Paper Group ANR 145
FastPET: Near Real-Time PET Reconstruction from Histo-Images Using a Neural Network. Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective. Toward Low-Cost and Stable Blockchain Networks. A Novel Image Dehazing and Assessment Method. Deep-Learning-Enabled Simulated Annealing for Topology Optimizat …
FastPET: Near Real-Time PET Reconstruction from Histo-Images Using a Neural Network
| Title | FastPET: Near Real-Time PET Reconstruction from Histo-Images Using a Neural Network |
| Authors | William Whiteley, Vladimir Panin, Chuanyu Zhou, Jorge Cabello, Deepak Bharkhada, Jens Gregor |
| Abstract | Direct reconstruction of positron emission tomography (PET) data using deep neural networks is a growing field of research. Initial results are promising, but often the networks are complex, memory utilization inefficient, produce relatively small image sizes (e.g. 128x128), and low count rate reconstructions are of varying quality. This paper proposes FastPET, a novel direct reconstruction convolutional neural network that is architecturally simple, memory space efficient, produces larger images (e.g. 440x440) and is capable of processing a wide range of count densities. FastPET operates on noisy and blurred histo-images reconstructing clinical-quality multi-slice image volumes 800x faster than ordered subsets expectation maximization (OSEM). Patient data studies show a higher contrast recovery value than for OSEM with equivalent variance and a higher overall signal-to-noise ratio with both cases due to FastPET’s lower noise images. This work also explored the application to low dose PET imaging and found FastPET able to produce images comparable to normal dose with only 50% and 25% counts. We additionally explored the effect of reducing the anatomical region by training specific FastPET variants on brain and chest images and found narrowing the data distribution led to increased performance. |
| Tasks | |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04665v1 |
| https://arxiv.org/pdf/2002.04665v1.pdf | |
| PWC | https://paperswithcode.com/paper/fastpet-near-real-time-pet-reconstruction |
| Repo | |
| Framework | |
Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
| Title | Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective |
| Authors | Muhammad Abdullah Jamal, Matthew Brown, Ming-Hsuan Yang, Liqiang Wang, Boqing Gong |
| Abstract | Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our expectation of the model to perform well on all classes. We analyze this mismatch from a domain adaptation point of view. First of all, we connect existing class-balanced methods for long-tailed classification to target shift, a well-studied scenario in domain adaptation. The connection reveals that these methods implicitly assume that the training data and test data share the same class-conditioned distribution, which does not hold in general and especially for the tail classes. While a head class could contain abundant and diverse training examples that well represent the expected data at inference time, the tail classes are often short of representative training data. To this end, we propose to augment the classic class-balanced learning by explicitly estimating the differences between the class-conditioned distributions with a meta-learning approach. We validate our approach with six benchmark datasets and three loss functions. |
| Tasks | Domain Adaptation, Meta-Learning |
| Published | 2020-03-24 |
| URL | https://arxiv.org/abs/2003.10780v1 |
| https://arxiv.org/pdf/2003.10780v1.pdf | |
| PWC | https://paperswithcode.com/paper/rethinking-class-balanced-methods-for-long |
| Repo | |
| Framework | |
Toward Low-Cost and Stable Blockchain Networks
| Title | Toward Low-Cost and Stable Blockchain Networks |
| Authors | Minghong Fang, Jia Liu |
| Abstract | Envisioned to be the future of secured distributed systems, blockchain networks have received increasing attention from both the industry and academia in recent years. However, blockchain mining processes demand high hardware costs and consume a vast amount of energy (studies have shown that the amount of energy consumed in Bitcoin mining is almost the same as the electricity used in Ireland). To address the high mining cost problem of blockchain networks, in this paper, we propose a blockchain mining resources allocation algorithm to reduce the mining cost in PoW-based (proof-of-work-based) blockchain networks. We first propose an analytical queueing model for general blockchain networks. In our queueing model, transactions arrive randomly to the queue and are served in a batch manner with unknown service rate probability distribution and agnostic to any priority mechanism. Then, we leverage the Lyapunov optimization techniques to propose a dynamic mining resources allocation algorithm (DMRA), which is parameterized by a tuning parameter $K>0$. We show that our algorithm achieves an $[O(1/K), O(K)]$ cost-optimality-gap-vs-delay tradeoff. Our simulation results also demonstrate the effectiveness of DMRA in reducing mining costs. |
