Paper Group ANR 986
Human-Centered Autonomous Vehicle Systems: Principles of Effective Shared Autonomy. Co-training for Extraction of Adverse Drug Reaction Mentions from Tweets. Guided Zoom: Questioning Network Evidence for Fine-grained Classification. A Nonconvex Projection Method for Robust PCA. Are Efficient Deep Representations Learnable?. Long-term face tracking …
Human-Centered Autonomous Vehicle Systems: Principles of Effective Shared Autonomy
Title | Human-Centered Autonomous Vehicle Systems: Principles of Effective Shared Autonomy |
Authors | Lex Fridman |
Abstract | Building effective, enjoyable, and safe autonomous vehicles is a lot harder than has historically been considered. The reason is that, simply put, an autonomous vehicle must interact with human beings. This interaction is not a robotics problem nor a machine learning problem nor a psychology problem nor an economics problem nor a policy problem. It is all of these problems put into one. It challenges our assumptions about the limitations of human beings at their worst and the capabilities of artificial intelligence systems at their best. This work proposes a set of principles for designing and building autonomous vehicles in a human-centered way that does not run away from the complexity of human nature but instead embraces it. We describe our development of the Human-Centered Autonomous Vehicle (HCAV) as an illustrative case study of implementing these principles in practice. |
Tasks | Autonomous Vehicles |
Published | 2018-10-03 |
URL | http://arxiv.org/abs/1810.01835v1 |
http://arxiv.org/pdf/1810.01835v1.pdf | |
PWC | https://paperswithcode.com/paper/human-centered-autonomous-vehicle-systems |
Repo | |
Framework | |
Co-training for Extraction of Adverse Drug Reaction Mentions from Tweets
Title | Co-training for Extraction of Adverse Drug Reaction Mentions from Tweets |
Authors | Shashank Gupta, Manish Gupta, Vasudeva Varma, Sachin Pawar, Nitin Ramrakhiyani, Girish K. Palshikar |
Abstract | Adverse drug reactions (ADRs) are one of the leading causes of mortality in health care. Current ADR surveillance systems are often associated with a substantial time lag before such events are officially published. On the other hand, online social media such as Twitter contain information about ADR events in real-time, much before any official reporting. Current state-of-the-art methods in ADR mention extraction use Recurrent Neural Networks (RNN), which typically need large labeled corpora. Towards this end, we propose a semi-supervised method based on co-training which can exploit a large pool of unlabeled tweets to augment the limited supervised training data, and as a result enhance the performance. Experiments with 0.1M tweets show that the proposed approach outperforms the state-of-the-art methods for the ADR mention extraction task by 5% in terms of F1 score. |
Tasks | |
Published | 2018-02-14 |
URL | http://arxiv.org/abs/1802.05121v1 |
http://arxiv.org/pdf/1802.05121v1.pdf | |
PWC | https://paperswithcode.com/paper/co-training-for-extraction-of-adverse-drug |
Repo | |
Framework | |
Guided Zoom: Questioning Network Evidence for Fine-grained Classification
Title | Guided Zoom: Questioning Network Evidence for Fine-grained Classification |
Authors | Sarah Adel Bargal, Andrea Zunino, Vitali Petsiuk, Jianming Zhang, Kate Saenko, Vittorio Murino, Stan Sclaroff |
Abstract | We propose Guided Zoom, an approach that utilizes spatial grounding of a model’s decision to make more informed predictions. It does so by making sure the model has “the right reasons” for a prediction, defined as reasons that are coherent with those used to make similar correct decisions at training time. The reason/evidence upon which a deep convolutional neural network makes a prediction is defined to be the spatial grounding, in the pixel space, for a specific class conditional probability in the model output. Guided Zoom examines how reasonable such evidence is for each of the top-k predicted classes, rather than solely trusting the top-1 prediction. We show that Guided Zoom improves the classification accuracy of a deep convolutional neural network model and obtains state-of-the-art results on three fine-grained classification benchmark datasets. |
Tasks | |
Published | 2018-12-06 |
URL | https://arxiv.org/abs/1812.02626v2 |
https://arxiv.org/pdf/1812.02626v2.pdf | |
PWC | https://paperswithcode.com/paper/guided-zoom-questioning-network-evidence-for |
Repo | |
Framework | |
A Nonconvex Projection Method for Robust PCA
Title | A Nonconvex Projection Method for Robust PCA |
Authors | Aritra Dutta, Filip Hanzely, Peter Richtárik |
Abstract | Robust principal component analysis (RPCA) is a well-studied problem with the goal of decomposing a matrix into the sum of low-rank and sparse components. In this paper, we propose a nonconvex feasibility reformulation of RPCA problem and apply an alternating projection method to solve it. To the best of our knowledge, we are the first to propose a method that solves RPCA problem without considering any objective function, convex relaxation, or surrogate convex constraints. We demonstrate through extensive numerical experiments on a variety of applications, including shadow removal, background estimation, face detection, and galaxy evolution, that our approach matches and often significantly outperforms current state-of-the-art in various ways. |
Tasks | Face Detection |
Published | 2018-05-21 |
URL | https://arxiv.org/abs/1805.07962v2 |
https://arxiv.org/pdf/1805.07962v2.pdf | |
PWC | https://paperswithcode.com/paper/a-nonconvex-projection-method-for-robust-pca |
Repo | |
Framework | |
Are Efficient Deep Representations Learnable?
