Paper Group ANR 100
Estimating Entropy of Distributions in Constant Space. Saliency Based Fire Detection Using Texture and Color Features. Deep Multi-View Learning using Neuron-Wise Correlation-Maximizing Regularizers. Responsible Facial Recognition and Beyond. Discovering Episodes with Compact Minimal Windows. Local Aggregation for Unsupervised Learning of Visual Emb …
Estimating Entropy of Distributions in Constant Space
| Title | Estimating Entropy of Distributions in Constant Space |
| Authors | Jayadev Acharya, Sourbh Bhadane, Piotr Indyk, Ziteng Sun |
| Abstract | We consider the task of estimating the entropy of $k$-ary distributions from samples in the streaming model, where space is limited. Our main contribution is an algorithm that requires $O\left(\frac{k \log (1/\varepsilon)^2}{\varepsilon^3}\right)$ samples and a constant $O(1)$ memory words of space and outputs a $\pm\varepsilon$ estimate of $H(p)$. Without space limitations, the sample complexity has been established as $S(k,\varepsilon)=\Theta\left(\frac k{\varepsilon\log k}+\frac{\log^2 k}{\varepsilon^2}\right)$, which is sub-linear in the domain size $k$, and the current algorithms that achieve optimal sample complexity also require nearly-linear space in $k$. Our algorithm partitions $[0,1]$ into intervals and estimates the entropy contribution of probability values in each interval. The intervals are designed to trade off the bias and variance of these estimates. |
| Tasks | |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07976v1 |
| https://arxiv.org/pdf/1911.07976v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-entropy-of-distributions-in-1 |
| Repo | |
| Framework | |
Saliency Based Fire Detection Using Texture and Color Features
| Title | Saliency Based Fire Detection Using Texture and Color Features |
| Authors | Maedeh Jamali, Nader Karimi, Shadrokh Samavi |
| Abstract | Due to industry deployment and extension of urban areas, early warning systems have an essential role in giving emergency. Fire is an event that can rapidly spread and cause injury, death, and damage. Early detection of fire could significantly reduce these injuries. Video-based fire detection is a low cost and fast method in comparison with conventional fire detectors. Most available fire detection methods have a high false-positive rate and low accuracy. In this paper, we increase accuracy by using spatial and temporal features. Captured video sequences are divided into Spatio-temporal blocks. Then a saliency map and combination of color and texture features are used for detecting fire regions. We use the HSV color model as a spatial feature and LBP-TOP for temporal processing of fire texture. Fire detection tests on publicly available datasets have shown the accuracy and robustness of the algorithm. |
| Tasks | |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.10059v1 |
| https://arxiv.org/pdf/1912.10059v1.pdf | |
| PWC | https://paperswithcode.com/paper/saliency-based-fire-detection-using-texture |
| Repo | |
| Framework | |
Deep Multi-View Learning using Neuron-Wise Correlation-Maximizing Regularizers
| Title | Deep Multi-View Learning using Neuron-Wise Correlation-Maximizing Regularizers |
| Authors | Kui Jia, Jiehong Lin, Mingkui Tan, Dacheng Tao |
| Abstract | Many machine learning problems concern with discovering or associating common patterns in data of multiple views or modalities. Multi-view learning is of the methods to achieve such goals. Recent methods propose deep multi-view networks via adaptation of generic Deep Neural Networks (DNNs), which concatenate features of individual views at intermediate network layers (i.e., fusion layers). In this work, we study the problem of multi-view learning in such end-to-end networks. We take a regularization approach via multi-view learning criteria, and propose a novel, effective, and efficient neuron-wise correlation-maximizing regularizer. We implement our proposed regularizers collectively as a correlation-regularized network layer (CorrReg). CorrReg can be applied to either fully-connected or convolutional fusion layers, simply by replacing them with their CorrReg counterparts. By partitioning neurons of a hidden layer in generic DNNs into multiple subsets, we also consider a multi-view feature learning perspective of generic DNNs. Such a perspective enables us to study deep multi-view learning in the context of regularized network training, for which we present control experiments of benchmark image classification to show the efficacy of our proposed CorrReg. To investigate how CorrReg is useful for practical multi-view learning problems, we conduct experiments of RGB-D object/scene recognition and multi-view based 3D object recognition, using networks with fusion layers that concatenate intermediate features of individual modalities or views for subsequent classification. Applying CorrReg to fusion layers of these networks consistently improves classification performance. In particular, we achieve the new state of the art on the benchmark RGB-D object and RGB-D scene datasets. We make the implementation of CorrReg publicly available. |