| Tasks | |
| Published | 2020-02-19 |
| URL | https://arxiv.org/abs/2002.08027v2 |
| https://arxiv.org/pdf/2002.08027v2.pdf | |
| PWC | https://paperswithcode.com/paper/toward-low-cost-and-stable-blockchain |
| Repo | |
| Framework | |
A Novel Image Dehazing and Assessment Method
| Title | A Novel Image Dehazing and Assessment Method |
| Authors | Saad Bin Sami, Abdul Muqeet, Humera Tariq |
| Abstract | Images captured in hazy weather conditions often suffer from color contrast and color fidelity. This degradation is represented by transmission map which represents the amount of attenuation and airlight which represents the color of additive noise. In this paper, we have proposed a method to estimate the transmission map using haze levels instead of airlight color since there are some ambiguities in estimation of airlight. Qualitative and quantitative results of proposed method show competitiveness of the method given. In addition we have proposed two metrics which are based on statistics of natural outdoor images for assessment of haze removal algorithms. |
| Tasks | Image Dehazing |
| Published | 2020-01-20 |
| URL | https://arxiv.org/abs/2001.06963v1 |
| https://arxiv.org/pdf/2001.06963v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-image-dehazing-and-assessment-method |
| Repo | |
| Framework | |
Deep-Learning-Enabled Simulated Annealing for Topology Optimization
| Title | Deep-Learning-Enabled Simulated Annealing for Topology Optimization |
| Authors | Changyu Deng, Can Qin, Wei Lu |
| Abstract | Topology optimization by distributing materials in a domain requires stochastic optimizers to solve highly complicated problems. However, solving such problems requires millions of finite element calculations with hundreds of design variables or more involved , whose computational cost is huge and often unacceptable. To speed up computation, here we report a method to integrate deep learning into stochastic optimization algorithm. A Deep Neural Network (DNN) learns and substitutes the objective function by forming a loop with Generative Simulated Annealing (GSA). In each iteration, GSA uses DNN to evaluate the objective function to obtain an optimized solution, based on which new training data are generated; thus, DNN enhances its accuracy and GSA could accordingly improve its solution in next iteration until convergence. Our algorithm was tested by compliance minimization problems and reduced computational time by over two orders of magnitude. This approach sheds light on solving large multi-dimensional optimization problems. |
| Tasks | Stochastic Optimization |
| Published | 2020-02-04 |
| URL | https://arxiv.org/abs/2002.01927v1 |
| https://arxiv.org/pdf/2002.01927v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-enabled-simulated-annealing-for |
| Repo | |
| Framework | |
Safe Counterfactual Reinforcement Learning
| Title | Safe Counterfactual Reinforcement Learning |
| Authors | Yusuke Narita, Shota Yasui, Kohei Yata |
| Abstract | We develop a method for predicting the performance of reinforcement learning and bandit algorithms, given historical data that may have been generated by a different algorithm. Our estimator has the property that its prediction converges in probability to the true performance of a counterfactual algorithm at the fast $\sqrt{N}$ rate, as the sample size $N$ increases. We also show a correct way to estimate the variance of our prediction, thus allowing the analyst to quantify the uncertainty in the prediction. These properties hold even when the analyst does not know which among a large number of potentially important state variables are really important. These theoretical guarantees make our estimator safe to use. We finally apply it to improve advertisement design by a major advertisement company. We find that our method produces smaller mean squared errors than state-of-the-art methods. |
