Paper Group ANR 437
Accelerating and Improving AlphaZero Using Population Based Training. PDS: Deduce Elder Privacy from Smart Homes. Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images. LT-Net: Label Transfer by Learning Reversible Voxel-wise Correspondence for One-shot Medical Image Segmentation. Beyond Application End-Point Resu …
Accelerating and Improving AlphaZero Using Population Based Training
| Title | Accelerating and Improving AlphaZero Using Population Based Training |
| Authors | Ti-Rong Wu, Ting-Han Wei, I-Chen Wu |
| Abstract | AlphaZero has been very successful in many games. Unfortunately, it still consumes a huge amount of computing resources, the majority of which is spent in self-play. Hyperparameter tuning exacerbates the training cost since each hyperparameter configuration requires its own time to train one run, during which it will generate its own self-play records. As a result, multiple runs are usually needed for different hyperparameter configurations. This paper proposes using population based training (PBT) to help tune hyperparameters dynamically and improve strength during training time. Another significant advantage is that this method requires a single run only, while incurring a small additional time cost, since the time for generating self-play records remains unchanged though the time for optimization is increased following the AlphaZero training algorithm. In our experiments for 9x9 Go, the PBT method is able to achieve a higher win rate for 9x9 Go than the baselines, each with its own hyperparameter configuration and trained individually. For 19x19 Go, with PBT, we are able to obtain improvements in playing strength. Specifically, the PBT agent can obtain up to 74% win rate against ELF OpenGo, an open-source state-of-the-art AlphaZero program using a neural network of a comparable capacity. This is compared to a saturated non-PBT agent, which achieves a win rate of 47% against ELF OpenGo under the same circumstances. |
| Tasks | |
| Published | 2020-03-13 |
| URL | https://arxiv.org/abs/2003.06212v1 |
| https://arxiv.org/pdf/2003.06212v1.pdf | |
| PWC | https://paperswithcode.com/paper/accelerating-and-improving-alphazero-using |
| Repo | |
| Framework | |
PDS: Deduce Elder Privacy from Smart Homes
| Title | PDS: Deduce Elder Privacy from Smart Homes |
| Authors | Ming-Chang Lee, Jia-Chun Lin, Olaf Owe |
| Abstract | With the development of IoT technologies in the past few years, a wide range of smart devices are deployed in a variety of environments aiming to improve the quality of human life in a cost efficient way. Due to the increasingly serious aging problem around the world, smart homes for elder healthcare have become an important IoT-based application, which not only enables elders’ health to be properly monitored and taken care of, but also allows them to live more comfortably and independently in their houses. However, elders’ privacy might be disclosed from smart homes due to non-fully protected network communication. To show that elders’ privacy could be substantially exposed, in this paper we develop a Privacy Deduction Scheme (PDS for short) by eavesdropping sensor traffic from a smart home to identify elders’ movement activities and speculating sensor locations in the smart home based on a series of deductions from the viewpoint of an attacker. The experimental results based on sensor datasets from real smart homes demonstrate the effectiveness of PDS in deducing and disclosing elders’ privacy, which might be maliciously exploited by attackers to endanger elders and their properties. |
| Tasks | |
| Published | 2020-01-21 |
| URL | https://arxiv.org/abs/2001.08099v1 |
| https://arxiv.org/pdf/2001.08099v1.pdf | |
| PWC | https://paperswithcode.com/paper/pds-deduce-elder-privacy-from-smart-homes |
| Repo | |
| Framework | |
Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images
| Title | Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images |
| Authors | Heming Zhu, Yu Cao, Hang Jin, Weikai Chen, Dong Du, Zhangye Wang, Shuguang Cui, Xiaoguang Han |
| Abstract | High-fidelity clothing reconstruction is the key to achieving photorealism in a wide range of applications including human digitization, virtual try-on, etc. Recent advances in learning-based approaches have accomplished unprecedented accuracy in recovering unclothed human shape and pose from single images, thanks to the availability of powerful statistical models, e.g. SMPL, learned from a large number of body scans. In contrast, modeling and recovering clothed human and 3D garments remains notoriously difficult, mostly due to the lack of large-scale clothing models available for the research community. We propose to fill this gap by introducing Deep Fashion3D, the largest collection to date of 3D garment models, with the goal of establishing a novel benchmark and dataset for the evaluation