Paper Group ANR 351
Kernel-Induced Label Propagation by Mapping for Semi-Supervised Classification. A deep learning approach for analyzing the composition of chemometric data. Increasing Expressivity of a Hyperspherical VAE. Real-Time Freespace Segmentation on Autonomous Robots for Detection of Obstacles and Drop-Offs. AC-Teach: A Bayesian Actor-Critic Method for Poli …
Kernel-Induced Label Propagation by Mapping for Semi-Supervised Classification
| Title | Kernel-Induced Label Propagation by Mapping for Semi-Supervised Classification |
| Authors | Zhao Zhang, Lei Jia, Mingbo Zhao, Guangcan Liu, Meng Wang, Shuicheng Yan |
| Abstract | Kernel methods have been successfully applied to the areas of pattern recognition and data mining. In this paper, we mainly discuss the issue of propagating labels in kernel space. A Kernel-Induced Label Propagation (Kernel-LP) framework by mapping is proposed for high-dimensional data classification using the most informative patterns of data in kernel space. The essence of Kernel-LP is to perform joint label propagation and adaptive weight learning in a transformed kernel space. That is, our Kernel-LP changes the task of label propagation from the commonly-used Euclidean space in most existing work to kernel space. The motivation of our Kernel-LP to propagate labels and learn the adaptive weights jointly by the assumption of an inner product space of inputs, i.e., the original linearly inseparable inputs may be mapped to be separable in kernel space. Kernel-LP is based on existing positive and negative LP model, i.e., the effects of negative label information are integrated to improve the label prediction power. Also, Kernel-LP performs adaptive weight construction over the same kernel space, so it can avoid the tricky process of choosing the optimal neighborhood size suffered in traditional criteria. Two novel and efficient out-of-sample approaches for our Kernel-LP to involve new test data are also presented, i.e., (1) direct kernel mapping and (2) kernel mapping-induced label reconstruction, both of which purely depend on the kernel matrix between training set and testing set. Owing to the kernel trick, our algorithms will be applicable to handle the high-dimensional real data. Extensive results on real datasets demonstrate the effectiveness of our approach. |
| Tasks | |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12236v2 |
| https://arxiv.org/pdf/1905.12236v2.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-induced-label-propagation-by-mapping |
| Repo | |
| Framework | |
A deep learning approach for analyzing the composition of chemometric data
| Title | A deep learning approach for analyzing the composition of chemometric data |
| Authors | Muhammad Bilal, Mohib Ullah |
| Abstract | We propose novel deep learning based chemometric data analysis technique. We trained L2 regularized sparse autoencoder end-to-end for reducing the size of the feature vector to handle the classic problem of the curse of dimensionality in chemometric data analysis. We introduce a novel technique of automatic selection of nodes inside the hidden layer of an autoencoder through Pareto optimization. Moreover, Gaussian process regressor is applied on the reduced size feature vector for the regression. We evaluated our technique on orange juice and wine dataset and results are compared against 3 state-of-the-art methods. Quantitative results are shown on Normalized Mean Square Error (NMSE) and the results show considerable improvement in the state-of-the-art. |
| Tasks | |
| Published | 2019-05-07 |
| URL | https://arxiv.org/abs/1905.03420v1 |
| https://arxiv.org/pdf/1905.03420v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503420 |
| Repo | |
| Framework | |
Increasing Expressivity of a Hyperspherical VAE
| Title | Increasing Expressivity of a Hyperspherical VAE |
| Authors | Tim R. Davidson, Jakub M. Tomczak, Efstratios Gavves |
| Abstract | Learning suitable latent representations for observed, high-dimensional data is an important research topic underlying many recent advances in machine learning. While traditionally the Gaussian normal distribution has been the go-to latent parameterization, recently a variety of works have successfully proposed the use of manifold-valued latents. In one such work (Davidson et al., 2018), the authors empirically show the potential benefits of using a hyperspherical von Mises-Fisher (vMF) distribution in low dimensionality. However, due to the unique distributional form of the vMF, expressivity in higher dimensional space is limited as a result of its scalar concentration parameter leading to a ‘hyperspherical bottleneck’. In this work we propose to extend the usability of hyperspherical parameterizations to higher dimensions using a product-space instead, showing improved results on a selection of image datasets. |
