optimization |
| Authors | Ni Chen, Zhenbo Ren, Dayan Li, Edmund Y. Lam, Guohai Situ |
| Abstract | Light field reconstruction from images captured by focal plane sweeping can achieve high lateral resolution comparable to the modern camera sensor. This is impossible for the conventional micro-lenslet based light field capture systems. However, the severe defocus noise and the low depth resolution limit its applications. In this paper, we analyze the defocus noise and the depth resolution in the focal plane sweeping based light field reconstruction technique, and propose a method to reduce the defocus noise and improve the depth resolution. Both numerical and experimental results verify the proposed method. |
| Tasks | |
| Published | 2016-12-30 |
| URL | http://arxiv.org/abs/1701.05084v1 |
| http://arxiv.org/pdf/1701.05084v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-the-noise-in-back-projection |
| Repo | |
| Framework | |
Procedural urban environments for FPS games
| Title | Procedural urban environments for FPS games |
| Authors | Jan Kruse, Ricardo Sosa, Andy M. Connor |
| Abstract | This paper presents a novel approach to procedural generation of urban maps for First Person Shooter (FPS) games. A multi-agent evolutionary system is employed to place streets, buildings and other items inside the Unity3D game engine, resulting in playable video game levels. A computational agent is trained using machine learning techniques to capture the intent of the game designer as part of the multi-agent system, and to enable a semi-automated aesthetic selection for the underlying genetic algorithm. |
| Tasks | FPS Games |
| Published | 2016-04-20 |
| URL | http://arxiv.org/abs/1604.05791v1 |
| http://arxiv.org/pdf/1604.05791v1.pdf | |
| PWC | https://paperswithcode.com/paper/procedural-urban-environments-for-fps-games |
| Repo | |
| Framework | |
A Novel Information Theoretic Framework for Finding Semantic Similarity in WordNet
| Title | A Novel Information Theoretic Framework for Finding Semantic Similarity in WordNet |
| Authors | Abhijit Adhikari, Shivang Singh, Deepjyoti Mondal, Biswanath Dutta, Animesh Dutta |
| Abstract | Information content (IC) based measures for finding semantic similarity is gaining preferences day by day. Semantics of concepts can be highly characterized by information theory. The conventional way for calculating IC is based on the probability of appearance of concepts in corpora. Due to data sparseness and corpora dependency issues of those conventional approaches, a new corpora independent intrinsic IC calculation measure has evolved. In this paper, we mainly focus on such intrinsic IC model and several topological aspects of the underlying ontology. Accuracy of intrinsic IC calculation and semantic similarity measure rely on these aspects deeply. Based on these analysis we propose an information theoretic framework which comprises an intrinsic IC calculator and a semantic similarity model. Our approach is compared with state of the art semantic similarity measures based on corpora dependent IC calculation as well as intrinsic IC based methods using several benchmark data set. We also compare our model with the related Edge based, Feature based and Distributional approaches. Experimental results show that our intrinsic IC model gives high correlation value when applied to different semantic similarity models. Our proposed semantic similarity model also achieves significant results when embedded with some state of the art IC models including ours. |
| Tasks | Semantic Similarity, Semantic Textual Similarity |
| Published | 2016-07-19 |
| URL | http://arxiv.org/abs/1607.05422v1 |
| http://arxiv.org/pdf/1607.05422v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-information-theoretic-framework-for |
| Repo | |
| Framework | |