of image-based garment reconstruction systems. Deep Fashion3D contains 2078 models reconstructed from real garments, which covers 10 different categories and 563 garment instances. It provides rich annotations including 3D feature lines, 3D body pose and the corresponded multi-view real images. In addition, each garment is randomly posed to enhance the variety of real clothing deformations. To demonstrate the advantage of Deep Fashion3D, we propose a novel baseline approach for single-view garment reconstruction, which leverages the merits of both mesh and implicit representations. A novel adaptable template is proposed to enable the learning of all types of clothing in a single network. Extensive experiments have been conducted on the proposed dataset to verify its significance and usefulness. We will make Deep Fashion3D publicly available upon publication. |
| Tasks | |
| Published | 2020-03-28 |
| URL | https://arxiv.org/abs/2003.12753v1 |
| https://arxiv.org/pdf/2003.12753v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-fashion3d-a-dataset-and-benchmark-for-3d |
| Repo | |
| Framework | |
LT-Net: Label Transfer by Learning Reversible Voxel-wise Correspondence for One-shot Medical Image Segmentation
| Title | LT-Net: Label Transfer by Learning Reversible Voxel-wise Correspondence for One-shot Medical Image Segmentation |
| Authors | Shuxin Wang, Shilei Cao, Dong Wei, Renzhen Wang, Kai Ma, Liansheng Wang, Deyu Meng, Yefeng Zheng |
| Abstract | We introduce a one-shot segmentation method to alleviate the burden of manual annotation for medical images. The main idea is to treat one-shot segmentation as a classical atlas-based segmentation problem, where voxel-wise correspondence from the atlas to the unlabelled data is learned. Subsequently, segmentation label of the atlas can be transferred to the unlabelled data with the learned correspondence. However, since ground truth correspondence between images is usually unavailable, the learning system must be well-supervised to avoid mode collapse and convergence failure. To overcome this difficulty, we resort to the forward-backward consistency, which is widely used in correspondence problems, and additionally learn the backward correspondences from the warped atlases back to the original atlas. This cycle-correspondence learning design enables a variety of extra, cycle-consistency-based supervision signals to make the training process stable, while also boost the performance. We demonstrate the superiority of our method over both deep learning-based one-shot segmentation methods and a classical multi-atlas segmentation method via thorough experiments. |
| Tasks | Medical Image Segmentation, One-Shot Segmentation, Semantic Segmentation |
| Published | 2020-03-16 |
| URL | https://arxiv.org/abs/2003.07072v3 |
| https://arxiv.org/pdf/2003.07072v3.pdf | |
| PWC | https://paperswithcode.com/paper/lt-net-label-transfer-by-learning-reversible |
| Repo | |
| Framework | |
Beyond Application End-Point Results: Quantifying Statistical Robustness of MCMC Accelerators
| Title | Beyond Application End-Point Results: Quantifying Statistical Robustness of MCMC Accelerators |
| Authors | Xiangyu Zhang, Ramin Bashizade, Yicheng Wang, Cheng Lyu, Sayan Mukherjee, Alvin R. Lebeck |
| Abstract | Statistical machine learning often uses probabilistic algorithms, such as Markov Chain Monte Carlo (MCMC), to solve a wide range of problems. Probabilistic computations, often considered too slow on conventional processors, can be accelerated with specialized hardware by exploiting parallelism and optimizing the design using various approximation techniques. Current methodologies for evaluating correctness of probabilistic accelerators are often incomplete, mostly focusing only on end-point result quality (“accuracy”). It is important for hardware designers and domain experts to look beyond end-point “accuracy” and be aware of the hardware optimizations impact on other statistical properties. This work takes a first step towards defining metrics and a methodology for quantitatively evaluating correctness of probabilistic accelerators beyond end-point result quality. We propose three pillars of statistical robustness: 1) sampling quality, 2) convergence diagnostic, and 3) goodness of fit. We apply our framework to a representative MCMC accelerator and surface design issues that cannot be exposed using only application end-point result quality. Applying the framework to guide design space exploration shows that statistical robustness comparable to floating-point software can be achieved by slightly increasing the bit representation, without floating-point hardware requirements. |
| Tasks | |
| Published | 2020-03-05 |
| URL | https://arxiv.org/abs/2003.04223v1 |
| https://arxiv.org/pdf/2003.04223v1.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-application-end-point-results |
| Repo | |
