January 26, 2020

3101 words 15 mins read

Paper Group ANR 1543

Collaborative representation-based robust face recognition by discriminative low-rank representation. OCC: A Smart Reply System for Efficient In-App Communications. Cramnet: Layer-wise Deep Neural Network Compression with Knowledge Transfer from a Teacher Network. Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interaction …

Collaborative representation-based robust face recognition by discriminative low-rank representation


Title	Collaborative representation-based robust face recognition by discriminative low-rank representation
Authors	Wen Zhao, Xiao-Jun Wu, He-Feng Yin, Zi-Qi Li
Abstract	We consider the problem of robust face recognition in which both the training and test samples might be corrupted because of disguise and occlusion. Performance of conventional subspace learning methods and recently proposed sparse representation based classification (SRC) might be degraded when corrupted training samples are provided. In addition, sparsity based approaches are time-consuming due to the sparsity constraint. To alleviate the aforementioned problems to some extent, in this paper, we propose a discriminative low-rank representation method for collaborative representation-based (DLRR-CR) robust face recognition. DLRR-CR not only obtains a clean dictionary, it further forces the sub-dictionaries for distinct classes to be as independent as possible by introducing a structural incoherence regularization term. Simultaneously, a low-rank projection matrix can be learned to remove the possible corruptions in the testing samples. Collaborative representation based classification (CRC) method is exploited in our proposed method which has closed-form solution. Experimental results obtained on public face databases verify the effectiveness and robustness of our method.
Tasks	Face Recognition, Robust Face Recognition, Sparse Representation-based Classification
Published	2019-12-17
URL	https://arxiv.org/abs/1912.07778v1
PDF	https://arxiv.org/pdf/1912.07778v1.pdf
PWC	https://paperswithcode.com/paper/collaborative-representation-based-robust
Repo
Framework

OCC: A Smart Reply System for Efficient In-App Communications


Title	OCC: A Smart Reply System for Efficient In-App Communications
Authors	Yue Weng, Huaixiu Zheng, Franziska Bell, Gokhan Tur
Abstract	Smart reply systems have been developed for various messaging platforms. In this paper, we introduce Uber’s smart reply system: one-click-chat (OCC), which is a key enhanced feature on top of the Uber in-app chat system. It enables driver-partners to quickly respond to rider messages using smart replies. The smart replies are dynamically selected according to conversation content using machine learning algorithms. Our system consists of two major components: intent detection and reply retrieval, which are very different from standard smart reply systems where the task is to directly predict a reply. It is designed specifically for mobile applications with short and non-canonical messages. Reply retrieval utilizes pairings between intent and reply based on their popularity in chat messages as derived from historical data. For intent detection, a set of embedding and classification techniques are experimented with, and we choose to deploy a solution using unsupervised distributed embedding and nearest-neighbor classifier. It has the advantage of only requiring a small amount of labeled training data, simplicity in developing and deploying to production, and fast inference during serving and hence highly scalable. At the same time, it performs comparably with deep learning architectures such as word-level convolutional neural network. Overall, the system achieves a high accuracy of 76% on intent detection. Currently, the system is deployed in production for English-speaking countries and 71% of in-app communications between riders and driver-partners adopted the smart replies to speedup the communication process.
Tasks	Intent Detection
Published	2019-07-18
URL	https://arxiv.org/abs/1907.08167v1
PDF	https://arxiv.org/pdf/1907.08167v1.pdf
PWC	https://paperswithcode.com/paper/occ-a-smart-reply-system-for-efficient-in-app
Repo
Framework

Cramnet: Layer-wise Deep Neural Network Compression with Knowledge Transfer from a Teacher Network


