Paper Group ANR 827
Improving Adversarial Robustness by Encouraging Discriminative Features. PACO: Global Signal Restoration via PAtch COnsensus. Deep Unsupervised Learning of Visual Similarities. Reconciled Polynomial Machine: A Unified Representation of Shallow and Deep Learning Models. On the scaling of polynomial features for representation matching. Learning to T …
Improving Adversarial Robustness by Encouraging Discriminative Features
| Title | Improving Adversarial Robustness by Encouraging Discriminative Features |
| Authors | Chirag Agarwal, Anh Nguyen, Dan Schonfeld |
| Abstract | Deep neural networks (DNNs) have achieved state-of-the-art results in various pattern recognition tasks. However, they perform poorly on out-of-distribution adversarial examples i.e. inputs that are specifically crafted by an adversary to cause DNNs to misbehave, questioning the security and reliability of applications. In this paper, we encourage DNN classifiers to learn more discriminative features by imposing a center loss in addition to the regular softmax cross-entropy loss. Intuitively, the center loss encourages DNNs to simultaneously learns a center for the deep features of each class, and minimize the distances between the intra-class deep features and their corresponding class centers. We hypothesize that minimizing distances between intra-class features and maximizing the distances between inter-class features at the same time would improve a classifier’s robustness to adversarial examples. Our results on state-of-the-art architectures on MNIST, CIFAR-10, and CIFAR-100 confirmed that intuition and highlight the importance of discriminative features. |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://arxiv.org/abs/1811.00621v2 |
| https://arxiv.org/pdf/1811.00621v2.pdf | |
| PWC | https://paperswithcode.com/paper/improving-adversarial-robustness-by |
| Repo | |
| Framework | |
PACO: Global Signal Restoration via PAtch COnsensus
| Title | PACO: Global Signal Restoration via PAtch COnsensus |
| Authors | Ignacio Francisco Ramírez Paulino |
| Abstract | Many signal processing algorithms break the target signal into overlapping segments (also called windows, or patches), process them separately, and then stitch them back into place to produce a unified output. At the overlaps, the final value of those samples that are estimated more than once needs to be decided in some way. Averaging, the simplest approach, tends to produce blurred results. Significant work has been devoted to this issue in recent years: several works explore the idea of a weighted average of the overlapped patches and/or pixels; a more recent approach is to promote agreement (consensus) between the patches at their intersections. This work investigates the case where consensus is imposed as a hard constraint on the restoration problem. This leads to a general framework applicable to all sorts of signals, problems, decomposition strategies, and featuring a number of theoretical and practical advantages over other similar methods. The framework itself consists of a general optimization problem and a simple and efficient \admm-based algorithm for solving it. We also show that the consensus step of the algorithm, which is the main bottleneck of similar methods, can be solved efficiently and easily for any arbitrary patch decomposition scheme. As an example of the potential of our framework, we propose a method for filling missing samples (inpainting) which can be applied to signals of any dimension, and show its effectiveness on audio, image and video signals. |
| Tasks | |
| Published | 2018-08-20 |
| URL | https://arxiv.org/abs/1808.06942v2 |
| https://arxiv.org/pdf/1808.06942v2.pdf | |
| PWC | https://paperswithcode.com/paper/paco-signal-restoration-via-patch-consensus |
| Repo | |
| Framework | |
Deep Unsupervised Learning of Visual Similarities
| Title | Deep Unsupervised Learning of Visual Similarities |
| Authors | Artsiom Sanakoyeu, Miguel A. Bautista, Björn Ommer |
| Abstract | Exemplar learning of visual similarities in an unsupervised manner is a problem of paramount importance to Computer Vision. In this context, however, the recent breakthrough in deep learning could not yet unfold its full potential. With only a single positive sample, a great imbalance between one positive and many negatives, and unreliable relationships between most samples, training of Convolutional Neural networks is impaired. In this paper we use weak estimates of local similarities and propose a single optimization problem to extract batches of samples with mutually consistent relations. Conflicting relations are distributed over different batches and similar samples are grouped into compact groups. Learning visual similarities is then framed as a sequence of categorization tasks. The CNN then consolidates transitivity relations within and between groups and learns a single representation for all samples without the need for labels. The proposed unsupervised approach has shown competitive performance on detailed posture analysis and object classification. |
| Tasks | Object Classification |
| Published | 2018-02-22 |
| URL | http://arxiv.org/abs/1802.08562v1 |
| http://arxiv.org/pdf/1802.08562v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-unsupervised-learning-of-visual |
