January 30, 2020

3028 words 15 mins read

Paper Group ANR 418

MemNet: Memory-Efficiency Guided Neural Architecture Search with Augment-Trim learning. Skeleton-based Gait Index Estimation with LSTMs. Image quality assessment for determining efficacy and limitations of Super-Resolution Convolutional Neural Network (SRCNN). Differentially Private Model Publishing for Deep Learning. Schrödinger Bridge Samplers. L …

MemNet: Memory-Efficiency Guided Neural Architecture Search with Augment-Trim learning


Title	MemNet: Memory-Efficiency Guided Neural Architecture Search with Augment-Trim learning
Authors	Peiye Liu, Bo Wu, Huadong Ma, Pavan Kumar Chundi, Mingoo Seok
Abstract	Recent studies on automatic neural architectures search have demonstrated significant performance, competitive to or even better than hand-crafted neural architectures. However, most of the existing network architecture tend to use residual, parallel structures and concatenation block between shallow and deep features to construct a large network. This requires large amounts of memory for storing both weights and feature maps. This is challenging for mobile and embedded devices since they may not have enough memory to perform inference with the designed large network model. To close this gap, we propose MemNet, an augment-trim learning-based neural network search framework that optimizes not only performance but also memory requirement. Specifically, it employs memory consumption based ranking score which forces an upper bound on memory consumption for navigating the search process. Experiment results show that, as compared to the state-of-the-art efficient designing methods, MemNet can find an architecture which can achieve competitive accuracy and save an average of 24.17% on the total memory needed.
Tasks	Neural Architecture Search
Published	2019-07-22
URL	https://arxiv.org/abs/1907.09569v1
PDF	https://arxiv.org/pdf/1907.09569v1.pdf
PWC	https://paperswithcode.com/paper/memnet-memory-efficiency-guided-neural
Repo
Framework

Skeleton-based Gait Index Estimation with LSTMs


Title	Skeleton-based Gait Index Estimation with LSTMs
Authors	Trong Nguyen Nguyen, Huu Hung Huynh, Jean Meunier
Abstract	In this paper, we propose a method that estimates a gait index for a sequence of skeletons. Our system is a stack of an encoder and a decoder that are formed by Long Short-Term Memories (LSTMs). In the encoding stage, the characteristics of an input are automatically determined and are compressed into a latent space. The decoding stage then attempts to reconstruct the input according to such intermediate representation. The reconstruction error is thus considered as a weak gait index. By combining such weak indices over a long-time movement, our system can provide a good estimation for the gait index. Our experiments on a large dataset (nearly one hundred thousand skeletons) showed that the index given by the proposed method outperformed some recent works on gait analysis.
Tasks
Published	2019-08-17
URL	https://arxiv.org/abs/1908.07416v1
PDF	https://arxiv.org/pdf/1908.07416v1.pdf
PWC	https://paperswithcode.com/paper/skeleton-based-gait-index-estimation-with
Repo
Framework

Image quality assessment for determining efficacy and limitations of Super-Resolution Convolutional Neural Network (SRCNN)


Title	Image quality assessment for determining efficacy and limitations of Super-Resolution Convolutional Neural Network (SRCNN)
Authors	Chris M. Ward, Josh Harguess, Brendan Crabb, Shibin Parameswaran
Abstract	Traditional metrics for evaluating the efficacy of image processing techniques do not lend themselves to understanding the capabilities and limitations of modern image processing methods - particularly those enabled by deep learning. When applying image processing in engineering solutions, a scientist or engineer has a need to justify their design decisions with clear metrics. By applying blind/referenceless image spatial quality (BRISQUE), Structural SIMilarity (SSIM) index scores, and Peak signal-to-noise ratio (PSNR) to images before and after image processing, we can quantify quality improvements in a meaningful way and determine the lowest recoverable image quality for a given method.
Tasks	Image Quality Assessment, Super-Resolution
Published	2019-05-14
URL	https://arxiv.org/abs/1905.05373v1
PDF	https://arxiv.org/pdf/1905.05373v1.pdf
PWC	https://paperswithcode.com/paper/image-quality-assessment-for-determining
Repo
Framework