| Framework | |
Analysis of Softmax Approximation for Deep Classifiers under Input-Dependent Label Noise
| Title | Analysis of Softmax Approximation for Deep Classifiers under Input-Dependent Label Noise |
| Authors | Mark Collier, Basil Mustafa, Efi Kokiopoulou, Jesse Berent |
| Abstract | Modelling uncertainty arising from input-dependent label noise is an increasingly important problem. A state-of-the-art approach for classification [Kendall and Gal, 2017] places a normal distribution over the softmax logits, where the mean and variance of this distribution are learned functions of the inputs. This approach achieves impressive empirical performance but lacks theoretical justification. We show that this model is a special case of a well known and theoretically understood model studied in econometrics. Under this view the softmax over the logit distribution is a smooth approximation to an argmax, where the approximation is exact in the zero temperature limit. We further illustrate that the softmax temperature controls a bias-variance trade-off and the optimal point on this trade-off is not always found at 1.0. By tuning the softmax temperature, we achieve improved performance on well known image classification benchmarks with controlled label noise. For image segmentation, where input-dependent label noise naturally arises, we show that tuning the temperature increases the mean IoU on the PASCAL VOC and Cityscapes datasets by more than 1% over the state-of-the-art model and a strong baseline that does not model this noise source. |
| Tasks | Image Classification, Semantic Segmentation |
| Published | 2020-03-15 |
| URL | https://arxiv.org/abs/2003.06778v1 |
| https://arxiv.org/pdf/2003.06778v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-softmax-approximation-for-deep |
| Repo | |
| Framework | |
Evaluation of Parameterized Quantum Circuits: on the design, and the relation between classification accuracy, expressibility and entangling capability
| Title | Evaluation of Parameterized Quantum Circuits: on the design, and the relation between classification accuracy, expressibility and entangling capability |
| Authors | Thomas Hubregtsen, Josef Pichlmeier, Koen Bertels |
| Abstract | Quantum computers promise improvements in terms of both computational speedup and increased accuracy. Relevant areas are optimization, chemistry and machine learning, of which we will focus on the latter. Much of the prior art focuses on determining computational speedup, but how do we know if a particular quantum circuit shows promise for achieving high classification accuracy? Previous work by Sim et al. proposed descriptors to characterize and compare Parameterized Quantum Circuits. In this work, we will investigate any potential relation between the classification accuracy and two of these descriptors, being expressibility and entangling capability. We will first investigate different types of gates in quantum circuits and the changes they incur on the decision boundary. From this, we will propose design criteria for constructing circuits. We will also numerically compare the classifications performance of various quantum circuits and their quantified measure of expressibility and entangling capability, as derived in previous work. From this, we conclude that the common approach to layer combinations of rotational gates and conditional rotational gates provides the best accuracy. We also show that, for our experiments on a limited number of circuits, a coarse-grained relationship exists between entangling capability and classification accuracy, as well as a more fine-grained correlation between expressibility and classification accuracy. Future research will need to be performed to quantify this relation. |
| Tasks | |
| Published | 2020-03-22 |
| URL | https://arxiv.org/abs/2003.09887v1 |
| https://arxiv.org/pdf/2003.09887v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluation-of-parameterized-quantum-circuits |
| Repo | |
| Framework | |
Linking Social Media Posts to News with Siamese Transformers
| Title | Linking Social Media Posts to News with Siamese Transformers |
| Authors | Jacob Danovitch |
| Abstract | Many computational social science projects examine online discourse surrounding a specific trending topic. These works often involve the acquisition of large-scale corpora relevant to the event in question to analyze aspects of the response to the event. Keyword searches present a precision-recall trade-off and crowd-sourced annotations, while effective, are costly. This work aims to enable automatic and accurate ad-hoc retrieval of comments discussing a trending topic from a large corpus, using only a handful of seed news articles. |
| Tasks | |
| Published | 2020-01-10 |
| URL | https://arxiv.org/abs/2001.03303v1 |
| https://arxiv.org/pdf/2001.03303v1.pdf | |
| PWC | https://paperswithcode.com/paper/linking-social-media-posts-to-news-with |