| Tasks | |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.02912v1 |
| https://arxiv.org/pdf/1910.02912v1.pdf | |
| PWC | https://paperswithcode.com/paper/increasing-expressivity-of-a-hyperspherical |
| Repo | |
| Framework | |
Real-Time Freespace Segmentation on Autonomous Robots for Detection of Obstacles and Drop-Offs
| Title | Real-Time Freespace Segmentation on Autonomous Robots for Detection of Obstacles and Drop-Offs |
| Authors | Anish Singhani |
| Abstract | Mobile robots navigating in indoor and outdoor environments must be able to identify and avoid unsafe terrain. Although a significant amount of work has been done on the detection of standing obstacles (solid obstructions), not much work has been done on the detection of negative obstacles (e.g. dropoffs, ledges, downward stairs). We propose a method of terrain safety segmentation using deep convolutional networks. Our custom semantic segmentation architecture uses a single camera as input and creates a freespace map distinguishing safe terrain and obstacles. We then show how this freespace map can be used for real-time navigation on an indoor robot. The results show that our system generalizes well, is suitable for real-time operation, and runs at around 55 fps on a small indoor robot powered by a low-power embedded GPU. |
| Tasks | Semantic Segmentation |
| Published | 2019-02-03 |
| URL | http://arxiv.org/abs/1902.00842v1 |
| http://arxiv.org/pdf/1902.00842v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-freespace-segmentation-on |
| Repo | |
| Framework | |
AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers
| Title | AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers |
| Authors | Andrey Kurenkov, Ajay Mandlekar, Roberto Martin-Martin, Silvio Savarese, Animesh Garg |
| Abstract | The exploration mechanism used by a Deep Reinforcement Learning (RL) agent plays a key role in determining its sample efficiency. Thus, improving over random exploration is crucial to solve long-horizon tasks with sparse rewards. We propose to leverage an ensemble of partial solutions as teachers that guide the agent’s exploration with action suggestions throughout training. While the setup of learning with teachers has been previously studied, our proposed approach - Actor-Critic with Teacher Ensembles (AC-Teach) - is the first to work with an ensemble of suboptimal teachers that may solve only part of the problem or contradict other each other, forming a unified algorithmic solution that is compatible with a broad range of teacher ensembles. AC-Teach leverages a probabilistic representation of the expected outcome of the teachers’ and student’s actions to direct exploration, reduce dithering, and adapt to the dynamically changing quality of the learner. We evaluate a variant of AC-Teach that guides the learning of a Bayesian DDPG agent on three tasks - path following, robotic pick and place, and robotic cube sweeping using a hook - and show that it improves largely on sampling efficiency over a set of baselines, both for our target scenario of unconstrained suboptimal teachers and for easier setups with optimal or single teachers. Additional results and videos at https://sites.google.com/view/acteach/home. |
| Tasks | |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.04121v3 |
| https://arxiv.org/pdf/1909.04121v3.pdf | |
| PWC | https://paperswithcode.com/paper/ac-teach-a-bayesian-actor-critic-method-for |
| Repo | |
| Framework | |
Joint analysis of clinical risk factors and 4D cardiac motion for survival prediction using a hybrid deep learning network
| Title | Joint analysis of clinical risk factors and 4D cardiac motion for survival prediction using a hybrid deep learning network |
| Authors | Shihao Jin, Nicolò Savioli, Antonio de Marvao, Timothy JW Dawes, Axel Gandy, Daniel Rueckert, Declan P O’Regan |
| Abstract | In this work, a novel approach is proposed for joint analysis of high dimensional time-resolved cardiac motion features obtained from segmented cardiac MRI and low dimensional clinical risk factors to improve survival prediction in heart failure. Different methods are evaluated to find the optimal way to insert conventional covariates into deep prediction networks. Correlation analysis between autoencoder latent codes and covariate features is used to examine how these predictors interact. We believe that similar approaches could also be used to introduce knowledge of genetic variants to such survival networks to improve outcome prediction by jointly analysing cardiac motion traits with inheritable risk factors. |
