Paper Group ANR 1078
Semantic RL with Action Grammars: Data-Efficient Learning of Hierarchical Task Abstractions. Constrained Thompson Sampling for Wireless Link Optimization. Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos. A Stochastic Gradient Method with Biased Estimation for Faster Nonconvex Optimization. Analysis Co …
Semantic RL with Action Grammars: Data-Efficient Learning of Hierarchical Task Abstractions
| Title | Semantic RL with Action Grammars: Data-Efficient Learning of Hierarchical Task Abstractions |
| Authors | Robert Tjarko Lange, Aldo Faisal |
| Abstract | Hierarchical Reinforcement Learning algorithms have successfully been applied to temporal credit assignment problems with sparse reward signals. However, state-of-the-art algorithms require manual specification of sub-task structures, a sample inefficient exploration phase or lack semantic interpretability. Humans, on the other hand, efficiently detect hierarchical sub-structures induced by their surroundings. It has been argued that this inference process universally applies to language, logical reasoning as well as motor control. Therefore, we propose a cognitive-inspired Reinforcement Learning architecture which uses grammar induction to identify sub-goal policies. By treating an on-policy trajectory as a sentence sampled from the policy-conditioned language of the environment, we identify hierarchical constituents with the help of unsupervised grammatical inference. The resulting set of temporal abstractions is called action grammar (Pastra & Aloimonos, 2012) and unifies symbolic and connectionist approaches to Reinforcement Learning. It can be used to facilitate efficient imitation, transfer and online learning. |
| Tasks | Hierarchical Reinforcement Learning |
| Published | 2019-07-29 |
| URL | https://arxiv.org/abs/1907.12477v2 |
| https://arxiv.org/pdf/1907.12477v2.pdf | |
| PWC | https://paperswithcode.com/paper/action-grammars-a-cognitive-model-for |
| Repo | |
| Framework | |
Constrained Thompson Sampling for Wireless Link Optimization
| Title | Constrained Thompson Sampling for Wireless Link Optimization |
| Authors | Vidit Saxena, Joakim Jaldén, Joseph E. Gonzalez, Ion Stoica, Hugo Tullberg |
| Abstract | Wireless communication systems operate in complex time-varying environments. Therefore, selecting the optimal configuration parameters in these systems is a challenging problem. For wireless links, rate selection is used to select the optimal data transmission rate that maximizes the link throughput subject to an application-defined latency constraint. We model rate selection as a stochastic multi-armed bandit (MAB) problem, where a finite set of transmission rates are modeled as independent bandit arms. For this setup, we propose Con-TS, a novel constrained version of the Thompson sampling algorithm, where the latency requirement is modeled by a linear constraint on arm selection probabilities. Since our algorithm learns a Bayesian model of the wireless link, it can be adapted to exploit prior knowledge often available in practical wireless networks. Through numerical results from simulated experiments, we demonstrate that Con-TS significantly outperforms state-of-the-art bandit algorithms proposed in the literature. Further, we compare Con-TS with the outer loop link adaptation (OLLA) scheme, which is the state-of-the-art in practical wireless networks and relies on carefully tuned offline link models. We show that Con-TS outperforms OLLA in simulations, further, it can elegantly incorporate information from the offline link models to substantially improve performance. |
| Tasks | |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.11102v1 |
| http://arxiv.org/pdf/1902.11102v1.pdf | |
| PWC | https://paperswithcode.com/paper/constrained-thompson-sampling-for-wireless |
| Repo | |
| Framework | |
Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos
| Title | Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos |
| Authors | Bo Hu, Jianfei Cai, Tat-Jen Cham, Junsong Yuan |
| Abstract | Previous spatial-temporal action localization methods commonly follow the pipeline of object detection to estimate bounding boxes and labels of actions. However, the temporal relation of an action has not been fully explored. In this paper, we propose an end-to-end Progress Regression Recurrent Neural Network (PR-RNN) for online spatial-temporal action localization, which learns to infer the action by temporal progress regression. Two new action attributes, called progression and progress rate, are introduced to describe the temporal engagement and relative temporal position of an action. In our method, frame-level features are first extracted by a Fully Convolutional Network (FCN). Subsequently, detection results and action progress attributes are regressed by the Convolutional Gated Recurrent Unit (ConvGRU) based on all the observed frames instead of a single frame or a short clip. Finally, a novel online linking method is designed to connect single-frame results to spatial-temporal tubes with the help of the estimated action progress attributes. Extensive experiments demonstrate that the progress attributes improve the localization accuracy by providing more precise temporal position of an action in unconstrained videos. Our proposed PR-RNN achieves the stateof-the-art performance for most of the IoU thresholds on two benchmark datasets. |
