Paper Group ANR 576
Agents and Devices: A Relative Definition of Agency. Periocular Recognition Using CNN Features Off-the-Shelf. Deep Neural Network for Analysis of DNA Methylation Data. Runtime Analysis for Self-adaptive Mutation Rates. Learned Neural Iterative Decoding for Lossy Image Compression Systems. Now you see me: evaluating performance in long-term visual t …
Agents and Devices: A Relative Definition of Agency
| Title | Agents and Devices: A Relative Definition of Agency |
| Authors | Laurent Orseau, Simon McGregor McGill, Shane Legg |
| Abstract | According to Dennett, the same system may be described using a physical' (mechanical) explanatory stance, or using an intentional’ (belief- and goal-based) explanatory stance. Humans tend to find the physical stance more helpful for certain systems, such as planets orbiting a star, and the intentional stance for others, such as living animals. We define a formal counterpart of physical and intentional stances within computational theory: a description of a system as either a device, or an agent, with the key difference being that devices' are directly described in terms of an input-output mapping, while agents’ are described in terms of the function they optimise. Bayes’ rule can then be applied to calculate the subjective probability of a system being a device or an agent, based only on its behaviour. We illustrate this using the trajectories of an object in a toy grid-world domain. |
| Tasks | |
| Published | 2018-05-31 |
| URL | http://arxiv.org/abs/1805.12387v1 |
| http://arxiv.org/pdf/1805.12387v1.pdf | |
| PWC | https://paperswithcode.com/paper/agents-and-devices-a-relative-definition-of |
| Repo | |
| Framework | |
Periocular Recognition Using CNN Features Off-the-Shelf
| Title | Periocular Recognition Using CNN Features Off-the-Shelf |
| Authors | Kevin Hernandez-Diaz, Fernando Alonso-Fernandez, Josef Bigun |
| Abstract | Periocular refers to the region around the eye, including sclera, eyelids, lashes, brows and skin. With a surprisingly high discrimination ability, it is the ocular modality requiring the least constrained acquisition. Here, we apply existing pre-trained architectures, proposed in the context of the ImageNet Large Scale Visual Recognition Challenge, to the task of periocular recognition. These have proven to be very successful for many other computer vision tasks apart from the detection and classification tasks for which they were designed. Experiments are done with a database of periocular images captured with a digital camera. We demonstrate that these off-the-shelf CNN features can effectively recognize individuals based on periocular images, despite being trained to classify generic objects. Compared against reference periocular features, they show an EER reduction of up to ~40%, with the fusion of CNN and traditional features providing additional improvements. |
| Tasks | Object Recognition |
| Published | 2018-09-17 |
| URL | http://arxiv.org/abs/1809.06157v1 |
| http://arxiv.org/pdf/1809.06157v1.pdf | |
| PWC | https://paperswithcode.com/paper/periocular-recognition-using-cnn-features-off |
| Repo | |
| Framework | |
Deep Neural Network for Analysis of DNA Methylation Data
| Title | Deep Neural Network for Analysis of DNA Methylation Data |
| Authors | Hong Yu, Zhanyu Ma |
| Abstract | Many researches demonstrated that the DNA methylation, which occurs in the context of a CpG, has strong correlation with diseases, including cancer. There is a strong interest in analyzing the DNA methylation data to find how to distinguish different subtypes of the tumor. However, the conventional statistical methods are not suitable for analyzing the highly dimensional DNA methylation data with bounded support. In order to explicitly capture the properties of the data, we design a deep neural network, which composes of several stacked binary restricted Boltzmann machines, to learn the low dimensional deep features of the DNA methylation data. Experiments show these features perform best in breast cancer DNA methylation data cluster analysis, comparing with some state-of-the-art methods. |
| Tasks | |
| Published | 2018-08-02 |
| URL | https://arxiv.org/abs/1808.01359v2 |
| https://arxiv.org/pdf/1808.01359v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-neural-network-for-analysis-of-dna |
| Repo | |