Title | Are Efficient Deep Representations Learnable? |
Authors | Maxwell Nye, Andrew Saxe |
Abstract | Many theories of deep learning have shown that a deep network can require dramatically fewer resources to represent a given function compared to a shallow network. But a question remains: can these efficient representations be learned using current deep learning techniques? In this work, we test whether standard deep learning methods can in fact find the efficient representations posited by several theories of deep representation. Specifically, we train deep neural networks to learn two simple functions with known efficient solutions: the parity function and the fast Fourier transform. We find that using gradient-based optimization, a deep network does not learn the parity function, unless initialized very close to a hand-coded exact solution. We also find that a deep linear neural network does not learn the fast Fourier transform, even in the best-case scenario of infinite training data, unless the weights are initialized very close to the exact hand-coded solution. Our results suggest that not every element of the class of compositional functions can be learned efficiently by a deep network, and further restrictions are necessary to understand what functions are both efficiently representable and learnable. |
Tasks | |
Published | 2018-07-17 |
URL | http://arxiv.org/abs/1807.06399v1 |
http://arxiv.org/pdf/1807.06399v1.pdf | |
PWC | https://paperswithcode.com/paper/are-efficient-deep-representations-learnable |
Repo | |
Framework | |
Long-term face tracking in the wild using deep learning
Title | Long-term face tracking in the wild using deep learning |
Authors | Kunlei Zhang, Elaheh Rashedi, Elaheh Barati, Xue-wen Chen |
Abstract | This paper investigates long-term face tracking of a specific person given his/her face image in a single frame as a query in a video stream. Through taking advantage of pre-trained deep learning models on big data, a novel system is developed for accurate video face tracking in the unconstrained environments depicting various people and objects moving in and out of the frame. In the proposed system, we present a detection-verification-tracking method (dubbed as ‘DVT’) which accomplishes the long-term face tracking task through the collaboration of face detection, face verification, and (short-term) face tracking. An offline trained detector based on cascaded convolutional neural networks localizes all faces appeared in the frames, and an offline trained face verifier based on deep convolutional neural networks and similarity metric learning decides if any face or which face corresponds to the queried person. An online trained tracker follows the face from frame to frame. When validated on a sitcom episode and a TV show, the DVT method outperforms tracking-learning-detection (TLD) and face-TLD in terms of recall and precision. The proposed system is also tested on many other types of videos and shows very promising results. |
Tasks | Face Detection, Face Verification, Metric Learning |
Published | 2018-05-19 |
URL | http://arxiv.org/abs/1805.07646v1 |
http://arxiv.org/pdf/1805.07646v1.pdf | |
PWC | https://paperswithcode.com/paper/long-term-face-tracking-in-the-wild-using |
Repo | |
Framework | |
Anchor Cascade for Efficient Face Detection
Title | Anchor Cascade for Efficient Face Detection |
Authors | Baosheng Yu, Dacheng Tao |
Abstract | Face detection is essential to facial analysis tasks such as facial reenactment and face recognition. Both cascade face detectors and anchor-based face detectors have translated shining demos into practice and received intensive attention from the community. However, cascade face detectors often suffer from a low detection accuracy, while anchor-based face detectors rely heavily on very large networks pre-trained on large scale image classification datasets such as ImageNet [1], which is not computationally efficient for both training and deployment. In this paper, we devise an efficient anchor-based cascade framework called anchor cascade. To improve the detection accuracy by exploring contextual information, we further propose a context pyramid maxout mechanism for anchor cascade. As a result, anchor cascade can train very efficient face detection models with a high detection accuracy. Specifically, comparing with a popular CNN-based cascade face detector MTCNN [2], our anchor cascade face detector greatly improves the detection accuracy, e.g., from 0.9435 to 0.9704 at 1k false positives on FDDB, while it still runs in comparable speed. Experimental results on two widely used face detection benchmarks, FDDB and WIDER FACE, demonstrate the effectiveness of the proposed framework. |