| Tasks | Action Localization, Object Detection, Temporal Action Localization |
| Published | 2019-03-01 |
| URL | http://arxiv.org/abs/1903.00304v1 |
| http://arxiv.org/pdf/1903.00304v1.pdf | |
| PWC | https://paperswithcode.com/paper/progress-regression-rnn-for-online-spatial |
| Repo | |
| Framework | |
A Stochastic Gradient Method with Biased Estimation for Faster Nonconvex Optimization
| Title | A Stochastic Gradient Method with Biased Estimation for Faster Nonconvex Optimization |
| Authors | Jia Bi, Steve R. Gunn |
| Abstract | A number of optimization approaches have been proposed for optimizing nonconvex objectives (e.g. deep learning models), such as batch gradient descent, stochastic gradient descent and stochastic variance reduced gradient descent. Theory shows these optimization methods can converge by using an unbiased gradient estimator. However, in practice biased gradient estimation can allow more efficient convergence to the vicinity since an unbiased approach is computationally more expensive. To produce fast convergence there are two trade-offs of these optimization strategies which are between stochastic/batch, and between biased/unbiased. This paper proposes an integrated approach which can control the nature of the stochastic element in the optimizer and can balance the trade-off of estimator between the biased and unbiased by using a hyper-parameter. It is shown theoretically and experimentally that this hyper-parameter can be configured to provide an effective balance to improve the convergence rate. |
| Tasks | |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.05185v1 |
| https://arxiv.org/pdf/1905.05185v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-stochastic-gradient-method-with-biased |
| Repo | |
| Framework | |
Analysis Co-Sparse Coding for Energy Disaggregation
| Title | Analysis Co-Sparse Coding for Energy Disaggregation |
| Authors | Shikha Singh, Angshul Majumdar |
| Abstract | Energy disaggregation is the task of segregating the aggregate energy of the entire building (as logged by the smartmeter) into the energy consumed by individual appliances. This is a single channel (the only channel being the smart-meter) blind source (different electrical appliances) separation problem. In recent times dictionary learning based approaches have shown promise in addressing the disaggregation problem. The usual technique is to learn a dictionary for every device and use the learnt dictionaries as basis for blind source separation during disaggregation. Dictionary learning is a synthesis formulation; in this work, we propose an analysis approach. The advantage of our proposed approach is that, the requirement of training volume drastically reduces compared to state-of-the-art techniques. This means that, we require fewer instrumented homes, or fewer days of instrumentation per home; in either case this drastically reduces the sensing cost. Results on two benchmark datasets show that our method produces the same level of disaggregation accuracy as state-of-the-art methods but with only a fraction of the training data. |
| Tasks | Dictionary Learning |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.12130v1 |
| https://arxiv.org/pdf/1912.12130v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-co-sparse-coding-for-energy |
| Repo | |
| Framework | |
Semantic Feature Attention Network for Liver Tumor Segmentation in Large-scale CT database
| Title | Semantic Feature Attention Network for Liver Tumor Segmentation in Large-scale CT database |
| Authors | Yao Zhang, Cheng Zhong, Yang Zhang, Zhongchao Shi, Zhiqiang He |
| Abstract | Liver tumor segmentation plays an important role in hepatocellular carcinoma diagnosis and surgical planning. In this paper, we propose a novel Semantic Feature Attention Network (SFAN) for liver tumor segmentation from Computed Tomography (CT) volumes, which exploits the impact of both low-level and high-level features. In the SFAN, a Semantic Attention Transmission (SAT) module is designed to select discriminative low-level localization details with the guidance of neighboring high-level semantic information. Furthermore, a Global Context Attention (GCA) module is proposed to effectively fuse the multi-level features with the guidance of global context. Our experiments are based on 2 challenging databases, the public Liver Tumor Segmentation (LiTS) Challenge database and a large-scale in-house clinical database with 912 CT volumes. Experimental results show that our proposed framework can not only achieve the state-of-the-art performance with the Dice per case on liver tumor segmentation in LiTS database, but also outperform some widely used segmentation algorithms in the large-scale clinical database. |