Differentially Private Model Publishing for Deep Learning


Title	Differentially Private Model Publishing for Deep Learning
Authors	Lei Yu, Ling Liu, Calton Pu, Mehmet Emre Gursoy, Stacey Truex
Abstract	Deep learning techniques based on neural networks have shown significant success in a wide range of AI tasks. Large-scale training datasets are one of the critical factors for their success. However, when the training datasets are crowdsourced from individuals and contain sensitive information, the model parameters may encode private information and bear the risks of privacy leakage. The recent growing trend of the sharing and publishing of pre-trained models further aggravates such privacy risks. To tackle this problem, we propose a differentially private approach for training neural networks. Our approach includes several new techniques for optimizing both privacy loss and model accuracy. We employ a generalization of differential privacy called concentrated differential privacy(CDP), with both a formal and refined privacy loss analysis on two different data batching methods. We implement a dynamic privacy budget allocator over the course of training to improve model accuracy. Extensive experiments demonstrate that our approach effectively improves privacy loss accounting, training efficiency and model quality under a given privacy budget.
Tasks
Published	2019-04-03
URL	https://arxiv.org/abs/1904.02200v5
PDF	https://arxiv.org/pdf/1904.02200v5.pdf
PWC	https://paperswithcode.com/paper/differentially-private-model-publishing-for
Repo
Framework

Schrödinger Bridge Samplers


Title	Schrödinger Bridge Samplers
Authors	Espen Bernton, Jeremy Heng, Arnaud Doucet, Pierre E. Jacob
Abstract	Consider a reference Markov process with initial distribution $\pi_{0}$ and transition kernels ${M_{t}}_{t\in[1:T]}$, for some $T\in\mathbb{N}$. Assume that you are given distribution $\pi_{T}$, which is not equal to the marginal distribution of the reference process at time $T$. In this scenario, Schr"odinger addressed the problem of identifying the Markov process with initial distribution $\pi_{0}$ and terminal distribution equal to $\pi_{T}$ which is the closest to the reference process in terms of Kullback–Leibler divergence. This special case of the so-called Schr"odinger bridge problem can be solved using iterative proportional fitting, also known as the Sinkhorn algorithm. We leverage these ideas to develop novel Monte Carlo schemes, termed Schr"odinger bridge samplers, to approximate a target distribution $\pi$ on $\mathbb{R}^{d}$ and to estimate its normalizing constant. This is achieved by iteratively modifying the transition kernels of the reference Markov chain to obtain a process whose marginal distribution at time $T$ becomes closer to $\pi_T = \pi$, via regression-based approximations of the corresponding iterative proportional fitting recursion. We report preliminary experiments and make connections with other problems arising in the optimal transport, optimal control and physics literatures.
Tasks
Published	2019-12-31
URL	https://arxiv.org/abs/1912.13170v1
PDF	https://arxiv.org/pdf/1912.13170v1.pdf
PWC	https://paperswithcode.com/paper/schrodinger-bridge-samplers
Repo
Framework

Lane Attention: Predicting Vehicles’ Moving Trajectories by Learning Their Attention over Lanes


Title	Lane Attention: Predicting Vehicles’ Moving Trajectories by Learning Their Attention over Lanes
Authors	Jiacheng Pan, Hongyi Sun, Kecheng Xu, Yifei Jiang, Xiangquan Xiao, Jiangtao Hu, Jinghao Miao
Abstract	Accurately forecasting the future movements of surrounding vehicles is essential for safe and efficient operations of autonomous driving cars. This task is difficult because a vehicle’s moving trajectory is greatly determined by its driver’s intention, which is often hard to estimate. By leveraging attention mechanisms along with long short-term memory (LSTM) networks, this work learns the relation between a driver’s intention and the vehicle’s changing positions relative to road infrastructures, and uses it to guide the prediction. Different from other state-of-the-art solutions, our work treats the on-road lanes as non-Euclidean structures, unfolds the vehicle’s moving history to form a spatio-temporal graph, and uses methods from Graph Neural Networks to solve the problem. Not only is our approach a pioneering attempt in using non-Euclidean methods to process static environmental features around a predicted object, our model also outperforms other state-of-the-art models in several metrics. The practicability and interpretability analysis of the model shows great potential for large-scale deployment in various autonomous driving systems in addition to our own.
Tasks	Autonomous Driving
Published	2019-09-29
URL	https://arxiv.org/abs/1909.13377v1
PDF	https://arxiv.org/pdf/1909.13377v1.pdf
PWC	https://paperswithcode.com/paper/lane-attention-predicting-vehicles-moving
Repo
Framework