| Repo | |
| Framework | |
Learning End-to-End Codes for the BPSK-constrained Gaussian Wiretap Channel
| Title | Learning End-to-End Codes for the BPSK-constrained Gaussian Wiretap Channel |
| Authors | Alireza Nooraiepour, Sina Rezaei Aghdam |
| Abstract | Finite-length codes are learned for the Gaussian wiretap channel in an end-to-end manner assuming that the communication parties are equipped with deep neural networks (DNNs), and communicate through binary phase-shift keying (BPSK) modulation scheme. The goal is to find codes via DNNs which allow a pair of transmitter and receiver to communicate reliably and securely in the presence of an adversary aiming at decoding the secret messages. Following the information-theoretic secrecy principles, the security is evaluated in terms of mutual information utilizing a deep learning tool called MINE (mutual information neural estimation). System performance is evaluated for different DNN architectures, designed based on the existing secure coding schemes, at the transmitter. Numerical results demonstrate that the legitimate parties can indeed establish a secure transmission in this setting as the learned codes achieve points on almost the boundary of the equivocation region. |
| Tasks | |
| Published | 2020-03-23 |
| URL | https://arxiv.org/abs/2003.10577v1 |
| https://arxiv.org/pdf/2003.10577v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-end-to-end-codes-for-the-bpsk |
| Repo | |
| Framework | |
Pseudo Labeling and Negative Feedback Learning for Large-scale Multi-label Domain Classification
| Title | Pseudo Labeling and Negative Feedback Learning for Large-scale Multi-label Domain Classification |
| Authors | Joo-Kyung Kim, Young-Bum Kim |
| Abstract | In large-scale domain classification, an utterance can be handled by multiple domains with overlapped capabilities. However, only a limited number of ground-truth domains are provided for each training utterance in practice while knowing as many as correct target labels is helpful for improving the model performance. In this paper, given one ground-truth domain for each training utterance, we regard domains consistently predicted with the highest confidences as additional pseudo labels for the training. In order to reduce prediction errors due to incorrect pseudo labels, we leverage utterances with negative system responses to decrease the confidences of the incorrectly predicted domains. Evaluating on user utterances from an intelligent conversational system, we show that the proposed approach significantly improves the performance of domain classification with hypothesis reranking. |
| Tasks | |
| Published | 2020-03-08 |
| URL | https://arxiv.org/abs/2003.03728v1 |
| https://arxiv.org/pdf/2003.03728v1.pdf | |
| PWC | https://paperswithcode.com/paper/pseudo-labeling-and-negative-feedback |
| Repo | |
| Framework | |
Don’t Forget The Past: Recurrent Depth Estimation from Monocular Video
| Title | Don’t Forget The Past: Recurrent Depth Estimation from Monocular Video |
| Authors | Vaishakh Patil, Wouter Van Gansbeke, Dengxin Dai, Luc Van Gool |
| Abstract | Autonomous cars need continuously updated depth information. Thus far, the depth is mostly estimated independently for a single frame at a time, even if the method starts from video input. Our method produces a time series of depth maps, which makes it an ideal candidate for online learning approaches. In particular, we put three different types of depth estimation (supervised depth prediction, self-supervised depth prediction, and self-supervised depth completion) into a common framework. We integrate the corresponding networks with a convolutional LSTM such that the spatiotemporal structures of depth across frames can be exploited to yield a more accurate depth estimation. Our method is flexible. It can be applied to monocular videos only or be combined with different types of sparse depth patterns. We carefully study the architecture of the recurrent network and its training strategy. We are first to successfully exploit recurrent networks for real-time self-supervised monocular depth estimation and completion. Extensive experiments show that our recurrent method outperforms its image-based counterpart consistently and significantly in both self-supervised scenarios. It also outperforms previous depth estimation methods of the three popular groups. |
| Tasks | Depth Completion, Depth Estimation, Monocular Depth Estimation, Time Series |
| Published | 2020-01-08 |
| URL | https://arxiv.org/abs/2001.02613v1 |
| https://arxiv.org/pdf/2001.02613v1.pdf | |
| PWC | https://paperswithcode.com/paper/dont-forget-the-past-recurrent-depth |
| Repo | |
| Framework | |
Optical Fiber Channel Modeling Using Conditional Generative Adversarial Network
| Title | Optical Fiber Channel Modeling Using Conditional Generative Adversarial Network |