| Tasks | Computed Tomography (CT) |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.00282v1 |
| https://arxiv.org/pdf/1911.00282v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-feature-attention-network-for-liver |
| Repo | |
| Framework | |
Reconstructing Multi-echo Magnetic Resonance Images via Structured Deep Dictionary Learning
| Title | Reconstructing Multi-echo Magnetic Resonance Images via Structured Deep Dictionary Learning |
| Authors | Vanika Singhal, Angshul Majumdar |
| Abstract | Multi-echo magnetic resonance (MR) images are acquired by changing the echo times (for T2 weighted) or relaxation times (for T1 weighted) of scans. The resulting (multi-echo) images are usually used for quantitative MR imaging. Acquiring MR images is a slow process and acquiring multi scans of the same cross section for multi-echo imaging is even slower. In order to accelerate the scan, compressed sensing (CS) based techniques have been advocating partial K-space (Fourier domain) scans; the resulting images are reconstructed via structured CS algorithms. In recent times, it has been shown that instead of using off-the-shelf CS, better results can be obtained by adaptive reconstruction algorithms based on structured dictionary learning. In this work, we show that the reconstruction results can be further improved by using structured deep dictionaries. Experimental results on real datasets show that by using our proposed technique the scan-time can be cut by half compared to the state-of-the-art. |
| Tasks | Dictionary Learning |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04690v1 |
| https://arxiv.org/pdf/1912.04690v1.pdf | |
| PWC | https://paperswithcode.com/paper/reconstructing-multi-echo-magnetic-resonance |
| Repo | |
| Framework | |
A Scalable Multilabel Classification to Deploy Deep Learning Architectures For Edge Devices
| Title | A Scalable Multilabel Classification to Deploy Deep Learning Architectures For Edge Devices |
| Authors | Tolulope A. Odetola, Ogheneuriri Oderhohwo, Syed Rafay Hasan |
| Abstract | Convolution Neural Networks (CNN) have performed well in many applications such as object detection, pattern recognition, video surveillance and so on. CNN carryout feature extraction on labelled data to perform classification. Multi-label classification assigns more than one label to a particular data sample in a data set. In multi-label classification, properties of a data point that are considered to be mutually exclusive are classified. However, existing multi-label classification requires some form of data pre-processing that involves image training data cropping or image tiling. The computation and memory requirement of these multi-label CNN models makes their deployment on edge devices challenging. In this paper, we propose a methodology that solves this problem by extending the capability of existing multi-label classification and provide models with lower latency that requires smaller memory size when deployed on edge devices. We make use of a single CNN model designed with multiple loss layers and multiple accuracy layers. This methodology is tested on state-of-the-art deep learning algorithms such as AlexNet, GoogleNet and SqueezeNet using the Stanford Cars Dataset and deployed on Raspberry Pi3. From the results the proposed methodology achieves comparable accuracy with 1.8x less MACC operation, 0.97x reduction in latency and 0.5x, 0.84x and 0.97x reduction in size for the generated AlexNet, GoogleNet and SqueezeNet CNN models respectively when compared to conventional ways of achieving multi-label classification like hard-coding multi-label instances into single labels. The methodology also yields CNN models that achieve 50% less MACC operations, 50% reduction in latency and size of generated versions of AlexNet, GoogleNet and SqueezeNet respectively when compared to conventional ways using 2 different single-labelled models to achieve multi-label classification. |
| Tasks | Multi-Label Classification, Object Detection |
| Published | 2019-11-05 |
| URL | https://arxiv.org/abs/1911.02098v2 |
| https://arxiv.org/pdf/1911.02098v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-scalable-multilabel-classification-to |
| Repo | |
| Framework | |
MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims
| Title | MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims |
| Authors | Isabelle Augenstein, Christina Lioma, Dongsheng Wang, Lucas Chaves Lima, Casper Hansen, Christian Hansen, Jakob Grue Simonsen |