Title	Cramnet: Layer-wise Deep Neural Network Compression with Knowledge Transfer from a Teacher Network
Authors	Jon Hoffman
Abstract	Neural Networks accomplish amazing things, but they suffer from computational and memory bottlenecks that restrict their usage. Nowhere can this be better seen than in the mobile space, where specialized hardware is being created just to satisfy the demand for neural networks. Previous studies have shown that neural networks have vastly more connections than they actually need to do their work. This thesis develops a method that can compress networks to less than 10% of memory and less than 25% of computational power, without loss of accuracy, and without creating sparse networks that require special code to run.
Tasks	Neural Network Compression, Transfer Learning
Published	2019-04-11
URL	http://arxiv.org/abs/1904.05982v1
PDF	http://arxiv.org/pdf/1904.05982v1.pdf
PWC	https://paperswithcode.com/paper/cramnet-layer-wise-deep-neural-network
Repo
Framework

Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interaction


Title	Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interaction
Authors	Susanne Trick, Dorothea Koert, Jan Peters, Constantin Rothkopf
Abstract	Assistive robots can potentially improve the quality of life and personal independence of elderly people by supporting everyday life activities. To guarantee a safe and intuitive interaction between human and robot, human intentions need to be recognized automatically. As humans communicate their intentions multimodally, the use of multiple modalities for intention recognition may not just increase the robustness against failure of individual modalities but especially reduce the uncertainty about the intention to be predicted. This is desirable as particularly in direct interaction between robots and potentially vulnerable humans a minimal uncertainty about the situation as well as knowledge about this actual uncertainty is necessary. Thus, in contrast to existing methods, in this work a new approach for multimodal intention recognition is introduced that focuses on uncertainty reduction through classifier fusion. For the four considered modalities speech, gestures, gaze directions and scene objects individual intention classifiers are trained, all of which output a probability distribution over all possible intentions. By combining these output distributions using the Bayesian method Independent Opinion Pool the uncertainty about the intention to be recognized can be decreased. The approach is evaluated in a collaborative human-robot interaction task with a 7-DoF robot arm. The results show that fused classifiers which combine multiple modalities outperform the respective individual base classifiers with respect to increased accuracy, robustness, and reduced uncertainty.
Tasks	Intent Detection
Published	2019-07-04
URL	https://arxiv.org/abs/1907.02426v1
PDF	https://arxiv.org/pdf/1907.02426v1.pdf
PWC	https://paperswithcode.com/paper/multimodal-uncertainty-reduction-for
Repo
Framework

Mutual exclusivity as a challenge for deep neural networks


Title	Mutual exclusivity as a challenge for deep neural networks
Authors	Kanishk Gandhi, Brenden M. Lake
Abstract	Strong inductive biases allow children to learn in fast and adaptable ways. Children use the mutual exclusivity (ME) bias to help disambiguate how words map to referents, assuming that if an object has one label then it does not need another. In this paper, we investigate whether or not standard neural architectures have an ME bias, demonstrating that they lack this learning assumption. Moreover, we show that their inductive biases are poorly matched to lifelong learning formulations of classification and translation. We demonstrate that there is a compelling case for designing neural networks that reason by mutual exclusivity, which remains an open challenge.
Tasks	Machine Translation, Object Recognition
Published	2019-06-24
URL	https://arxiv.org/abs/1906.10197v2
PDF	https://arxiv.org/pdf/1906.10197v2.pdf
PWC	https://paperswithcode.com/paper/mutual-exclusivity-as-a-challenge-for-neural
Repo
Framework

Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector


Title	Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector
Authors	Di Feng, Xiao Wei, Lars Rosenbaum, Atsuto Maki, Klaus Dietmayer
Abstract	Training a deep object detector for autonomous driving requires a huge amount of labeled data. While recording data via on-board sensors such as camera or LiDAR is relatively easy, annotating data is very tedious and time-consuming, especially when dealing with 3D LiDAR points or radar data. Active learning has the potential to minimize human annotation efforts while maximizing the object detector’s performance. In this work, we propose an active learning method to train a LiDAR 3D object detector with the least amount of labeled training data necessary. The detector leverages 2D region proposals generated from the RGB images to reduce the search space of objects and speed up the learning process. Experiments show that our proposed method works under different uncertainty estimations and query functions, and can save up to 60% of the labeling efforts while reaching the same network performance.
Tasks	Active Learning, Autonomous Driving
Published	2019-01-29
URL	https://arxiv.org/abs/1901.10609v2
PDF	https://arxiv.org/pdf/1901.10609v2.pdf
PWC	https://paperswithcode.com/paper/deep-active-learning-for-efficient-training
Repo
Framework