| Repo | |
| Framework | |
Reconciled Polynomial Machine: A Unified Representation of Shallow and Deep Learning Models
| Title | Reconciled Polynomial Machine: A Unified Representation of Shallow and Deep Learning Models |
| Authors | Jiawei Zhang, Limeng Cui, Fisher B. Gouza |
| Abstract | In this paper, we aim at introducing a new machine learning model, namely reconciled polynomial machine, which can provide a unified representation of existing shallow and deep machine learning models. Reconciled polynomial machine predicts the output by computing the inner product of the feature kernel function and variable reconciling function. Analysis of several concrete models, including Linear Models, FM, MVM, Perceptron, MLP and Deep Neural Networks, will be provided in this paper, which can all be reduced to the reconciled polynomial machine representations. Detailed analysis of the learning error by these models will also be illustrated in this paper based on their reduced representations from the function approximation perspective. |
| Tasks | |
| Published | 2018-05-19 |
| URL | http://arxiv.org/abs/1805.07507v1 |
| http://arxiv.org/pdf/1805.07507v1.pdf | |
| PWC | https://paperswithcode.com/paper/reconciled-polynomial-machine-a-unified |
| Repo | |
| Framework | |
On the scaling of polynomial features for representation matching
| Title | On the scaling of polynomial features for representation matching |
| Authors | Siddhartha Brahma |
| Abstract | In many neural models, new features as polynomial functions of existing ones are used to augment representations. Using the natural language inference task as an example, we investigate the use of scaled polynomials of degree 2 and above as matching features. We find that scaling degree 2 features has the highest impact on performance, reducing classification error by 5% in the best models. |
| Tasks | Natural Language Inference |
| Published | 2018-02-20 |
| URL | http://arxiv.org/abs/1802.07374v1 |
| http://arxiv.org/pdf/1802.07374v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-scaling-of-polynomial-features-for |
| Repo | |
| Framework | |
Learning to Transcribe by Ear
| Title | Learning to Transcribe by Ear |
| Authors | Rainer Kelz, Gerhard Widmer |
| Abstract | Rethinking how to model polyphonic transcription formally, we frame it as a reinforcement learning task. Such a task formulation encompasses the notion of a musical agent and an environment containing an instrument as well as the sound source to be transcribed. Within this conceptual framework, the transcription process can be described as the agent interacting with the instrument in the environment, and obtaining reward by playing along with what it hears. Choosing from a discrete set of actions - the notes to play on its instrument - the amount of reward the agent experiences depends on which notes it plays and when. This process resembles how a human musician might approach the task of transcription, and the satisfaction she achieves by closely mimicking the sound source to transcribe on her instrument. Following a discussion of the theoretical framework and the benefits of modelling the problem in this way, we focus our attention on several practical considerations and address the difficulties in training an agent to acceptable performance on a set of tasks with increasing difficulty. We demonstrate promising results in partially constrained environments. |
| Tasks | |
| Published | 2018-05-29 |
| URL | http://arxiv.org/abs/1805.11526v1 |
| http://arxiv.org/pdf/1805.11526v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-transcribe-by-ear |
| Repo | |
| Framework | |
The variable quality of metadata about biological samples used in biomedical experiments
| Title | The variable quality of metadata about biological samples used in biomedical experiments |
| Authors | Rafael S. Gonçalves, Mark A. Musen |
| Abstract | We present an analytical study of the quality of metadata about samples used in biomedical experiments. The metadata under analysis are stored in two well-known databases: BioSample—a repository managed by the National Center for Biotechnology Information (NCBI), and BioSamples—a repository managed by the European Bioinformatics Institute (EBI). We tested whether 11.4M sample metadata records in the two repositories are populated with values that fulfill the stated requirements for such values. Our study revealed multiple anomalies in the metadata. Most metadata field names and their values are not standardized or controlled. Even simple binary or numeric fields are often populated with inadequate values of different data types. By clustering metadata field names, we discovered there are often many distinct ways to represent the same aspect of a sample. Overall, the metadata we analyzed reveal that there is a lack of principled mechanisms to enforce and validate metadata requirements. The significant aberrancies that we found in the metadata are likely to impede search and secondary use of the associated datasets. |
| Tasks | |
| Published | 2018-08-17 |
| URL | http://arxiv.org/abs/1808.06907v2 |
| http://arxiv.org/pdf/1808.06907v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-variable-quality-of-metadata-about |
| Repo | |
| Framework | |
Prediction Rule Reshaping
| Title | Prediction Rule Reshaping |