| Tasks | |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.02951v1 |
| https://arxiv.org/pdf/1910.02951v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-analysis-of-clinical-risk-factors-and |
| Repo | |
| Framework | |
Self-supervised Audio Spatialization with Correspondence Classifier
| Title | Self-supervised Audio Spatialization with Correspondence Classifier |
| Authors | Yu-Ding Lu, Hsin-Ying Lee, Hung-Yu Tseng, Ming-Hsuan Yang |
| Abstract | Spatial audio is an essential medium to audiences for 3D visual and auditory experience. However, the recording devices and techniques are expensive or inaccessible to the general public. In this work, we propose a self-supervised audio spatialization network that can generate spatial audio given the corresponding video and monaural audio. To enhance spatialization performance, we use an auxiliary classifier to classify ground-truth videos and those with audio where the left and right channels are swapped. We collect a large-scale video dataset with spatial audio to validate the proposed method. Experimental results demonstrate the effectiveness of the proposed model on the audio spatialization task. |
| Tasks | |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05375v1 |
| https://arxiv.org/pdf/1905.05375v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-audio-spatialization-with |
| Repo | |
| Framework | |
2-bit Model Compression of Deep Convolutional Neural Network on ASIC Engine for Image Retrieval
| Title | 2-bit Model Compression of Deep Convolutional Neural Network on ASIC Engine for Image Retrieval |
| Authors | Bin Yang, Lin Yang, Xiaochun Li, Wenhan Zhang, Hua Zhou, Yequn Zhang, Yongxiong Ren, Yinbo Shi |
| Abstract | Image retrieval utilizes image descriptors to retrieve the most similar images to a given query image. Convolutional neural network (CNN) is becoming the dominant approach to extract image descriptors for image retrieval. For low-power hardware implementation of image retrieval, the drawback of CNN-based feature descriptor is that it requires hundreds of megabytes of storage. To address this problem, this paper applies deep model quantization and compression to CNN in ASIC chip for image retrieval. It is demonstrated that the CNN-based features descriptor can be extracted using as few as 2-bit weights quantization to deliver a similar performance as floating-point model for image retrieval. In addition, to implement CNN in ASIC, especially for large scale images, the limited buffer size of chips should be considered. To retrieve large scale images, we propose an improved pooling strategy, region nested invariance pooling (RNIP), which uses cropped sub-images for CNN. Testing results on chip show that integrating RNIP with the proposed 2-bit CNN model compression approach is capable of retrieving large scale images. |
| Tasks | Image Retrieval, Model Compression, Quantization |
| Published | 2019-05-08 |
| URL | https://arxiv.org/abs/1905.03362v1 |
| https://arxiv.org/pdf/1905.03362v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503362 |
| Repo | |
| Framework | |
Context-Driven Data Mining through Bias Removal and Data Incompleteness Mitigation
| Title | Context-Driven Data Mining through Bias Removal and Data Incompleteness Mitigation |
| Authors | Feras A. Batarseh, Ajay Kulkarni |
| Abstract | The results of data mining endeavors are majorly driven by data quality. Throughout these deployments, serious show-stopper problems are still unresolved, such as: data collection ambiguities, data imbalance, hidden biases in data, the lack of domain information, and data incompleteness. This paper is based on the premise that context can aid in mitigating these issues. In a traditional data science lifecycle, context is not considered. Context-driven Data Science Lifecycle (C-DSL); the main contribution of this paper, is developed to address these challenges. Two case studies (using data-sets from sports events) are developed to test C-DSL. Results from both case studies are evaluated using common data mining metrics such as: coefficient of determination (R2 value) and confusion matrices. The work presented in this paper aims to re-define the lifecycle and introduce tangible improvements to its outcomes. |
| Tasks | |
| Published | 2019-10-19 |
| URL | https://arxiv.org/abs/1910.08670v1 |
| https://arxiv.org/pdf/1910.08670v1.pdf | |