| Tasks | 3D Object Recognition, Image Classification, MULTI-VIEW LEARNING, Object Recognition, Scene Recognition |
| Published | 2019-04-25 |
| URL | http://arxiv.org/abs/1904.11151v1 |
| http://arxiv.org/pdf/1904.11151v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-multi-view-learning-using-neuron-wise |
| Repo | |
| Framework | |
Responsible Facial Recognition and Beyond
| Title | Responsible Facial Recognition and Beyond |
| Authors | Yi Zeng, Enmeng Lu, Yinqian Sun, Ruochen Tian |
| Abstract | Facial recognition is changing the way we live in and interact with our society. Here we discuss the two sides of facial recognition, summarizing potential risks and current concerns. We introduce current policies and regulations in different countries. Very importantly, we point out that the risks and concerns are not only from facial recognition, but also realistically very similar to other biometric recognition technology, including but not limited to gait recognition, iris recognition, fingerprint recognition, voice recognition, etc. To create a responsible future, we discuss possible technological moves and efforts that should be made to keep facial recognition (and biometric recognition in general) developing for social good. |
| Tasks | Gait Recognition, Iris Recognition |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.12935v1 |
| https://arxiv.org/pdf/1909.12935v1.pdf | |
| PWC | https://paperswithcode.com/paper/responsible-facial-recognition-and-beyond |
| Repo | |
| Framework | |
Discovering Episodes with Compact Minimal Windows
| Title | Discovering Episodes with Compact Minimal Windows |
| Authors | Nikolaj Tatti |
| Abstract | Discovering the most interesting patterns is the key problem in the field of pattern mining. While ranking or selecting patterns is well-studied for itemsets it is surprisingly under-researched for other, more complex, pattern types. In this paper we propose a new quality measure for episodes. An episode is essentially a set of events with possible restrictions on the order of events. We say that an episode is significant if its occurrence is abnormally compact, that is, only few gap events occur between the actual episode events, when compared to the expected length according to the independence model. We can apply this measure as a post-pruning step by first discovering frequent episodes and then rank them according to this measure. In order to compute the score we will need to compute the mean and the variance according to the independence model. As a main technical contribution we introduce a technique that allows us to compute these values. Such a task is surprisingly complex and in order to solve it we develop intricate finite state machines that allow us to compute the needed statistics. We also show that asymptotically our score can be interpreted as a P-value. In our experiments we demonstrate that despite its intricacy our ranking is fast: we can rank tens of thousands episodes in seconds. Our experiments with text data demonstrate that our measure ranks interpretable episodes high. |
| Tasks | |
| Published | 2019-04-15 |
| URL | http://arxiv.org/abs/1904.07974v1 |
| http://arxiv.org/pdf/1904.07974v1.pdf | |
| PWC | https://paperswithcode.com/paper/190407974 |
| Repo | |
| Framework | |
Local Aggregation for Unsupervised Learning of Visual Embeddings
| Title | Local Aggregation for Unsupervised Learning of Visual Embeddings |
| Authors | Chengxu Zhuang, Alex Lin Zhai, Daniel Yamins |
| Abstract | Unsupervised approaches to learning in neural networks are of substantial interest for furthering artificial intelligence, both because they would enable the training of networks without the need for large numbers of expensive annotations, and because they would be better models of the kind of general-purpose learning deployed by humans. However, unsupervised networks have long lagged behind the performance of their supervised counterparts, especially in the domain of large-scale visual recognition. Recent developments in training deep convolutional embeddings to maximize non-parametric instance separation and clustering objectives have shown promise in closing this gap. Here, we describe a method that trains an embedding function to maximize a metric of local aggregation, causing similar data instances to move together in the embedding space, while allowing dissimilar instances to separate. This aggregation metric is dynamic, allowing soft clusters of different scales to emerge. We evaluate our procedure on several large-scale visual recognition datasets, achieving state-of-the-art unsupervised transfer learning performance on object recognition in ImageNet, scene recognition in Places 205, and object detection in PASCAL VOC. |