Tasks | Face Detection, Face Recognition, Image Classification |
Published | 2018-05-09 |
URL | http://arxiv.org/abs/1805.03363v1 |
http://arxiv.org/pdf/1805.03363v1.pdf | |
PWC | https://paperswithcode.com/paper/anchor-cascade-for-efficient-face-detection |
Repo | |
Framework | |
Input and Weight Space Smoothing for Semi-supervised Learning
Title | Input and Weight Space Smoothing for Semi-supervised Learning |
Authors | Safa Cicek, Stefano Soatto |
Abstract | We propose regularizing the empirical loss for semi-supervised learning by acting on both the input (data) space, and the weight (parameter) space. We show that the two are not equivalent, and in fact are complementary, one affecting the minimality of the resulting representation, the other insensitivity to nuisance variability. We propose a method to perform such smoothing, which combines known input-space smoothing with a novel weight-space smoothing, based on a min-max (adversarial) optimization. The resulting Adversarial Block Coordinate Descent (ABCD) algorithm performs gradient ascent with a small learning rate for a random subset of the weights, and standard gradient descent on the remaining weights in the same mini-batch. It achieves comparable performance to the state-of-the-art without resorting to heavy data augmentation, using a relatively simple architecture. |
Tasks | Data Augmentation |
Published | 2018-05-23 |
URL | http://arxiv.org/abs/1805.09302v1 |
http://arxiv.org/pdf/1805.09302v1.pdf | |
PWC | https://paperswithcode.com/paper/input-and-weight-space-smoothing-for-semi |
Repo | |
Framework | |
A Practical Approach to Sizing Neural Networks
Title | A Practical Approach to Sizing Neural Networks |
Authors | Gerald Friedland, Alfredo Metere, Mario Krell |
Abstract | Memorization is worst-case generalization. Based on MacKay’s information theoretic model of supervised machine learning, this article discusses how to practically estimate the maximum size of a neural network given a training data set. First, we present four easily applicable rules to analytically determine the capacity of neural network architectures. This allows the comparison of the efficiency of different network architectures independently of a task. Second, we introduce and experimentally validate a heuristic method to estimate the neural network capacity requirement for a given dataset and labeling. This allows an estimate of the required size of a neural network for a given problem. We conclude the article with a discussion on the consequences of sizing the network wrongly, which includes both increased computation effort for training as well as reduced generalization capability. |
Tasks | |
Published | 2018-10-04 |
URL | http://arxiv.org/abs/1810.02328v1 |
http://arxiv.org/pdf/1810.02328v1.pdf | |
PWC | https://paperswithcode.com/paper/a-practical-approach-to-sizing-neural |
Repo | |
Framework | |
Reproducible evaluation of classification methods in Alzheimer’s disease: framework and application to MRI and PET data
Title | Reproducible evaluation of classification methods in Alzheimer’s disease: framework and application to MRI and PET data |
Authors | Jorge Samper-González, Ninon Burgos, Simona Bottani, Sabrina Fontanella, Pascal Lu, Arnaud Marcoux, Alexandre Routier, Jérémy Guillon, Michael Bacci, Junhao Wen, Anne Bertrand, Hugo Bertin, Marie-Odile Habert, Stanley Durrleman, Theodoros Evgeniou, Olivier Colliot, for the Alzheimer’s Disease Neuroimaging Initiative, the Australian Imaging Biomarkers, Lifestyle flagship study of ageing |