| PWC | https://paperswithcode.com/paper/context-driven-data-mining-through-bias |
| Repo | |
| Framework | |
DiabDeep: Pervasive Diabetes Diagnosis based on Wearable Medical Sensors and Efficient Neural Networks
| Title | DiabDeep: Pervasive Diabetes Diagnosis based on Wearable Medical Sensors and Efficient Neural Networks |
| Authors | Hongxu Yin, Bilal Mukadam, Xiaoliang Dai, Niraj K. Jha |
| Abstract | Diabetes impacts the quality of life of millions of people. However, diabetes diagnosis is still an arduous process, given that the disease develops and gets treated outside the clinic. The emergence of wearable medical sensors (WMSs) and machine learning points to a way forward to address this challenge. WMSs enable a continuous mechanism to collect and analyze physiological signals. However, disease diagnosis based on WMS data and its effective deployment on resource-constrained edge devices remain challenging due to inefficient feature extraction and vast computation cost. In this work, we propose a framework called DiabDeep that combines efficient neural networks (called DiabNNs) with WMSs for pervasive diabetes diagnosis. DiabDeep bypasses the feature extraction stage and acts directly on WMS data. It enables both an (i) accurate inference on the server, e.g., a desktop, and (ii) efficient inference on an edge device, e.g., a smartphone, based on varying design goals and resource budgets. On the server, we stack sparsely connected layers to deliver high accuracy. On the edge, we use a hidden-layer long short-term memory based recurrent layer to cut down on computation and storage. At the core of DiabDeep lies a grow-and-prune training flow: it leverages gradient-based growth and magnitude-based pruning algorithms to learn both weights and connections for DiabNNs. We demonstrate the effectiveness of DiabDeep through analyzing data from 52 participants. For server (edge) side inference, we achieve a 96.3% (95.3%) accuracy in classifying diabetics against healthy individuals, and a 95.7% (94.6%) accuracy in distinguishing among type-1/type-2 diabetic, and healthy individuals. Against conventional baselines, DiabNNs achieve higher accuracy, while reducing the model size (FLOPs) by up to 454.5x (8.9x). Therefore, the system can be viewed as pervasive and efficient, yet very accurate. |
| Tasks | |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.04925v1 |
| https://arxiv.org/pdf/1910.04925v1.pdf | |
| PWC | https://paperswithcode.com/paper/diabdeep-pervasive-diabetes-diagnosis-based |
| Repo | |
| Framework | |
Signatures in Shape Analysis: an Efficient Approach to Motion Identification
| Title | Signatures in Shape Analysis: an Efficient Approach to Motion Identification |
| Authors | Elena Celledoni, Pål Erik Lystad, Nikolas Tapia |
| Abstract | Signatures provide a succinct description of certain features of paths in a reparametrization invariant way. We propose a method for classifying shapes based on signatures, and compare it to current approaches based on the SRV transform and dynamic programming. |
| Tasks | |
| Published | 2019-06-14 |
| URL | https://arxiv.org/abs/1906.06406v1 |
| https://arxiv.org/pdf/1906.06406v1.pdf | |
| PWC | https://paperswithcode.com/paper/signatures-in-shape-analysis-an-efficient |
| Repo | |
| Framework | |
Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection
| Title | Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection |
| Authors | Nilesh A. Ahuja, Ibrahima Ndiour, Trushant Kalyanpur, Omesh Tickoo |
| Abstract | We present a principled approach for detecting out-of-distribution (OOD) and adversarial samples in deep neural networks. Our approach consists in modeling the outputs of the various layers (deep features) with parametric probability distributions once training is completed. At inference, the likelihoods of the deep features w.r.t the previously learnt distributions are calculated and used to derive uncertainty estimates that can discriminate in-distribution samples from OOD samples. We explore the use of two classes of multivariate distributions for modeling the deep features - Gaussian and Gaussian mixture - and study the trade-off between accuracy and computational complexity. We demonstrate benefits of our approach on image features by detecting OOD images and adversarially-generated images, using popular DNN architectures on MNIST and CIFAR10 datasets. We show that more precise modeling of the feature distributions result in significantly improved detection of OOD and adversarial samples; up to 12 percentage points in AUPR and AUROC metrics. We further show that our approach remains extremely effective when applied to video data and associated spatio-temporal features by detecting adversarial samples on activity classification tasks using UCF101 dataset, and the C3D network. To our knowledge, our methodology is the first one reported for reliably detecting white-box adversarial framing, a state-of-the-art adversarial attack for video classifiers. |