| Abstract | We contribute the largest publicly available dataset of naturally occurring factual claims for the purpose of automatic claim verification. It is collected from 26 fact checking websites in English, paired with textual sources and rich metadata, and labelled for veracity by human expert journalists. We present an in-depth analysis of the dataset, highlighting characteristics and challenges. Further, we present results for automatic veracity prediction, both with established baselines and with a novel method for joint ranking of evidence pages and predicting veracity that outperforms all baselines. Significant performance increases are achieved by encoding evidence, and by modelling metadata. Our best-performing model achieves a Macro F1 of 49.2%, showing that this is a challenging testbed for claim veracity prediction. |
| Tasks | |
| Published | 2019-09-07 |
| URL | https://arxiv.org/abs/1909.03242v2 |
| https://arxiv.org/pdf/1909.03242v2.pdf | |
| PWC | https://paperswithcode.com/paper/multifc-a-real-world-multi-domain-dataset-for |
| Repo | |
| Framework | |
Robustness to Adversarial Perturbations in Learning from Incomplete Data
| Title | Robustness to Adversarial Perturbations in Learning from Incomplete Data |
| Authors | Amir Najafi, Shin-ichi Maeda, Masanori Koyama, Takeru Miyato |
| Abstract | What is the role of unlabeled data in an inference problem, when the presumed underlying distribution is adversarially perturbed? To provide a concrete answer to this question, this paper unifies two major learning frameworks: Semi-Supervised Learning (SSL) and Distributionally Robust Learning (DRL). We develop a generalization theory for our framework based on a number of novel complexity measures, such as an adversarial extension of Rademacher complexity and its semi-supervised analogue. Moreover, our analysis is able to quantify the role of unlabeled data in the generalization under a more general condition compared to the existing theoretical works in SSL. Based on our framework, we also present a hybrid of DRL and EM algorithms that has a guaranteed convergence rate. When implemented with deep neural networks, our method shows a comparable performance to those of the state-of-the-art on a number of real-world benchmark datasets. |
| Tasks | |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.13021v1 |
| https://arxiv.org/pdf/1905.13021v1.pdf | |
| PWC | https://paperswithcode.com/paper/190513021 |
| Repo | |
| Framework | |
Towards continuous learning for glioma segmentation with elastic weight consolidation
| Title | Towards continuous learning for glioma segmentation with elastic weight consolidation |
| Authors | Karin van Garderen, Sebastian van der Voort, Fatih Incekara, Marion Smits, Stefan Klein |
| Abstract | When finetuning a convolutional neural network (CNN) on data from a new domain, catastrophic forgetting will reduce performance on the original training data. Elastic Weight Consolidation (EWC) is a recent technique to prevent this, which we evaluated while training and re-training a CNN to segment glioma on two different datasets. The network was trained on the public BraTS dataset and finetuned on an in-house dataset with non-enhancing low-grade glioma. EWC was found to decrease catastrophic forgetting in this case, but was also found to restrict adaptation to the new domain. |
| Tasks | |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11479v1 |
| https://arxiv.org/pdf/1909.11479v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-continuous-learning-for-glioma |
| Repo | |
| Framework | |
F-measure Maximizing Logistic Regression
| Title | F-measure Maximizing Logistic Regression |
| Authors | Masaaki Okabe, Jun Tsuchida, Hiroshi Yadohisa |
| Abstract | Logistic regression is a widely used method in several fields. When applying logistic regression to imbalanced data, for which majority classes dominate over minority classes, all class labels are estimated as `majority class.’ In this article, we use an F-measure optimization method to improve the performance of logistic regression applied to imbalanced data. While many F-measure optimization methods adopt a ratio of the estimators to approximate the F-measure, the ratio of the estimators tends to have more bias than when the ratio is directly approximated. Therefore, we employ an approximate F-measure for estimating the relative density ratio. In addition, we define a relative F-measure and approximate the relative F-measure. We show an algorithm for a logistic regression weighted approximated relative to the F-measure. The experimental results using real world data demonstrated that our proposed method is an efficient algorithm to improve the performance of logistic regression applied to imbalanced data. | |
| Tasks | |
| Published | 2019-05-07 |
| URL | https://arxiv.org/abs/1905.02535v1 |