| Authors | Hang Yang, Zekun Niu, Lilin Yi, Shilin Xiao |
| Abstract | In this paper, we use CGAN (conditional generative adversarial network) to model the fiber-optic channel and the performance is similar with the conventional method, SSFM (split-step Fourier method), while the running time is reduced from several minutes to about 2 seconds at 80-km distance. |
| Tasks | |
| Published | 2020-02-28 |
| URL | https://arxiv.org/abs/2002.12648v1 |
| https://arxiv.org/pdf/2002.12648v1.pdf | |
| PWC | https://paperswithcode.com/paper/optical-fiber-channel-modeling-using |
| Repo | |
| Framework | |
Gaussian process imputation of multiple financial series
| Title | Gaussian process imputation of multiple financial series |
| Authors | Taco de Wolff, Alejandro Cuevas, Felipe Tobar |
| Abstract | In Financial Signal Processing, multiple time series such as financial indicators, stock prices and exchange rates are strongly coupled due to their dependence on the latent state of the market and therefore they are required to be jointly analysed. We focus on learning the relationships among financial time series by modelling them through a multi-output Gaussian process (MOGP) with expressive covariance functions. Learning these market dependencies among financial series is crucial for the imputation and prediction of financial observations. The proposed model is validated experimentally on two real-world financial datasets for which their correlations across channels are analysed. We compare our model against other MOGPs and the independent Gaussian process on real financial data. |
| Tasks | Imputation, Time Series |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.05789v1 |
| https://arxiv.org/pdf/2002.05789v1.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-process-imputation-of-multiple |
| Repo | |
| Framework | |
Exact Indexing of Time Series under Dynamic Time Warping
| Title | Exact Indexing of Time Series under Dynamic Time Warping |
| Authors | Zhengxin Li |
| Abstract | Dynamic time warping (DTW) is a robust similarity measure of time series. However, it does not satisfy triangular inequality and has high computational complexity, severely limiting its applications in similarity search on large-scale datasets. Usually, we resort to lower bounding distances to speed up similarity search under DTW. Unfortunately, there is still a lack of an effective lower bounding distance that can measure unequal-length time series and has desirable tightness. In the paper, we propose a novel lower bounding distance LB_Keogh+, which is a seamless combination of sequence extension and LB_Keogh. It can be used for unequal-length sequences and has low computational complexity. Besides, LB_Keogh+ can extend sequences to an arbitrary suitable length, without significantly reducing tightness. Next, based on LB_Keogh+, an exact index of time series under DTW is devised. Then, we introduce several theorems and complete the relevant proofs to guarantee no false dismissals in our similarity search. Finally, extensive experiments are conducted on real-world datasets. Experimental results indicate that our proposed method can perform similarity search of unequal-length sequences with high tightness and good pruning power. |
| Tasks | Time Series |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04187v1 |
| https://arxiv.org/pdf/2002.04187v1.pdf | |
| PWC | https://paperswithcode.com/paper/exact-indexing-of-time-series-under-dynamic |
| Repo | |
| Framework | |
Time Series Alignment with Global Invariances
| Title | Time Series Alignment with Global Invariances |
| Authors | Titouan Vayer, Laetitia Chapel, Nicolas Courty, Rémi Flamary, Yann Soullard, Romain Tavenard |
| Abstract | In this work we address the problem of comparing time series while taking into account both feature space transformation and temporal variability. The proposed framework combines a latent global transformation of the feature space with the widely used Dynamic Time Warping (DTW). The latent global transformation captures the feature invariance while the DTW (or its smooth counterpart soft-DTW) deals with the temporal shifts. We cast the problem as a joint optimization over the global transformation and the temporal alignments. The versatility of our framework allows for several variants depending on the invariance class at stake. Among our contributions we define a differentiable loss for time series and present two algorithms for the computation of time series barycenters under our new geometry. We illustrate the interest of our approach on both simulated and real world data. |
| Tasks | Time Series, Time Series Alignment |
| Published | 2020-02-10 |
| URL | https://arxiv.org/abs/2002.03848v1 |
| https://arxiv.org/pdf/2002.03848v1.pdf | |
| PWC | https://paperswithcode.com/paper/time-series-alignment-with-global-invariances |
| Repo | |
| Framework | |