| Framework | |
Runtime Analysis for Self-adaptive Mutation Rates
| Title | Runtime Analysis for Self-adaptive Mutation Rates |
| Authors | Benjamin Doerr, Carsten Witt, Jing Yang |
| Abstract | We propose and analyze a self-adaptive version of the $(1,\lambda)$ evolutionary algorithm in which the current mutation rate is part of the individual and thus also subject to mutation. A rigorous runtime analysis on the OneMax benchmark function reveals that a simple local mutation scheme for the rate leads to an expected optimization time (number of fitness evaluations) of $O(n\lambda/\log\lambda+n\log n)$ when $\lambda$ is at least $C \ln n$ for some constant $C > 0$. For all values of $\lambda \ge C \ln n$, this performance is asymptotically best possible among all $\lambda$-parallel mutation-based unbiased black-box algorithms. Our result shows that self-adaptation in evolutionary computation can find complex optimal parameter settings on the fly. At the same time, it proves that a relatively complicated self-adjusting scheme for the mutation rate proposed by Doerr, Gie{\ss}en, Witt, and Yang~(GECCO~2017) can be replaced by our simple endogenous scheme. On the technical side, the paper contributes new tools for the analysis of two-dimensional drift processes arising in the analysis of dynamic parameter choices in EAs, including bounds on occupation probabilities in processes with non-constant drift. |
| Tasks | |
| Published | 2018-11-30 |
| URL | http://arxiv.org/abs/1811.12824v1 |
| http://arxiv.org/pdf/1811.12824v1.pdf | |
| PWC | https://paperswithcode.com/paper/runtime-analysis-for-self-adaptive-mutation |
| Repo | |
| Framework | |
Learned Neural Iterative Decoding for Lossy Image Compression Systems
| Title | Learned Neural Iterative Decoding for Lossy Image Compression Systems |
| Authors | Alexander G. Ororbia, Ankur Mali, Jian Wu, Scott O’Connell, David Miller, C. Lee Giles |
| Abstract | For lossy image compression systems, we develop an algorithm, iterative refinement, to improve the decoder’s reconstruction compared to standard decoding techniques. Specifically, we propose a recurrent neural network approach for nonlinear, iterative decoding. Our decoder, which works with any encoder, employs self-connected memory units that make use of causal and non-causal spatial context information to progressively reduce reconstruction error over a fixed number of steps. We experiment with variants of our estimator and find that iterative refinement consistently creates lower distortion images of higher perceptual quality compared to other approaches. Specifically, on the Kodak Lossless True Color Image Suite, we observe as much as a 0.871 decibel (dB) gain over JPEG, a 1.095 dB gain over JPEG 2000, and a 0.971 dB gain over a competitive neural model. |
| Tasks | Image Compression |
| Published | 2018-03-15 |
| URL | http://arxiv.org/abs/1803.05863v3 |
| http://arxiv.org/pdf/1803.05863v3.pdf | |
| PWC | https://paperswithcode.com/paper/learned-neural-iterative-decoding-for-lossy |
| Repo | |
| Framework | |
Now you see me: evaluating performance in long-term visual tracking
| Title | Now you see me: evaluating performance in long-term visual tracking |
| Authors | Alan Lukežič, Luka Čehovin Zajc, Tomáš Vojíř, Jiří Matas, Matej Kristan |
| Abstract | We propose a new long-term tracking performance evaluation methodology and present a new challenging dataset of carefully selected sequences with many target disappearances. We perform an extensive evaluation of six long-term and nine short-term state-of-the-art trackers, using new performance measures, suitable for evaluating long-term tracking - tracking precision, recall and F-score. The evaluation shows that a good model update strategy and the capability of image-wide re-detection are critical for long-term tracking performance. We integrated the methodology in the VOT toolkit to automate experimental analysis and benchmarking and to facilitate the development of long-term trackers. |
| Tasks | Visual Tracking |
| Published | 2018-04-19 |
| URL | http://arxiv.org/abs/1804.07056v1 |
| http://arxiv.org/pdf/1804.07056v1.pdf | |
| PWC | https://paperswithcode.com/paper/now-you-see-me-evaluating-performance-in-long |
| Repo | |
| Framework | |
Neural Networks and Quantifier Conservativity: Does Data Distribution Affect Learnability?