| Tasks | |
| Published | 2020-02-20 |
| URL | https://arxiv.org/abs/2002.08536v1 |
| https://arxiv.org/pdf/2002.08536v1.pdf | |
| PWC | https://paperswithcode.com/paper/safe-counterfactual-reinforcement-learning |
| Repo | |
| Framework | |
Measuring Diversity of Artificial Intelligence Conferences
| Title | Measuring Diversity of Artificial Intelligence Conferences |
| Authors | Ana Freire, Lorenzo Porcaro, Emilia Gómez |
| Abstract | The lack of diversity of the Artificial Intelligence (AI) field is nowadays a concern, and several initiatives such as funding schemes and mentoring programs have been designed to fight against it. However, there is no indication on how these initiatives actually impact AI diversity in the short and long term. This work studies the concept of diversity in this particular context and proposes a small set of diversity indicators (i.e. indexes) of AI scientific events. These indicators are designed to quantify the lack of diversity of the AI field and monitor its evolution. We consider diversity in terms of gender, geographical location and business (understood as the presence of academia versus industry). We compute these indicators for the different communities of a conference: authors, keynote speakers and organizing committee. From these components we compute a summarized diversity indicator for each AI event. We evaluate the proposed indexes for a set of recent major AI conferences and we discuss their values and limitations. |
| Tasks | |
| Published | 2020-01-20 |
| URL | https://arxiv.org/abs/2001.07038v1 |
| https://arxiv.org/pdf/2001.07038v1.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-diversity-of-artificial |
| Repo | |
| Framework | |
Real-Time Dispatching of Large-Scale Ride-Sharing Systems: Integrating Optimization, Machine Learning, and Model Predictive Control
| Title | Real-Time Dispatching of Large-Scale Ride-Sharing Systems: Integrating Optimization, Machine Learning, and Model Predictive Control |
| Authors | Connor Riley, Pascal Van Hentenryck, Enpeng Yuan |
| Abstract | This paper considers the dispatching of large-scale real-time ride-sharing systems to address congestion issues faced by many cities. The goal is to serve all customers (service guarantees) with a small number of vehicles while minimizing waiting times under constraints on ride duration. This paper proposes an end-to-end approach that tightly integrates a state-of-the-art dispatching algorithm, a machine-learning model to predict zone-to-zone demand over time, and a model predictive control optimization to relocate idle vehicles. Experiments using historic taxi trips in New York City indicate that this integration decreases average waiting times by about 30% over all test cases and reaches close to 55% on the largest instances for high-demand zones. |
| Tasks | |
| Published | 2020-03-24 |
| URL | https://arxiv.org/abs/2003.10942v1 |
| https://arxiv.org/pdf/2003.10942v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-dispatching-of-large-scale-ride |
| Repo | |
| Framework | |
MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation
| Title | MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation |
| Authors | Sicheng Zhao, Bo Li, Xiangyu Yue, Pengfei Xu, Kurt Keutzer |
| Abstract | Domain adaptation aims to learn a transferable model to bridge the domain shift between one labeled source domain and another sparsely labeled or unlabeled target domain. Since the labeled data may be collected from multiple sources, multi-source domain adaptation (MDA) has attracted increasing attention. Recent MDA methods do not consider the pixel-level alignment between sources and target or the misalignment across different sources. In this paper, we propose a novel MDA framework to address these challenges. Specifically, we design an end-to-end Multi-source Adversarial Domain Aggregation Network (MADAN). First, an adapted domain is generated for each source with dynamic semantic consistency while aligning towards the target at the pixel-level cycle-consistently. Second, sub-domain aggregation discriminator and cross-domain cycle discriminator are proposed to make different adapted domains more closely aggregated. Finally, feature-level alignment is performed between the aggregated domain and the target domain while training the task network. For the segmentation adaptation, we further enforce category-level alignment and incorporate context-aware generation, which constitutes MADAN+. We conduct extensive MDA experiments on digit recognition, object classification, and simulation-to-real semantic segmentation. The results demonstrate that the proposed MADAN and MANDA+ models outperform state-of-the-art approaches by a large margin. |