Abstract | A large number of papers have introduced novel machine learning and feature extraction methods for automatic classification of AD. However, they are difficult to reproduce because key components of the validation are often not readily available. These components include selected participants and input data, image preprocessing and cross-validation procedures. The performance of the different approaches is also difficult to compare objectively. In particular, it is often difficult to assess which part of the method provides a real improvement, if any. We propose a framework for reproducible and objective classification experiments in AD using three publicly available datasets (ADNI, AIBL and OASIS). The framework comprises: i) automatic conversion of the three datasets into BIDS format, ii) a modular set of preprocessing pipelines, feature extraction and classification methods, together with an evaluation framework, that provide a baseline for benchmarking the different components. We demonstrate the use of the framework for a large-scale evaluation on 1960 participants using T1 MRI and FDG PET data. In this evaluation, we assess the influence of different modalities, preprocessing, feature types, classifiers, training set sizes and datasets. Performances were in line with the state-of-the-art. FDG PET outperformed T1 MRI for all classification tasks. No difference in performance was found for the use of different atlases, image smoothing, partial volume correction of FDG PET images, or feature type. Linear SVM and L2-logistic regression resulted in similar performance and both outperformed random forests. The classification performance increased along with the number of subjects used for training. Classifiers trained on ADNI generalized well to AIBL and OASIS. All the code of the framework and the experiments is publicly available at: https://gitlab.icm-institute.org/aramislab/AD-ML. |
Tasks | |
Published | 2018-08-20 |
URL | http://arxiv.org/abs/1808.06452v1 |
http://arxiv.org/pdf/1808.06452v1.pdf | |
PWC | https://paperswithcode.com/paper/reproducible-evaluation-of-classification |
Repo | |
Framework | |
A Study on Overfitting in Deep Reinforcement Learning
Title | A Study on Overfitting in Deep Reinforcement Learning |
Authors | Chiyuan Zhang, Oriol Vinyals, Remi Munos, Samy Bengio |
Abstract | Recent years have witnessed significant progresses in deep Reinforcement Learning (RL). Empowered with large scale neural networks, carefully designed architectures, novel training algorithms and massively parallel computing devices, researchers are able to attack many challenging RL problems. However, in machine learning, more training power comes with a potential risk of more overfitting. As deep RL techniques are being applied to critical problems such as healthcare and finance, it is important to understand the generalization behaviors of the trained agents. In this paper, we conduct a systematic study of standard RL agents and find that they could overfit in various ways. Moreover, overfitting could happen “robustly”: commonly used techniques in RL that add stochasticity do not necessarily prevent or detect overfitting. In particular, the same agents and learning algorithms could have drastically different test performance, even when all of them achieve optimal rewards during training. The observations call for more principled and careful evaluation protocols in RL. We conclude with a general discussion on overfitting in RL and a study of the generalization behaviors from the perspective of inductive bias. |
Tasks | |
Published | 2018-04-18 |
URL | http://arxiv.org/abs/1804.06893v2 |
http://arxiv.org/pdf/1804.06893v2.pdf | |
PWC | https://paperswithcode.com/paper/a-study-on-overfitting-in-deep-reinforcement |
Repo | |
Framework | |
Information Planning for Text Data
Title | Information Planning for Text Data |
Authors | Vadim Smolyakov |
Abstract | Information planning enables faster learning with fewer training examples. It is particularly applicable when training examples are costly to obtain. This work examines the advantages of information planning for text data by focusing on three supervised models: Naive Bayes, supervised LDA and deep neural networks. We show that planning based on entropy and mutual information outperforms random selection baseline and therefore accelerates learning. |
Tasks | |
Published | 2018-02-09 |
URL | http://arxiv.org/abs/1802.03360v3 |
http://arxiv.org/pdf/1802.03360v3.pdf | |
PWC | https://paperswithcode.com/paper/information-planning-for-text-data |
Repo | |
Framework | |
An empirical study on hyperparameter tuning of decision trees
Title | An empirical study on hyperparameter tuning of decision trees |
Authors | Rafael Gomes Mantovani, Tomáš Horváth, Ricardo Cerri, Sylvio Barbon Junior, Joaquin Vanschoren, André Carlos Ponce de Leon Ferreira de Carvalho |