Perturbative estimation of stochastic gradients


Title	Perturbative estimation of stochastic gradients
Authors	Luca Ambrogioni, Marcel A. J. van Gerven
Abstract	In this paper we introduce a family of stochastic gradient estimation techniques based of the perturbative expansion around the mean of the sampling distribution. We characterize the bias and variance of the resulting Taylor-corrected estimators using the Lagrange error formula. Furthermore, we introduce a family of variance reduction techniques that can be applied to other gradient estimators. Finally, we show that these new perturbative methods can be extended to discrete functions using analytic continuation. Using this technique, we derive a new gradient descent method for training stochastic networks with binary weights. In our experiments, we show that the perturbative correction improves the convergence of stochastic variational inference both in the continuous and in the discrete case.
Tasks
Published	2019-03-31
URL	https://arxiv.org/abs/1904.00469v4
PDF	https://arxiv.org/pdf/1904.00469v4.pdf
PWC	https://paperswithcode.com/paper/perturbative-estimation-of-stochastic
Repo
Framework

Heterogeneous Proxytypes Extended: Integrating Theory-like Representations and Mechanisms with Prototypes and Exemplars


Title	Heterogeneous Proxytypes Extended: Integrating Theory-like Representations and Mechanisms with Prototypes and Exemplars
Authors	Antonio Lieto
Abstract	The paper introduces an extension of the proposal according to which conceptual representations in cognitive agents should be intended as heterogeneous proxytypes. The main contribution of this paper is in that it details how to reconcile, under a heterogeneous representational perspective, different theories of typicality about conceptual representation and reasoning. In particular, it provides a novel theoretical hypothesis - as well as a novel categorization algorithm called DELTA - showing how to integrate the representational and reasoning assumptions of the theory-theory of concepts with the those ascribed to the prototype and exemplars-based theories.
Tasks
Published	2019-09-04
URL	https://arxiv.org/abs/1909.01645v1
PDF	https://arxiv.org/pdf/1909.01645v1.pdf
PWC	https://paperswithcode.com/paper/heterogeneous-proxytypes-extended-integrating
Repo
Framework

Probability Calibration for Knowledge Graph Embedding Models


Title	Probability Calibration for Knowledge Graph Embedding Models
Authors	Pedro Tabacof, Luca Costabello
Abstract	Knowledge graph embedding research has overlooked the problem of probability calibration. We show popular embedding models are indeed uncalibrated. That means probability estimates associated to predicted triples are unreliable. We present a novel method to calibrate a model when ground truth negatives are not available, which is the usual case in knowledge graphs. We propose to use Platt scaling and isotonic regression alongside our method. Experiments on three datasets with ground truth negatives show our contribution leads to well-calibrated models when compared to the gold standard of using negatives. We get significantly better results than the uncalibrated models from all calibration methods. We show isotonic regression offers the best the performance overall, not without trade-offs. We also show that calibrated models reach state-of-the-art accuracy without the need to define relation-specific decision thresholds.
Tasks	Calibration, Graph Embedding, Knowledge Graph Embedding, Knowledge Graphs
Published	2019-12-20
URL	https://arxiv.org/abs/1912.10000v2
PDF	https://arxiv.org/pdf/1912.10000v2.pdf
PWC	https://paperswithcode.com/paper/probability-calibration-for-knowledge-graph-1
Repo
Framework