| Tasks | Domain Adaptation, Object Classification, Semantic Segmentation |
| Published | 2020-02-19 |
| URL | https://arxiv.org/abs/2003.00820v1 |
| https://arxiv.org/pdf/2003.00820v1.pdf | |
| PWC | https://paperswithcode.com/paper/madan-multi-source-adversarial-domain |
| Repo | |
| Framework | |
3D ResNet with Ranking Loss Function for Abnormal Activity Detection in Videos
| Title | 3D ResNet with Ranking Loss Function for Abnormal Activity Detection in Videos |
| Authors | Shikha Dubey, Abhijeet Boragule, Moongu Jeon |
| Abstract | Abnormal activity detection is one of the most challenging tasks in the field of computer vision. This study is motivated by the recent state-of-art work of abnormal activity detection, which utilizes both abnormal and normal videos in learning abnormalities with the help of multiple instance learning by providing the data with video-level information. In the absence of temporal-annotations, such a model is prone to give a false alarm while detecting the abnormalities. For this reason, in this paper, we focus on the task of minimizing the false alarm rate while performing an abnormal activity detection task. The mitigation of these false alarms and recent advancement of 3D deep neural network in video action recognition task collectively give us motivation to exploit the 3D ResNet in our proposed method, which helps to extract spatial-temporal features from the videos. Afterwards, using these features and deep multiple instance learning along with the proposed ranking loss, our model learns to predict the abnormality score at the video segment level. Therefore, our proposed method 3D deep Multiple Instance Learning with ResNet (MILR) along with the new proposed ranking loss function achieves the best performance on the UCF-Crime benchmark dataset, as compared to other state-of-art methods. The effectiveness of our proposed method is demonstrated on the UCF-Crime dataset. |
| Tasks | Action Detection, Activity Detection, Multiple Instance Learning, Temporal Action Localization |
| Published | 2020-02-04 |
| URL | https://arxiv.org/abs/2002.01132v1 |
| https://arxiv.org/pdf/2002.01132v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-resnet-with-ranking-loss-function-for |
| Repo | |
| Framework | |
Effective AER Object Classification Using Segmented Probability-Maximization Learning in Spiking Neural Networks
| Title | Effective AER Object Classification Using Segmented Probability-Maximization Learning in Spiking Neural Networks |
| Authors | Qianhui Liu, Haibo Ruan, Dong Xing, Huajin Tang, Gang Pan |
| Abstract | Address event representation (AER) cameras have recently attracted more attention due to the advantages of high temporal resolution and low power consumption, compared with traditional frame-based cameras. Since AER cameras record the visual input as asynchronous discrete events, they are inherently suitable to coordinate with the spiking neural network (SNN), which is biologically plausible and energy-efficient on neuromorphic hardware. However, using SNN to perform the AER object classification is still challenging, due to the lack of effective learning algorithms for this new representation. To tackle this issue, we propose an AER object classification model using a novel segmented probability-maximization (SPA) learning algorithm. Technically, 1) the SPA learning algorithm iteratively maximizes the probability of the classes that samples belong to, in order to improve the reliability of neuron responses and effectiveness of learning; 2) a peak detection (PD) mechanism is introduced in SPA to locate informative time points segment by segment, based on which information within the whole event stream can be fully utilized by the learning. Extensive experimental results show that, compared to state-of-the-art methods, not only our model is more effective, but also it requires less information to reach a certain level of accuracy. |
| Tasks | Object Classification |
| Published | 2020-02-14 |
| URL | https://arxiv.org/abs/2002.06199v1 |
| https://arxiv.org/pdf/2002.06199v1.pdf | |
| PWC | https://paperswithcode.com/paper/effective-aer-object-classification-using |
| Repo | |
| Framework | |