| https://arxiv.org/pdf/1905.02535v1.pdf | |
| PWC | https://paperswithcode.com/paper/f-measure-maximizing-logistic-regression |
| Repo | |
| Framework | |
Unsupervised Adversarial Attacks on Deep Feature-based Retrieval with GAN
| Title | Unsupervised Adversarial Attacks on Deep Feature-based Retrieval with GAN |
| Authors | Guoping Zhao, Mingyu Zhang, Jiajun Liu, Ji-Rong Wen |
| Abstract | Studies show that Deep Neural Network (DNN)-based image classification models are vulnerable to maliciously constructed adversarial examples. However, little effort has been made to investigate how DNN-based image retrieval models are affected by such attacks. In this paper, we introduce Unsupervised Adversarial Attacks with Generative Adversarial Networks (UAA-GAN) to attack deep feature-based image retrieval systems. UAA-GAN is an unsupervised learning model that requires only a small amount of unlabeled data for training. Once trained, it produces query-specific perturbations for query images to form adversarial queries. The core idea is to ensure that the attached perturbation is barely perceptible to human yet effective in pushing the query away from its original position in the deep feature space. UAA-GAN works with various application scenarios that are based on deep features, including image retrieval, person Re-ID and face search. Empirical results show that UAA-GAN cripples retrieval performance without significant visual changes in the query images. UAA-GAN generated adversarial examples are less distinguishable because they tend to incorporate subtle perturbations in textured or salient areas of the images, such as key body parts of human, dominant structural patterns/textures or edges, rather than in visually insignificant areas (e.g., background and sky). Such tendency indicates that the model indeed learned how to toy with both image retrieval systems and human eyes. |
| Tasks | Image Classification, Image Retrieval |
| Published | 2019-07-12 |
| URL | https://arxiv.org/abs/1907.05793v1 |
| https://arxiv.org/pdf/1907.05793v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-adversarial-attacks-on-deep |
| Repo | |
| Framework | |
Hierarchical Feature Aggregation Networks for Video Action Recognition
| Title | Hierarchical Feature Aggregation Networks for Video Action Recognition |
| Authors | Swathikiran Sudhakaran, Sergio Escalera, Oswald Lanz |
| Abstract | Most action recognition methods base on a) a late aggregation of frame level CNN features using average pooling, max pooling, or RNN, among others, or b) spatio-temporal aggregation via 3D convolutions. The first assume independence among frame features up to a certain level of abstraction and then perform higher-level aggregation, while the second extracts spatio-temporal features from grouped frames as early fusion. In this paper we explore the space in between these two, by letting adjacent feature branches interact as they develop into the higher level representation. The interaction happens between feature differencing and averaging at each level of the hierarchy, and it has convolutional structure that learns to select the appropriate mode locally in contrast to previous works that impose one of the modes globally (e.g. feature differencing) as a design choice. We further constrain this interaction to be conservative, e.g. a local feature subtraction in one branch is compensated by the addition on another, such that the total feature flow is preserved. We evaluate the performance of our proposal on a number of existing models, i.e. TSN, TRN and ECO, to show its flexibility and effectiveness in improving action recognition performance. |
| Tasks | Action Recognition In Videos, Temporal Action Localization |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12462v1 |
| https://arxiv.org/pdf/1905.12462v1.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-feature-aggregation-networks-for |
| Repo | |
| Framework | |
Deep Retrieval-Based Dialogue Systems: A Short Review
| Title | Deep Retrieval-Based Dialogue Systems: A Short Review |
| Authors | Basma El Amel Boussaha, Nicolas Hernandez, Christine Jacquin, Emmanuel Morin |
| Abstract | Building dialogue systems that naturally converse with humans is being an attractive and an active research domain. Multiple systems are being designed everyday and several datasets are being available. For this reason, it is being hard to keep an up-to-date state-of-the-art. In this work, we present the latest and most relevant retrieval-based dialogue systems and the available datasets used to build and evaluate them. We discuss their limitations and provide insights and guidelines for future work. |
| Tasks | |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.12878v1 |
| https://arxiv.org/pdf/1907.12878v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-retrieval-based-dialogue-systems-a-short |
| Repo | |
| Framework | |