Abstract | Machine learning algorithms often contain many hyperparameters whose values affect the predictive performance of the induced models in intricate ways. Due to the high number of possibilities for these hyperparameter configurations, and their complex interactions, it is common to use optimization techniques to find settings that lead to high predictive accuracy. However, we lack insight into how to efficiently explore this vast space of configurations: which are the best optimization techniques, how should we use them, and how significant is their effect on predictive or runtime performance? This paper provides a comprehensive approach for investigating the effects of hyperparameter tuning on three Decision Tree induction algorithms, CART, C4.5 and CTree. These algorithms were selected because they are based on similar principles, have presented a high predictive performance in several previous works and induce interpretable classification models. Additionally, they contain many interacting hyperparameters to be adjusted. Experiments were carried out with different tuning strategies to induce models and evaluate the relevance of hyperparameters using 94 classification datasets from OpenML. Experimental results indicate that hyperparameter tuning provides statistically significant improvements for C4.5 and CTree in only one-third of the datasets, and in most of the datasets for CART. Different tree algorithms may present different tuning scenarios, but in general, the tuning techniques required relatively few iterations to find accurate solutions. Furthermore, the best technique for all the algorithms was the Irace. Finally, we find that tuning a specific small subset of hyperparameters contributes most of the achievable optimal predictive performance. |
Tasks | |
Published | 2018-12-05 |
URL | http://arxiv.org/abs/1812.02207v2 |
http://arxiv.org/pdf/1812.02207v2.pdf | |
PWC | https://paperswithcode.com/paper/an-empirical-study-on-hyperparameter-tuning |
Repo | |
Framework | |
Multi-task Learning of Cascaded CNN for Facial Attribute Classification
Title | Multi-task Learning of Cascaded CNN for Facial Attribute Classification |
Authors | Ni Zhuang, Yan Yan, Si Chen, Hanzi Wang |
Abstract | Recently, facial attribute classification (FAC) has attracted significant attention in the computer vision community. Great progress has been made along with the availability of challenging FAC datasets. However, conventional FAC methods usually firstly pre-process the input images (i.e., perform face detection and alignment) and then predict facial attributes. These methods ignore the inherent dependencies among these tasks (i.e., face detection, facial landmark localization and FAC). Moreover, some methods using convolutional neural network are trained based on the fixed loss weights without considering the differences between facial attributes. In order to address the above problems, we propose a novel multi-task learning of cas- caded convolutional neural network method, termed MCFA, for predicting multiple facial attributes simultaneously. Specifically, the proposed method takes advantage of three cascaded sub-networks (i.e., S_Net, M_Net and L_Net corresponding to the neural networks under different scales) to jointly train multiple tasks in a coarse-to-fine manner, which can achieve end-to-end optimization. Furthermore, the proposed method automatically assigns the loss weight to each facial attribute based on a novel dynamic weighting scheme, thus making the proposed method concentrate on predicting the more difficult facial attributes. Experimental results show that the proposed method outperforms several state-of-the-art FAC methods on the challenging CelebA and LFWA datasets. |
Tasks | Face Alignment, Face Detection, Facial Attribute Classification, Multi-Task Learning |
Published | 2018-05-03 |
URL | http://arxiv.org/abs/1805.01290v1 |
http://arxiv.org/pdf/1805.01290v1.pdf | |
PWC | https://paperswithcode.com/paper/multi-task-learning-of-cascaded-cnn-for |
Repo | |
Framework | |
Structural query-by-committee
Title | Structural query-by-committee |
Authors | Christopher Tosh, Sanjoy Dasgupta |
Abstract | In this work, we describe a framework that unifies many different interactive learning tasks. We present a generalization of the {\it query-by-committee} active learning algorithm for this setting, and we study its consistency and rate of convergence, both theoretically and empirically, with and without noise. |
Tasks | Active Learning |
Published | 2018-03-17 |
URL | http://arxiv.org/abs/1803.06586v1 |
http://arxiv.org/pdf/1803.06586v1.pdf | |
PWC | https://paperswithcode.com/paper/structural-query-by-committee |
Repo | |
Framework | |