| Title | Neural Networks and Quantifier Conservativity: Does Data Distribution Affect Learnability? |
| Authors | Vishwali Mhasawade, Ildikó Emese Szabó, Melanie Tosik, Sheng-Fu Wang |
| Abstract | All known natural language determiners are conservative. Psycholinguistic experiments indicate that children exhibit a corresponding learnability bias when faced with the task of learning new determiners. However, recent work indicates that this bias towards conservativity is not observed during the training stage of artificial neural networks. In this work, we investigate whether the learnability bias exhibited by children is in part due to the distribution of quantifiers in natural language. We share results of five experiments, contrasted by the distribution of conservative vs. non-conservative determiners in the training data. We demonstrate that the aquisitional issues with non-conservative quantifiers can not be explained by the distribution of natural language data, which favors conservative quantifiers. This finding indicates that the bias in language acquisition data might be innate or representational. |
| Tasks | Language Acquisition |
| Published | 2018-09-15 |
| URL | http://arxiv.org/abs/1809.05733v1 |
| http://arxiv.org/pdf/1809.05733v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-networks-and-quantifier-conservativity |
| Repo | |
| Framework | |
Temporal Coherent and Graph Optimized Manifold Ranking for Visual Tracking
| Title | Temporal Coherent and Graph Optimized Manifold Ranking for Visual Tracking |
| Authors | Bo Jiang, Doudou Lin, Bin Luo, Jin Tang |
| Abstract | Recently, weighted patch representation has been widely studied for alleviating the impact of background information included in bounding box to improve visual tracking results. However, existing weighted patch representation models generally exploit spatial structure information among patches in each frame separately which ignore (1) unary featureof each patch and (2) temporal correlation among patches in different frames. To address this problem, we propose a novel unified temporal coherence and graph optimized ranking model for weighted patch representation in visual tracking problem. There are three main contributions of this paper. First, we propose to employ a flexible graph ranking for patch weight computation which exploits both structure information among patches and unary feature of each patch simultaneously. Second, we propose a new more discriminative ranking model by further considering the temporal correlation among patches in different frames. Third, a neighborhood preserved, low-rank graph is learned and incorporated to build a unified optimized ranking model. Experiments on two benchmark datasets show the benefits of our model. |
| Tasks | Graph Ranking, Visual Tracking |
| Published | 2018-04-17 |
| URL | http://arxiv.org/abs/1804.06253v1 |
| http://arxiv.org/pdf/1804.06253v1.pdf | |
| PWC | https://paperswithcode.com/paper/temporal-coherent-and-graph-optimized |
| Repo | |
| Framework | |
Structured Output Learning with Abstention: Application to Accurate Opinion Prediction
| Title | Structured Output Learning with Abstention: Application to Accurate Opinion Prediction |
| Authors | Alexandre Garcia, Slim Essid, Chloé Clavel, Florence d’Alché-Buc |
| Abstract | Motivated by Supervised Opinion Analysis, we propose a novel framework devoted to Structured Output Learning with Abstention (SOLA). The structure prediction model is able to abstain from predicting some labels in the structured output at a cost chosen by the user in a flexible way. For that purpose, we decompose the problem into the learning of a pair of predictors, one devoted to structured abstention and the other, to structured output prediction. To compare fully labeled training data with predictions potentially containing abstentions, we define a wide class of asymmetric abstention-aware losses. Learning is achieved by surrogate regression in an appropriate feature space while prediction with abstention is performed by solving a new pre-image problem. Thus, SOLA extends recent ideas about Structured Output Prediction via surrogate problems and calibration theory and enjoys statistical guarantees on the resulting excess risk. Instantiated on a hierarchical abstention-aware loss, SOLA is shown to be relevant for fine-grained opinion mining and gives state-of-the-art results on this task. Moreover, the abstention-aware representations can be used to competitively predict user-review ratings based on a sentence-level opinion predictor. |
| Tasks | Calibration, Opinion Mining |
| Published | 2018-03-22 |
| URL | http://arxiv.org/abs/1803.08355v2 |
| http://arxiv.org/pdf/1803.08355v2.pdf | |