| Tasks | Adversarial Attack |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11786v1 |
| https://arxiv.org/pdf/1909.11786v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-modeling-of-deep-features-for |
| Repo | |
| Framework | |
Pluggable Social Artificial Intelligence for Enabling Human-Agent Teaming
| Title | Pluggable Social Artificial Intelligence for Enabling Human-Agent Teaming |
| Authors | J. van Diggelen, J. S. Barnhoorn, M. M. M. Peeters, W. van Staal, M. L. Stolk, B. van der Vecht, J. van der Waa, J. M. Schraagen |
| Abstract | As intelligent systems are increasingly capable of performing their tasks without the need for continuous human input, direction, or supervision, new human-machine interaction concepts are needed. A promising approach to this end is human-agent teaming, which envisions a novel interaction form where humans and machines behave as equal team partners. This paper presents an overview of the current state of the art in human-agent teaming, including the analysis of human-agent teams on five dimensions; a framework describing important teaming functionalities; a technical architecture, called SAIL, supporting social human-agent teaming through the modular implementation of the human-agent teaming functionalities; a technical implementation of the architecture; and a proof-of-concept prototype created with the framework and architecture. We conclude this paper with a reflection on where we stand and a glance into the future showing the way forward. |
| Tasks | |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04492v2 |
| https://arxiv.org/pdf/1909.04492v2.pdf | |
| PWC | https://paperswithcode.com/paper/pluggable-social-artificial-intelligence-for |
| Repo | |
| Framework | |
Estimation of blood oxygenation with learned spectral decoloring for quantitative photoacoustic imaging (LSD-qPAI)
| Title | Estimation of blood oxygenation with learned spectral decoloring for quantitative photoacoustic imaging (LSD-qPAI) |
| Authors | Janek Gröhl, Thomas Kirchner, Tim Adler, Lena Maier-Hein |
| Abstract | One of the main applications of photoacoustic (PA) imaging is the recovery of functional tissue properties, such as blood oxygenation (sO2). This is typically achieved by linear spectral unmixing of relevant chromophores from multispectral photoacoustic images. Despite the progress that has been made towards quantitative PA imaging (qPAI), most sO2 estimation methods yield poor results in realistic settings. In this work, we tackle the challenge by employing learned spectral decoloring for quantitative photoacoustic imaging (LSD-qPAI) to obtain quantitative estimates for blood oxygenation. LSD-qPAI computes sO2 directly from pixel-wise initial pressure spectra Sp0, which are vectors comprised of the initial pressure at the same spatial location over all recorded wavelengths. Initial results suggest that LSD-qPAI is able to obtain accurate sO2 estimates directly from multispectral photoacoustic measurements in silico and plausible estimates in vivo. |
| Tasks | |
| Published | 2019-02-15 |
| URL | http://arxiv.org/abs/1902.05839v1 |
| http://arxiv.org/pdf/1902.05839v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimation-of-blood-oxygenation-with-learned |
| Repo | |
| Framework | |
Joint Robust Voicing Detection and Pitch Estimation Based on Residual Harmonics
| Title | Joint Robust Voicing Detection and Pitch Estimation Based on Residual Harmonics |
| Authors | Thomas Drugman, Abeer Alwan |
| Abstract | This paper focuses on the problem of pitch tracking in noisy conditions. A method using harmonic information in the residual signal is presented. The proposed criterion is used both for pitch estimation, as well as for determining the voicing segments of speech. In the experiments, the method is compared to six state-of-the-art pitch trackers on the Keele and CSTR databases. The proposed technique is shown to be particularly robust to additive noise, leading to a significant improvement in adverse conditions. |
| Tasks | |
| Published | 2019-12-28 |
| URL | https://arxiv.org/abs/2001.00459v1 |
| https://arxiv.org/pdf/2001.00459v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-robust-voicing-detection-and-pitch |
| Repo | |
| Framework | |