| Tasks | Object Detection, Object Recognition, Scene Recognition, Transfer Learning |
| Published | 2019-03-29 |
| URL | http://arxiv.org/abs/1903.12355v2 |
| http://arxiv.org/pdf/1903.12355v2.pdf | |
| PWC | https://paperswithcode.com/paper/local-aggregation-for-unsupervised-learning |
| Repo | |
| Framework | |
Liability, Ethics, and Culture-Aware Behavior Specification using Rulebooks
| Title | Liability, Ethics, and Culture-Aware Behavior Specification using Rulebooks |
| Authors | Andrea Censi, Konstantin Slutsky, Tichakorn Wongpiromsarn, Dmitry Yershov, Scott Pendleton, James Fu, Emilio Frazzoli |
| Abstract | The behavior of self-driving cars must be compatible with an enormous set of conflicting and ambiguous objectives, from law, from ethics, from the local culture, and so on. This paper describes a new way to conveniently define the desired behavior for autonomous agents, which we use on the self-driving cars developed at nuTonomy. We define a “rulebook” as a pre-ordered set of “rules”, each akin to a violation metric on the possible outcomes (“realizations”). The rules are partially ordered by priority. The semantics of a rulebook imposes a pre-order on the set of realizations. We study the compositional properties of the rulebooks, and we derive which operations we can allow on the rulebooks to preserve previously-introduced constraints. While we demonstrate the application of these techniques in the self-driving domain, the methods are domain-independent. |
| Tasks | Self-Driving Cars |
| Published | 2019-02-25 |
| URL | http://arxiv.org/abs/1902.09355v2 |
| http://arxiv.org/pdf/1902.09355v2.pdf | |
| PWC | https://paperswithcode.com/paper/liability-ethics-and-culture-aware-behavior |
| Repo | |
| Framework | |
Classification of Radio Signals and HF Transmission Modes with Deep Learning
| Title | Classification of Radio Signals and HF Transmission Modes with Deep Learning |
| Authors | Stefan Scholl |
| Abstract | This paper investigates deep neural networks for radio signal classification. Instead of performing modulation recognition and combining it with further analysis methods, the classifier operates directly on the IQ data of the signals and outputs the transmission mode. A data set of radio signals of 18 different modes, that commonly occur in the HF radio band, is presented and used as a showcase example. The data set considers HF channel properties and is used to train four different deep neural network architectures. The results of the best networks show an excellent accuracy of up to 98%. |
| Tasks | |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04459v1 |
| https://arxiv.org/pdf/1906.04459v1.pdf | |
| PWC | https://paperswithcode.com/paper/classification-of-radio-signals-and-hf |
| Repo | |
| Framework | |
On the Functional Equivalence of TSK Fuzzy Systems to Neural Networks, Mixture of Experts, CART, and Stacking Ensemble Regression
| Title | On the Functional Equivalence of TSK Fuzzy Systems to Neural Networks, Mixture of Experts, CART, and Stacking Ensemble Regression |
| Authors | Dongrui Wu, Chin-Teng Lin, Jian Huang, Zhigang Zeng |
| Abstract | Fuzzy systems have achieved great success in numerous applications. However, there are still many challenges in designing an optimal fuzzy system, e.g., how to efficiently optimize its parameters, how to balance the trade-off between cooperations and competitions among the rules, how to overcome the curse of dimensionality, how to increase its generalization ability, etc. Literature has shown that by making appropriate connections between fuzzy systems and other machine learning approaches, good practices from other domains may be used to improve the fuzzy systems, and vice versa. This paper gives an overview on the functional equivalence between Takagi-Sugeno-Kang fuzzy systems and four classic machine learning approaches – neural networks, mixture of experts, classification and regression trees, and stacking ensemble regression – for regression problems. We also point out some promising new research directions, inspired by the functional equivalence, that could lead to solutions to the aforementioned problems. To our knowledge, this is so far the most comprehensive overview on the connections between fuzzy systems and other popular machine learning approaches, and hopefully will stimulate more hybridization between different machine learning algorithms. |