| PWC | https://paperswithcode.com/paper/structured-output-learning-with-abstention |
| Repo | |
| Framework | |
Essentially No Barriers in Neural Network Energy Landscape
| Title | Essentially No Barriers in Neural Network Energy Landscape |
| Authors | Felix Draxler, Kambis Veschgini, Manfred Salmhofer, Fred A. Hamprecht |
| Abstract | Training neural networks involves finding minima of a high-dimensional non-convex loss function. Knowledge of the structure of this energy landscape is sparse. Relaxing from linear interpolations, we construct continuous paths between minima of recent neural network architectures on CIFAR10 and CIFAR100. Surprisingly, the paths are essentially flat in both the training and test landscapes. This implies that neural networks have enough capacity for structural changes, or that these changes are small between minima. Also, each minimum has at least one vanishing Hessian eigenvalue in addition to those resulting from trivial invariance. |
| Tasks | |
| Published | 2018-03-02 |
| URL | http://arxiv.org/abs/1803.00885v5 |
| http://arxiv.org/pdf/1803.00885v5.pdf | |
| PWC | https://paperswithcode.com/paper/essentially-no-barriers-in-neural-network |
| Repo | |
| Framework | |
Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting
| Title | Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting |
| Authors | Craig Atkinson, Brendan McCane, Lech Szymanski, Anthony Robins |
| Abstract | Neural networks can achieve extraordinary results on a wide variety of tasks. However, when they attempt to sequentially learn a number of tasks, they tend to learn the new task while destructively forgetting previous tasks. One solution to this problem is pseudo-rehearsal, which involves learning the new task while rehearsing generated items representative of previous tasks. Our model combines pseudo-rehearsal with a deep generative model and a dual memory system, resulting in a method that does not demand additional storage requirements as the number of tasks increase. Our model iteratively learns three Atari 2600 games while retaining above human level performance on all three games and performing as well as a set of networks individually trained on the tasks. This result is achieved without revisiting or storing raw data from past tasks. Furthermore, previous state-of-the-art solutions demonstrate substantial forgetting compared to our model on these complex deep reinforcement learning tasks. |
| Tasks | Atari Games |
| Published | 2018-12-06 |
| URL | https://arxiv.org/abs/1812.02464v4 |
| https://arxiv.org/pdf/1812.02464v4.pdf | |
| PWC | https://paperswithcode.com/paper/pseudo-rehearsal-achieving-deep-reinforcement |
| Repo | |
| Framework | |
VITAL: VIsual Tracking via Adversarial Learning
| Title | VITAL: VIsual Tracking via Adversarial Learning |
| Authors | Yibing Song, Chao Ma, Xiaohe Wu, Lijun Gong, Linchao Bao, Wangmeng Zuo, Chunhua Shen, Rynson Lau, Ming-Hsuan Yang |
| Abstract | The tracking-by-detection framework consists of two stages, i.e., drawing samples around the target object in the first stage and classifying each sample as the target object or as background in the second stage. The performance of existing trackers using deep classification networks is limited by two aspects. First, the positive samples in each frame are highly spatially overlapped, and they fail to capture rich appearance variations. Second, there exists extreme class imbalance between positive and negative samples. This paper presents the VITAL algorithm to address these two problems via adversarial learning. To augment positive samples, we use a generative network to randomly generate masks, which are applied to adaptively dropout input features to capture a variety of appearance changes. With the use of adversarial learning, our network identifies the mask that maintains the most robust features of the target objects over a long temporal span. In addition, to handle the issue of class imbalance, we propose a high-order cost sensitive loss to decrease the effect of easy negative samples to facilitate training the classification network. Extensive experiments on benchmark datasets demonstrate that the proposed tracker performs favorably against state-of-the-art approaches. |
| Tasks | Visual Tracking |
| Published | 2018-04-12 |
| URL | http://arxiv.org/abs/1804.04273v1 |
| http://arxiv.org/pdf/1804.04273v1.pdf | |
| PWC | https://paperswithcode.com/paper/vital-visual-tracking-via-adversarial |
| Repo | |
| Framework | |
Concept-drifting Data Streams are Time Series; The Case for Continuous Adaptation
| Title | Concept-drifting Data Streams are Time Series; The Case for Continuous Adaptation |
| Authors | Jesse Read |