Performing Deep Recurrent Double Q-Learning for Atari Games


Title	Performing Deep Recurrent Double Q-Learning for Atari Games
Authors	Felipe Moreno-Vera
Abstract	Currently, many applications in Machine Learning are based on define new models to extract more information about data, In this case Deep Reinforcement Learning with the most common application in video games like Atari, Mario, and others causes an impact in how to computers can learning by himself with only information called rewards obtained from any action. There is a lot of algorithms modeled and implemented based on Deep Recurrent Q-Learning proposed by DeepMind used in AlphaZero and Go. In this document, We proposed Deep Recurrent Double Q-Learning that is an implementation of Deep Reinforcement Learning using Double Q-Learning algorithms and Recurrent Networks like LSTM and DRQN.
Tasks	Atari Games, Q-Learning
Published	2019-08-16
URL	https://arxiv.org/abs/1908.06040v2
PDF	https://arxiv.org/pdf/1908.06040v2.pdf
PWC	https://paperswithcode.com/paper/performing-deep-recurrent-double-q-learning
Repo
Framework

The Probabilistic Backbone of Data-Driven Complex Networks: An example in Climate


Title	The Probabilistic Backbone of Data-Driven Complex Networks: An example in Climate
Authors	Catharina Graafland, José M. Gutiérrez, Juan M. López, Diego Pazó, Miguel A. Rodríguez
Abstract	Correlation Networks (CNs) inherently suffer from redundant information in their network topology. Bayesian Networks (BNs), on the other hand, include only non-redundant information (from a probabilistic perspective) resulting in a sparse topology from which generalizable physical features can be extracted. We advocate the use of BNs to construct data-driven complex networks as they can be regarded as the probabilistic backbone of the underlying complex system. Results are illustrated at the hand of a global climate dataset.
Tasks
Published	2019-12-08
URL	https://arxiv.org/abs/1912.03758v1
PDF	https://arxiv.org/pdf/1912.03758v1.pdf
PWC	https://paperswithcode.com/paper/the-probabilistic-backbone-of-data-driven
Repo
Framework

Linear Mode Connectivity and the Lottery Ticket Hypothesis


Title	Linear Mode Connectivity and the Lottery Ticket Hypothesis
Authors	Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin
Abstract	We introduce “instability analysis,” which assesses whether a neural network optimizes to the same, linearly connected minimum under different samples of SGD noise. We find that standard vision models become “stable” in this way early in training. From then on, the outcome of optimization is determined to within a linearly connected region. We use instability to study “iterative magnitude pruning” (IMP), the procedure used by work on the lottery ticket hypothesis to identify subnetworks that could have trained to full accuracy from initialization. We find that these subnetworks only reach full accuracy when they are stable, which either occurs at initialization for small-scale settings (MNIST) or early in training for large-scale settings (Resnet-50 and Inception-v3 on ImageNet). This submission subsumes 1903.01611 (“Stabilizing the Lottery Ticket Hypothesis” and “The Lottery Ticket Hypothesis at Scale”)
Tasks
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05671v2
PDF	https://arxiv.org/pdf/1912.05671v2.pdf
PWC	https://paperswithcode.com/paper/linear-mode-connectivity-and-the-lottery
Repo
Framework

Plugin Networks for Inference under Partial Evidence


Title	Plugin Networks for Inference under Partial Evidence
Authors	Michal Koperski, Tomasz Konopczynski, Rafał Nowak, Piotr Semberecki, Tomasz Trzcinski
Abstract	In this paper, we propose a novel method to incorporate partial evidence in the inference of deep convolutional neural networks. Contrary to the existing, top performing methods, which either iteratively modify the input of the network or exploit external label taxonomy to take the partial evidence into account, we add separate network modules (“Plugin Networks”) to the intermediate layers of a pre-trained convolutional network. The goal of these modules is to incorporate additional signal, ie information about known labels, into the inference procedure and adjust the predicted output accordingly. Since the attached plugins have a simple structure, consisting of only fully connected layers, we drastically reduced the computational cost of training and inference. At the same time, the proposed architecture allows to propagate information about known labels directly to the intermediate layers to improve the final representation. Extensive evaluation of the proposed method confirms that our Plugin Networks outperform the state-of-the-art in a variety of tasks, including scene categorization, multi-label image annotation, and semantic segmentation.
Tasks	Semantic Segmentation
Published	2019-01-02
URL	https://arxiv.org/abs/1901.00326v3
PDF	https://arxiv.org/pdf/1901.00326v3.pdf
PWC	https://paperswithcode.com/paper/plugin-networks-for-inference-under-partial
Repo
Framework