| Tasks | |
| Published | 2019-03-25 |
| URL | https://arxiv.org/abs/1903.10572v2 |
| https://arxiv.org/pdf/1903.10572v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-functional-equivalence-of-tsk-fuzzy |
| Repo | |
| Framework | |
Machine Learning in the Air
| Title | Machine Learning in the Air |
| Authors | Deniz Gunduz, Paul de Kerret, Nicholas D. Sidiropoulos, David Gesbert, Chandra Murthy, Mihaela van der Schaar |
| Abstract | Thanks to the recent advances in processing speed and data acquisition and storage, machine learning (ML) is penetrating every facet of our lives, and transforming research in many areas in a fundamental manner. Wireless communications is another success story – ubiquitous in our lives, from handheld devices to wearables, smart homes, and automobiles. While recent years have seen a flurry of research activity in exploiting ML tools for various wireless communication problems, the impact of these techniques in practical communication systems and standards is yet to be seen. In this paper, we review some of the major promises and challenges of ML in wireless communication systems, focusing mainly on the physical layer. We present some of the most striking recent accomplishments that ML techniques have achieved with respect to classical approaches, and point to promising research directions where ML is likely to make the biggest impact in the near future. We also highlight the complementary problem of designing physical layer techniques to enable distributed ML at the wireless network edge, which further emphasizes the need to understand and connect ML with fundamental concepts in wireless communications. |
| Tasks | |
| Published | 2019-04-28 |
| URL | http://arxiv.org/abs/1904.12385v1 |
| http://arxiv.org/pdf/1904.12385v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-in-the-air |
| Repo | |
| Framework | |
Emotion Recognition with Spatial Attention and Temporal Softmax Pooling
| Title | Emotion Recognition with Spatial Attention and Temporal Softmax Pooling |
| Authors | Masih Aminbeidokhti, Marco Pedersoli, Patrick Cardinal, Eric Granger |
| Abstract | Video-based emotion recognition is a challenging task because it requires to distinguish the small deformations of the human face that represent emotions, while being invariant to stronger visual differences due to different identities. State-of-the-art methods normally use complex deep learning models such as recurrent neural networks (RNNs, LSTMs, GRUs), convolutional neural networks (CNNs, C3D, residual networks) and their combination. In this paper, we propose a simpler approach that combines a CNN pre-trained on a public dataset of facial images with (1) a spatial attention mechanism, to localize the most important regions of the face for a given emotion, and (2) temporal softmax pooling, to select the most important frames of the given video. Results on the challenging EmotiW dataset show that this approach can achieve higher accuracy than more complex approaches. |
| Tasks | Emotion Recognition |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.01254v2 |
| https://arxiv.org/pdf/1910.01254v2.pdf | |
| PWC | https://paperswithcode.com/paper/emotion-recognition-with-spatial-attention |
| Repo | |
| Framework | |
EvalNorm: Estimating Batch Normalization Statistics for Evaluation
| Title | EvalNorm: Estimating Batch Normalization Statistics for Evaluation |
| Authors | Saurabh Singh, Abhinav Shrivastava |
| Abstract | Batch normalization (BN) has been very effective for deep learning and is widely used. However, when training with small minibatches, models using BN exhibit a significant degradation in performance. In this paper we study this peculiar behavior of BN to gain a better understanding of the problem, and identify a cause. We propose ‘EvalNorm’ to address the issue by estimating corrected normalization statistics to use for BN during evaluation. EvalNorm supports online estimation of the corrected statistics while the model is being trained, and does not affect the training scheme of the model. As a result, EvalNorm can also be used with existing pre-trained models allowing them to benefit from our method. EvalNorm yields large gains for models trained with smaller batches. Our experiments show that EvalNorm performs 6.18% (absolute) better than vanilla BN for a batchsize of 2 on ImageNet validation set and from 1.5 to 7.0 points (absolute) gain on the COCO object detection benchmark across a variety of setups. |