Coupled Learning for Facial Deblur


Title	Coupled Learning for Facial Deblur
Authors	Dayong Tian, Dacheng Tao
Abstract	Blur in facial images significantly impedes the efficiency of recognition approaches. However, most existing blind deconvolution methods cannot generate satisfactory results due to their dependence on strong edges, which are sufficient in natural images but not in facial images. In this paper, we represent point spread functions (PSFs) by the linear combination of a set of pre-defined orthogonal PSFs, and similarly, an estimated intrinsic (EI) sharp face image is represented by the linear combination of a set of pre-defined orthogonal face images. In doing so, PSF and EI estimation is simplified to discovering two sets of linear combination coefficients, which are simultaneously found by our proposed coupled learning algorithm. To make our method robust to different types of blurry face images, we generate several candidate PSFs and EIs for a test image, and then, a non-blind deconvolution method is adopted to generate more EIs by those candidate PSFs. Finally, we deploy a blind image quality assessment metric to automatically select the optimal EI. Thorough experiments on the facial recognition technology database, extended Yale face database B, CMU pose, illumination, and expression (PIE) database, and face recognition grand challenge database version 2.0 demonstrate that the proposed approach effectively restores intrinsic sharp face images and, consequently, improves the performance of face recognition.
Tasks	Blind Image Quality Assessment, Face Recognition, Image Quality Assessment
Published	2019-04-18
URL	http://arxiv.org/abs/1904.08671v1
PDF	http://arxiv.org/pdf/1904.08671v1.pdf
PWC	https://paperswithcode.com/paper/coupled-learning-for-facial-deblur
Repo
Framework

Optimization of Speaker Extraction Neural Network with Magnitude and Temporal Spectrum Approximation Loss


Title	Optimization of Speaker Extraction Neural Network with Magnitude and Temporal Spectrum Approximation Loss
Authors	Chenglin Xu, Wei Rao, Eng Siong Chng, Haizhou Li
Abstract	The SpeakerBeam-FE (SBF) method is proposed for speaker extraction. It attempts to overcome the problem of unknown number of speakers in an audio recording during source separation. The mask approximation loss of SBF is sub-optimal, which doesn’t calculate direct signal reconstruction error and consider the speech context. To address these problems, this paper proposes a magnitude and temporal spectrum approximation loss to estimate a phase sensitive mask for the target speaker with the speaker characteristics. Moreover, this paper explores a concatenation framework instead of the context adaptive deep neural network in the SBF method to encode a speaker embedding into the mask estimation network. Experimental results under open evaluation condition show that the proposed method achieves 70.4% and 17.7% relative improvement over the SBF baseline on signal-to-distortion ratio (SDR) and perceptual evaluation of speech quality (PESQ), respectively. A further analysis demonstrates 69.1% and 72.3% relative SDR improvements obtained by the proposed method for different and same gender mixtures.
Tasks
Published	2019-03-24
URL	http://arxiv.org/abs/1903.09952v1
PDF	http://arxiv.org/pdf/1903.09952v1.pdf
PWC	https://paperswithcode.com/paper/optimization-of-speaker-extraction-neural
Repo
Framework

Localization-aware Channel Pruning for Object Detection


Title	Localization-aware Channel Pruning for Object Detection
Authors	Zihao Xie, Wenbing Tao, Li Zhu, Lin Zhao
Abstract	Channel pruning is one of the important methods for deep model compression. Most of existing pruning methods mainly focus on classification. Few of them conduct systematic research on object detection. However, object detection is different from classification, which requires not only semantic information but also localization information. In this paper, based on discrimination-aware channel pruning (DCP) which is state-of-the-art pruning method for classification, we propose a localization-aware auxiliary network to find out the channels with key information for classification and regression so that we can conduct channel pruning directly for object detection, which saves lots of time and computing resources. In order to capture the localization information, we first design the auxiliary network with a contextual ROIAlign layer which can obtain precise localization information of the default boxes by pixel alignment and enlarges the receptive fields of the default boxes when pruning shallow layers. Then, we construct a loss function for object detection task which tends to keep the channels that contain the key information for classification and regression. Extensive experiments demonstrate the effectiveness of our method. On MS COCO, we prune 70% parameters of the SSD based on ResNet-50 with modest accuracy drop, which outperforms the-state-of-art method.
Tasks	Model Compression, Object Detection
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02237v3
PDF	https://arxiv.org/pdf/1911.02237v3.pdf
PWC	https://paperswithcode.com/paper/localization-aware-channel-pruning-for-object
Repo
Framework

Efficient Path Prediction for Semi-Supervised and Weakly Supervised Hierarchical Text Classification