On Measuring Gender Bias in Translation of Gender-neutral Pronouns


Title	On Measuring Gender Bias in Translation of Gender-neutral Pronouns
Authors	Won Ik Cho, Ji Won Kim, Seok Min Kim, Nam Soo Kim
Abstract	Ethics regarding social bias has recently thrown striking issues in natural language processing. Especially for gender-related topics, the need for a system that reduces the model bias has grown in areas such as image captioning, content recommendation, and automated employment. However, detection and evaluation of gender bias in the machine translation systems are not yet thoroughly investigated, for the task being cross-lingual and challenging to define. In this paper, we propose a scheme for making up a test set that evaluates the gender bias in a machine translation system, with Korean, a language with gender-neutral pronouns. Three word/phrase sets are primarily constructed, each incorporating positive/negative expressions or occupations; all the terms are gender-independent or at least not biased to one side severely. Then, additional sentence lists are constructed concerning formality of the pronouns and politeness of the sentences. With the generated sentence set of size 4,236 in total, we evaluate gender bias in conventional machine translation systems utilizing the proposed measure, which is termed here as translation gender bias index (TGBI). The corpus and the code for evaluation is available on-line.
Tasks	Image Captioning, Machine Translation
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11684v1
PDF	https://arxiv.org/pdf/1905.11684v1.pdf
PWC	https://paperswithcode.com/paper/on-measuring-gender-bias-in-translation-of
Repo
Framework

Automatic Mass Detection in Breast Using Deep Convolutional Neural Network and SVM Classifier


Title	Automatic Mass Detection in Breast Using Deep Convolutional Neural Network and SVM Classifier
Authors	Md. Kamrul Hasan, Tajwar Abrar Aleef
Abstract	Mammography is the most widely used gold standard for screening breast cancer, where, mass detection is considered as the prominent step. Detecting mass in the breast is, however, an arduous problem as they usually have large variations between them in terms of shape, size, boundary, and texture. In this literature, the process of mass detection is automated with the use of transfer learning techniques of Deep Convolutional Neural Networks (DCNN). Pre-trained VGG19 network is used to extract features which are then followed by bagged decision tree for features selection and then a Support Vector Machine (SVM) classifier is trained and used for classifying between the mass and non-mass. Area Under ROC Curve (AUC) is chosen as the performance metric, which is then maximized during classifier selection and hyper-parameter tuning. The robustness of the two selected type of classifiers, C-SVM, and \u{psion}-SVM, are investigated with extensive experiments before selecting the best performing classifier. All experiments in this paper were conducted using the INbreast dataset. The best AUC obtained from the experimental results is 0.994 +/- 0.003 i.e. [0.991, 0.997]. Our results conclude that by using pre-trained VGG19 network, high-level distinctive features can be extracted from Mammograms which when used with the proposed SVM classifier is able to robustly distinguish between the mass and non-mass present in breast.
Tasks	Transfer Learning
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04424v1
PDF	https://arxiv.org/pdf/1907.04424v1.pdf
PWC	https://paperswithcode.com/paper/automatic-mass-detection-in-breast-using-deep
Repo
Framework