| Authors | Matt Bonakdarpour, Sabyasachi Chatterjee, Rina Foygel Barber, John Lafferty |
| Abstract | Two methods are proposed for high-dimensional shape-constrained regression and classification. These methods reshape pre-trained prediction rules to satisfy shape constraints like monotonicity and convexity. The first method can be applied to any pre-trained prediction rule, while the second method deals specifically with random forests. In both cases, efficient algorithms are developed for computing the estimators, and experiments are performed to demonstrate their performance on four datasets. We find that reshaping methods enforce shape constraints without compromising predictive accuracy. |
| Tasks | |
| Published | 2018-05-16 |
| URL | http://arxiv.org/abs/1805.06439v1 |
| http://arxiv.org/pdf/1805.06439v1.pdf | |
| PWC | https://paperswithcode.com/paper/prediction-rule-reshaping |
| Repo | |
| Framework | |
English Out-of-Vocabulary Lexical Evaluation Task
| Title | English Out-of-Vocabulary Lexical Evaluation Task |
| Authors | Han Wang, Ye Wang, Xinxiang Zhang, Mi Lu, Yoonsuck Choe, Jingjing Cao |
| Abstract | Unlike previous unknown nouns tagging task, this is the first attempt to focus on out-of-vocabulary (OOV) lexical evaluation tasks that do not require any prior knowledge. The OOV words are words that only appear in test samples. The goal of tasks is to provide solutions for OOV lexical classification and prediction. The tasks require annotators to conclude the attributes of the OOV words based on their related contexts. Then, we utilize unsupervised word embedding methods such as Word2Vec and Word2GM to perform the baseline experiments on the categorical classification task and OOV words attribute prediction tasks. |
| Tasks | |
| Published | 2018-04-11 |
| URL | https://arxiv.org/abs/1804.04242v3 |
| https://arxiv.org/pdf/1804.04242v3.pdf | |
| PWC | https://paperswithcode.com/paper/english-out-of-vocabulary-lexical-evaluation |
| Repo | |
| Framework | |
Dense Limit of the Dawid-Skene Model for Crowdsourcing and Regions of Sub-optimality of Message Passing Algorithms
| Title | Dense Limit of the Dawid-Skene Model for Crowdsourcing and Regions of Sub-optimality of Message Passing Algorithms |
| Authors | Christian Schmidt, Lenka Zdeborová |
| Abstract | Crowdsourcing is a strategy to categorize data through the contribution of many individuals. A wide range of theoretical and algorithmic contributions are based on the model of Dawid and Skene [1]. Recently it was shown in [2,3] that, in certain regimes, belief propagation is asymptotically optimal for data generated from the Dawid-Skene model. This paper is motivated by this recent progress. We analyze the dense limit of the Dawid-Skene model. It is shown that it belongs to a larger class of low-rank matrix estimation problems for which it is possible to express the asymptotic, Bayes-optimal, performance in a simple closed form. In the dense limit the mapping to a low-rank matrix estimation problem provides an approximate message passing algorithm that solves the problem algorithmically. We identify the regions where the algorithm efficiently computes the Bayes-optimal estimates. Our analysis refines the results of [2,3] about optimality of message passing algorithms by characterizing regions of parameters where these algorithms do not match the Bayes-optimal performance. We further study numerically the performance of approximate message passing, derived in the dense limit, on sparse instances and carry out experiments on a real world dataset. |
| Tasks | |
| Published | 2018-03-13 |
| URL | http://arxiv.org/abs/1803.04924v2 |
| http://arxiv.org/pdf/1803.04924v2.pdf | |
| PWC | https://paperswithcode.com/paper/dense-limit-of-the-dawid-skene-model-for |
| Repo | |
| Framework | |
Layer-wise synapse optimization for implementing neural networks on general neuromorphic architectures
| Title | Layer-wise synapse optimization for implementing neural networks on general neuromorphic architectures |
| Authors | John Mern, Jayesh K Gupta, Mykel Kochenderfer |
| Abstract | Deep artificial neural networks (ANNs) can represent a wide range of complex functions. Implementing ANNs in Von Neumann computing systems, though, incurs a high energy cost due to the bottleneck created between CPU and memory. Implementation on neuromorphic systems may help to reduce energy demand. Conventional ANNs must be converted into equivalent Spiking Neural Networks (SNNs) in order to be deployed on neuromorphic chips. This paper presents a way to perform this translation. We map the ANN weights to SNN synapses layer-by-layer by forming a least-square-error approximation problem at each layer. An optimal set of synapse weights may then be found for a given choice of ANN activation function and SNN neuron. Using an appropriate constrained solver, we can generate SNNs compatible with digital, analog, or hybrid chip architectures. We present an optimal node pruning method to allow SNN layer sizes to be set by the designer. To illustrate this process, we convert three ANNs, including one convolutional network, to SNNs. In all three cases, a simple linear program solver was used. The experiments show that the resulting networks maintain agreement with the original ANN and excellent performance on the evaluation tasks. The networks were also reduced in size with little loss in task performance. |