| Tasks | Object Detection |
| Published | 2019-04-12 |
| URL | https://arxiv.org/abs/1904.06031v2 |
| https://arxiv.org/pdf/1904.06031v2.pdf | |
| PWC | https://paperswithcode.com/paper/evalnorm-estimating-batch-normalization |
| Repo | |
| Framework | |
On the Generalization Gap in Reparameterizable Reinforcement Learning
| Title | On the Generalization Gap in Reparameterizable Reinforcement Learning |
| Authors | Huan Wang, Stephan Zheng, Caiming Xiong, Richard Socher |
| Abstract | Understanding generalization in reinforcement learning (RL) is a significant challenge, as many common assumptions of traditional supervised learning theory do not apply. We focus on the special class of reparameterizable RL problems, where the trajectory distribution can be decomposed using the reparametrization trick. For this problem class, estimating the expected return is efficient and the trajectory can be computed deterministically given peripheral random variables, which enables us to study reparametrizable RL using supervised learning and transfer learning theory. Through these relationships, we derive guarantees on the gap between the expected and empirical return for both intrinsic and external errors, based on Rademacher complexity as well as the PAC-Bayes bound. Our bound suggests the generalization capability of reparameterizable RL is related to multiple factors including “smoothness” of the environment transition, reward and agent policy function class. We also empirically verify the relationship between the generalization gap and these factors through simulations. |
| Tasks | Transfer Learning |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12654v1 |
| https://arxiv.org/pdf/1905.12654v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-generalization-gap-in |
| Repo | |
| Framework | |
A Multi-Task Architecture on Relevance-based Neural Query Translation
| Title | A Multi-Task Architecture on Relevance-based Neural Query Translation |
| Authors | Sheikh Muhammad Sarwar, Hamed Bonab, James Allan |
| Abstract | We describe a multi-task learning approach to train a Neural Machine Translation (NMT) model with a Relevance-based Auxiliary Task (RAT) for search query translation. The translation process for Cross-lingual Information Retrieval (CLIR) task is usually treated as a black box and it is performed as an independent step. However, an NMT model trained on sentence-level parallel data is not aware of the vocabulary distribution of the retrieval corpus. We address this problem with our multi-task learning architecture that achieves 16% improvement over a strong NMT baseline on Italian-English query-document dataset. We show using both quantitative and qualitative analysis that our model generates balanced and precise translations with the regularization effect it achieves from multi-task learning paradigm. |
| Tasks | Information Retrieval, Machine Translation, Multi-Task Learning |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.06849v1 |
| https://arxiv.org/pdf/1906.06849v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-multi-task-architecture-on-relevance-based |
| Repo | |
| Framework | |
A physics-aware machine to predict extreme events in turbulence
| Title | A physics-aware machine to predict extreme events in turbulence |
| Authors | Nguyen Anh Khoa Doan, Wolfgang Polifke, Luca Magri |
| Abstract | We propose a physics-aware machine learning method to time-accurately predict extreme events in a turbulent flow. The method combines two radically different approaches: empirical modelling based on reservoir computing, which learns the chaotic dynamics from data only, and physical modelling based on conservation laws. We show that the combination of the two approaches is able to predict the occurrence and amplitude of extreme events in the self-sustaining process in turbulence-the abrupt transitions from turbulent to quasi-laminar states-which cannot be achieved by using either approach separately. This opens up new possibilities for enhancing synergistically data-driven methods with physical knowledge for the accurate prediction of extreme events in chaotic dynamical systems. |
| Tasks | |
| Published | 2019-12-23 |
| URL | https://arxiv.org/abs/1912.10994v1 |
| https://arxiv.org/pdf/1912.10994v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-physics-aware-machine-to-predict-extreme |
| Repo | |
| Framework | |