Title	Efficient Path Prediction for Semi-Supervised and Weakly Supervised Hierarchical Text Classification
Authors	Huiru Xiao, Xin Liu, Yangqiu Song
Abstract	Hierarchical text classification has many real-world applications. However, labeling a large number of documents is costly. In practice, we can use semi-supervised learning or weakly supervised learning (e.g., dataless classification) to reduce the labeling cost. In this paper, we propose a path cost-sensitive learning algorithm to utilize the structural information and further make use of unlabeled and weakly-labeled data. We use a generative model to leverage the large amount of unlabeled data and introduce path constraints into the learning algorithm to incorporate the structural information of the class hierarchy. The posterior probabilities of both unlabeled and weakly labeled data can be incorporated with path-dependent scores. Since we put a structure-sensitive cost to the learning algorithm to constrain the classification consistent with the class hierarchy and do not need to reconstruct the feature vectors for different structures, we can significantly reduce the computational cost compared to structural output learning. Experimental results on two hierarchical text classification benchmarks show that our approach is not only effective but also efficient to handle the semi-supervised and weakly supervised hierarchical text classification.
Tasks	Text Classification
Published	2019-02-25
URL	http://arxiv.org/abs/1902.09347v1
PDF	http://arxiv.org/pdf/1902.09347v1.pdf
PWC	https://paperswithcode.com/paper/efficient-path-prediction-for-semi-supervised
Repo
Framework

2D LiDAR Map Prediction via Estimating Motion Flow with GRU


Title	2D LiDAR Map Prediction via Estimating Motion Flow with GRU
Authors	Yafei Song, Yonghong Tian, Gang Wang, Mingyang Li
Abstract	It is a significant problem to predict the 2D LiDAR map at next moment for robotics navigation and path-planning. To tackle this problem, we resort to the motion flow between adjacent maps, as motion flow is a powerful tool to process and analyze the dynamic data, which is named optical flow in video processing. However, unlike video, which contains abundant visual features in each frame, a 2D LiDAR map lacks distinctive local features. To alleviate this challenge, we propose to estimate the motion flow based on deep neural networks inspired by its powerful representation learning ability in estimating the optical flow of the video. To this end, we design a recurrent neural network based on gated recurrent unit, which is named LiDAR-FlowNet. As a recurrent neural network can encode the temporal dynamic information, our LiDAR-FlowNet can estimate motion flow between the current map and the unknown next map only from the current frame and previous frames. A self-supervised strategy is further designed to train the LiDAR-FlowNet model effectively, while no training data need to be manually annotated. With the estimated motion flow, it is straightforward to predict the 2D LiDAR map at the next moment. Experimental results verify the effectiveness of our LiDAR-FlowNet as well as the proposed training strategy. The results of the predicted LiDAR map also show the advantages of our motion flow based method.
Tasks	Optical Flow Estimation, Representation Learning
Published	2019-02-19
URL	http://arxiv.org/abs/1902.06919v1
PDF	http://arxiv.org/pdf/1902.06919v1.pdf
PWC	https://paperswithcode.com/paper/2d-lidar-map-prediction-via-estimating-motion
Repo
Framework

Learning Convex Optimization Control Policies


Title	Learning Convex Optimization Control Policies
Authors	Akshay Agrawal, Shane Barratt, Stephen Boyd, Bartolomeo Stellato
Abstract	Many control policies used in various applications determine the input or action by solving a convex optimization problem that depends on the current state and some parameters. Common examples of such convex optimization control policies (COCPs) include the linear quadratic regulator (LQR), convex model predictive control (MPC), and convex control-Lyapunov or approximate dynamic programming (ADP) policies. These types of control policies are tuned by varying the parameters in the optimization problem, such as the LQR weights, to obtain good performance, judged by application-specific metrics. Tuning is often done by hand, or by simple methods such as a crude grid search. In this paper we propose a method to automate this process, by adjusting the parameters using an approximate gradient of the performance metric with respect to the parameters. Our method relies on recently developed methods that can efficiently evaluate the derivative of the solution of a convex optimization problem with respect to its parameters. We illustrate our method on several examples.
Tasks
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09529v1
PDF	https://arxiv.org/pdf/1912.09529v1.pdf
PWC	https://paperswithcode.com/paper/learning-convex-optimization-control-policies
Repo
Framework