| Abstract | Learning from data streams is an increasingly important topic in data mining, machine learning, and artificial intelligence in general. A major focus in the data stream literature is on designing methods that can deal with concept drift, a challenge where the generating distribution changes over time. A general assumption in most of this literature is that instances are independently distributed in the stream. In this work we show that, in the context of concept drift, this assumption is contradictory, and that the presence of concept drift necessarily implies temporal dependence; and thus some form of time series. This has important implications on model design and deployment. We explore and highlight the these implications, and show that Hoeffding-tree based ensembles, which are very popular for learning in streams, are not naturally suited to learning \emph{within} drift; and can perform in this scenario only at significant computational cost of destructive adaptation. On the other hand, we develop and parameterize gradient-descent methods and demonstrate how they can perform \emph{continuous} adaptation with no explicit drift-detection mechanism, offering major advantages in terms of accuracy and efficiency. As a consequence of our theoretical discussion and empirical observations, we outline a number of recommendations for deploying methods in concept-drifting streams. |
| Tasks | Time Series |
| Published | 2018-10-04 |
| URL | http://arxiv.org/abs/1810.02266v1 |
| http://arxiv.org/pdf/1810.02266v1.pdf | |
| PWC | https://paperswithcode.com/paper/concept-drifting-data-streams-are-time-series |
| Repo | |
| Framework | |
Conceptual Knowledge Markup Language: An Introduction
| Title | Conceptual Knowledge Markup Language: An Introduction |
| Authors | Robert E. Kent |
| Abstract | Conceptual Knowledge Markup Language (CKML) is an application of XML. Earlier versions of CKML followed rather exclusively the philosophy of Conceptual Knowledge Processing (CKP), a principled approach to knowledge representation and data analysis that “advocates methods and instruments of conceptual knowledge processing which support people in their rational thinking, judgment and acting and promote critical discussion.” The new version of CKML continues to follow this approach, but also incorporates various principles, insights and techniques from Information Flow (IF), the logical design of distributed systems. Among other things, this allows diverse communities of discourse to compare their own information structures, as coded in logical theories, with that of other communities that share a common generic ontology. CKML incorporates the CKP ideas of concept lattice and formal context, along with the IF ideas of classification (= formal context), infomorphism, theory, interpretation and local logic. Ontology Markup Language (OML), a subset of CKML that is a self-sufficient markup language in its own right, follows the principles and ideas of Conceptual Graphs (CG). OML is used for structuring the specifications and axiomatics of metadata into ontologies. OML incorporates the CG ideas of concept, conceptual relation, conceptual graph, conceptual context, participants and ontology. The link from OML to CKML is the process of conceptual scaling, which is the interpretive transformation of ontologically structured knowledge to conceptual structured knowledge. |
| Tasks | |
| Published | 2018-10-10 |
| URL | http://arxiv.org/abs/1810.05534v1 |
| http://arxiv.org/pdf/1810.05534v1.pdf | |
| PWC | https://paperswithcode.com/paper/conceptual-knowledge-markup-language-an |
| Repo | |
| Framework | |
Learning Attribute Representation for Human Activity Recognition
| Title | Learning Attribute Representation for Human Activity Recognition |
| Authors | Fernando Moya Rueda, Gernot A. Fink |
| Abstract | Attribute representations became relevant in image recognition and word spotting, providing support under the presence of unbalance and disjoint datasets. However, for human activity recognition using sequential data from on-body sensors, human-labeled attributes are lacking. This paper introduces a search for attributes that represent favorably signal segments for recognizing human activities. It presents three deep architectures, including temporal-convolutions and an IMU centered design, for predicting attributes. An empiric evaluation of random and learned attribute representations, and as well as the networks is carried out on two datasets, outperforming the state-of-the art. |
| Tasks | Activity Recognition, Human Activity Recognition |
| Published | 2018-02-02 |
| URL | http://arxiv.org/abs/1802.00761v1 |
| http://arxiv.org/pdf/1802.00761v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-attribute-representation-for-human |
| Repo | |
| Framework | |