| Tasks | |
| Published | 2018-02-20 |
| URL | http://arxiv.org/abs/1802.06920v1 |
| http://arxiv.org/pdf/1802.06920v1.pdf | |
| PWC | https://paperswithcode.com/paper/layer-wise-synapse-optimization-for |
| Repo | |
| Framework | |
Navigating Assistance System for Quadcopter with Deep Reinforcement Learning
| Title | Navigating Assistance System for Quadcopter with Deep Reinforcement Learning |
| Authors | Tung-Cheng Wu, Shau-Yin Tseng, Chin-Feng Lai, Chia-Yu Ho, Ying-Hsun Lai |
| Abstract | In this paper, we present a deep reinforcement learning method for quadcopter bypassing the obstacle on the flying path. In the past study, the algorithm only controls the forward direction about quadcopter. In this letter, we use two functions to control quadcopter. One is quadcopter navigating function. It is based on calculating coordination point and find the straight path to the goal. The other function is collision avoidance function. It is implemented by deep Q-network model. Both two function will output rotating degree, the agent will combine both output and turn direct. Besides, deep Q-network can also make quadcopter fly up and down to bypass the obstacle and arrive at the goal. Our experimental result shows that the collision rate is 14% after 500 flights. Based on this work, we will train more complex sense and transfer model to the real quadcopter. |
| Tasks | |
| Published | 2018-11-12 |
| URL | http://arxiv.org/abs/1811.04584v1 |
| http://arxiv.org/pdf/1811.04584v1.pdf | |
| PWC | https://paperswithcode.com/paper/navigating-assistance-system-for-quadcopter |
| Repo | |
| Framework | |
Repetitive Motion Estimation Network: Recover cardiac and respiratory signal from thoracic imaging
| Title | Repetitive Motion Estimation Network: Recover cardiac and respiratory signal from thoracic imaging |
| Authors | Xiaoxiao Li, Vivek Singh, Yifan Wu, Klaus Kirchberg, James Duncan, Ankur Kapoor |
| Abstract | Tracking organ motion is important in image-guided interventions, but motion annotations are not always easily available. Thus, we propose Repetitive Motion Estimation Network (RMEN) to recover cardiac and respiratory signals. It learns the spatio-temporal repetition patterns, embedding high dimensional motion manifolds to 1D vectors with partial motion phase boundary annotations. Compared with the best alternative models, our proposed RMEN significantly decreased the QRS peaks detection offsets by 59.3%. Results showed that RMEN could handle the irregular cardiac and respiratory motion cases. Repetitive motion patterns learned by RMEN were visualized and indicated in the feature maps. |
| Tasks | Motion Estimation |
| Published | 2018-11-08 |
| URL | http://arxiv.org/abs/1811.03343v1 |
| http://arxiv.org/pdf/1811.03343v1.pdf | |
| PWC | https://paperswithcode.com/paper/repetitive-motion-estimation-network-recover |
| Repo | |
| Framework | |
Semantic Role Labeling for Knowledge Graph Extraction from Text
| Title | Semantic Role Labeling for Knowledge Graph Extraction from Text |
| Authors | Mehwish Alam, Aldo Gangemi, Valentina Presutti, Diego Reforgiato Recupero |
| Abstract | This paper introduces TakeFive, a new semantic role labeling method that transforms a text into a frame-oriented knowledge graph. It performs dependency parsing, identifies the words that evoke lexical frames, locates the roles and fillers for each frame, runs coercion techniques, and formalises the results as a knowledge graph. This formal representation complies with the frame semantics used in Framester, a factual-linguistic linked data resource. The obtained precision, recall and F1 values indicate that TakeFive is competitive with other existing methods such as SEMAFOR, Pikes, PathLSTM and FRED. We finally discuss how to combine TakeFive and FRED, obtaining higher values of precision, recall and F1. |
| Tasks | Dependency Parsing, Semantic Role Labeling |
| Published | 2018-11-04 |
| URL | http://arxiv.org/abs/1811.01409v1 |
| http://arxiv.org/pdf/1811.01409v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-role-labeling-for-knowledge-graph |
| Repo | |
| Framework | |
Non-entailed subsequences as a challenge for natural language inference
| Title | Non-entailed subsequences as a challenge for natural language inference |
| Authors | R. Thomas McCoy, Tal Linzen |
| Abstract | Neural network models have shown great success at natural language inference (NLI), the task of determining whether a premise entails a hypothesis. However, recent studies suggest that these models may rely on fallible heuristics rather than deep language understanding. We introduce a challenge set to test whether NLI systems adopt one such heuristic: assuming that a sentence entails all of its subsequences, such as assuming that “Alice believes Mary is lying” entails “Alice believes Mary.” We evaluate several competitive NLI models on this challenge set and find strong evidence that they do rely on the subsequence heuristic. |
| Tasks | Natural Language Inference |
| Published | 2018-11-29 |
| URL | http://arxiv.org/abs/1811.12112v2 |
| http://arxiv.org/pdf/1811.12112v2.pdf | |
| PWC | https://paperswithcode.com/paper/non-entailed-subsequences-as-a-challenge-for |
| Repo | |
| Framework | |