An “outside the box” solution for imbalanced data classification


Title	An “outside the box” solution for imbalanced data classification
Authors	Hubert Jegierski, Stanisław Saganowski
Abstract	A common problem of the real-world data sets is the class imbalance, which can significantly affect the classification abilities of classifiers. Numerous methods have been proposed to cope with this problem; however, even state-of-the-art methods offer a limited improvement (if any) for data sets with critically under-represented minority classes. For such problematic cases, an “outside the box” solution is required. Therefore, we propose a novel technique, called enrichment, which uses the information (observations) from the external data set(s). We present three approaches to implement enrichment technique: (1) selecting observations randomly, (2) iteratively choosing observations that improve the classification result, (3) adding observations that help the classifier to determine the border between classes better. We then thoroughly analyze developed solutions on ten real-world data sets to experimentally validate their usefulness. On average, our best approach improves the classification quality by 27%, and in the best case, by outstanding 66%. We also compare our technique with the universally applicable state-of-the-art methods. We find that our technique surpasses the existing methods performing, on average, 21% better. The advantage is especially noticeable for the smallest data sets, for which existing methods failed, while our solutions achieved the best results. Additionally, our technique applies to both the multi-class and binary classification tasks. It can also be combined with other techniques dealing with the class imbalance problem.
Tasks
Published	2019-11-16
URL	https://arxiv.org/abs/1911.06965v1
PDF	https://arxiv.org/pdf/1911.06965v1.pdf
PWC	https://paperswithcode.com/paper/an-outside-the-box-solution-for-imbalanced
Repo
Framework

Fast and Stable Interval Bounds Propagation for Training Verifiably Robust Models


Title	Fast and Stable Interval Bounds Propagation for Training Verifiably Robust Models
Authors	Paweł Morawiecki, Przemysław Spurek, Marek Śmieja, Jacek Tabor
Abstract	We present an efficient technique, which allows to train classification networks which are verifiably robust against norm-bounded adversarial attacks. This framework is built upon the work of Gowal et al., who applies the interval arithmetic to bound the activations at each layer and keeps the prediction invariant to the input perturbation. While that method is faster than competitive approaches, it requires careful tuning of hyper-parameters and a large number of epochs to converge. To speed up and stabilize training, we supply the cost function with an additional term, which encourages the model to keep the interval bounds at hidden layers small. Experimental results demonstrate that we can achieve comparable (or even better) results using a smaller number of training iterations, in a more stable fashion. Moreover, the proposed model is not so sensitive to the exact specification of the training process, which makes it easier to use by practitioners.
Tasks
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00628v2
PDF	https://arxiv.org/pdf/1906.00628v2.pdf
PWC	https://paperswithcode.com/paper/190600628
Repo
Framework

Intention-aware Long Horizon Trajectory Prediction of Surrounding Vehicles using Dual LSTM Networks


Title	Intention-aware Long Horizon Trajectory Prediction of Surrounding Vehicles using Dual LSTM Networks
Authors	Long Xin, Pin Wang, Ching-Yao Chan, Jianyu Chen, Shengbo Eben Li, Bo Cheng
Abstract	As autonomous vehicles (AVs) need to interact with other road users, it is of importance to comprehensively understand the dynamic traffic environment, especially the future possible trajectories of surrounding vehicles. This paper presents an algorithm for long-horizon trajectory prediction of surrounding vehicles using a dual long short term memory (LSTM) network, which is capable of effectively improving prediction accuracy in strongly interactive driving environments. In contrast to traditional approaches which require trajectory matching and manual feature selection, this method can automatically learn high-level spatial-temporal features of driver behaviors from naturalistic driving data through sequence learning. By employing two blocks of LSTMs, the proposed method feeds the sequential trajectory to the first LSTM for driver intention recognition as an intermediate indicator, which is immediately followed by a second LSTM for future trajectory prediction. Test results from real-world highway driving data show that the proposed method can, in comparison to state-of-art methods, output more accurate and reasonable estimate of different future trajectories over 5s time horizon with root mean square error (RMSE) for longitudinal and lateral prediction less than 5.77m and 0.49m, respectively.
Tasks	Autonomous Vehicles, Feature Selection, Intent Detection, Trajectory Prediction
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02815v1
PDF	https://arxiv.org/pdf/1906.02815v1.pdf
PWC	https://paperswithcode.com/paper/intention-aware-long-horizon-trajectory
Repo
Framework