Forecasting Industrial Aging Processes with Machine Learning Methods
| Title | Forecasting Industrial Aging Processes with Machine Learning Methods |
| Authors | Mihail Bogojeski, Simeon Sauer, Franziska Horn, Klaus-Robert Müller |
| Abstract | By accurately predicting industrial aging processes (IAPs), it is possible to schedule maintenance events further in advance, thereby ensuring a cost-efficient and reliable operation of the plant. So far, these degradation processes were usually described by mechanistic models or simple empirical prediction models. In this paper, we evaluate a wider range of data-driven models for this task, comparing some traditional stateless models (linear and kernel ridge regression, feed-forward neural networks) to more complex recurrent neural networks (echo state networks and LSTMs). To examine how much historical data is needed to train each of the models, we first examine their performance on a synthetic dataset with known dynamics. Next, the models are tested on real-world data from a large scale chemical plant. Our results show that LSTMs produce near perfect predictions when trained on a large enough dataset, while linear models may generalize better given small datasets with changing conditions. |
| Tasks | |
| Published | 2020-02-05 |
| URL | https://arxiv.org/abs/2002.01768v1 |
| https://arxiv.org/pdf/2002.01768v1.pdf | |
| PWC | https://paperswithcode.com/paper/forecasting-industrial-aging-processes-with |
| Repo | |
| Framework | |
Object Detection as a Positive-Unlabeled Problem
| Title | Object Detection as a Positive-Unlabeled Problem |
| Authors | Yuewei Yang, Kevin J Liang, Lawrence Carin |
| Abstract | As with other deep learning methods, label quality is important for learning modern convolutional object detectors. However, the potentially large number and wide diversity of object instances that can be found in complex image scenes makes constituting complete annotations a challenging task; objects missing annotations can be observed in a variety of popular object detection datasets. These missing annotations can be problematic, as the standard cross-entropy loss employed to train object detection models treats classification as a positive-negative (PN) problem: unlabeled regions are implicitly assumed to be background. As such, any object missing a bounding box results in a confusing learning signal, the effects of which we observe empirically. To remedy this, we propose treating object detection as a positive-unlabeled (PU) problem, which removes the assumption that unlabeled regions must be negative. We demonstrate that our proposed PU classification loss outperforms the standard PN loss on PASCAL VOC and MS COCO across a range of label missingness, as well as on Visual Genome and DeepLesion with full labels. |
| Tasks | Object Detection |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04672v1 |
| https://arxiv.org/pdf/2002.04672v1.pdf | |
| PWC | https://paperswithcode.com/paper/object-detection-as-a-positive-unlabeled |
| Repo | |
| Framework | |
Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation
| Title | Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation |
| Authors | Myeongjin Kim, Hyeran Byun |
| Abstract | Since annotating pixel-level labels for semantic segmentation is laborious, leveraging synthetic data is an attractive solution. However, due to the domain gap between synthetic domain and real domain, it is challenging for a model trained with synthetic data to generalize to real data. In this paper, considering the fundamental difference between the two domains as the texture, we propose a method to adapt to the texture of the target domain. First, we diversity the texture of synthetic images using a style transfer algorithm. The various textures of generated images prevent a segmentation model from overfitting to one specific (synthetic) texture. Then, we fine-tune the model with self-training to get direct supervision of the target texture. Our results achieve state-of-the-art performance and we analyze the properties of the model trained on the stylized dataset with extensive experiments. |
| Tasks | Domain Adaptation, Semantic Segmentation, Style Transfer |
| Published | 2020-03-02 |
| URL | https://arxiv.org/abs/2003.00867v2 |
| https://arxiv.org/pdf/2003.00867v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-texture-invariant-representation-for |
| Repo | |
| Framework | |
Advances in Deep Space Exploration via Simulators & Deep Learning
| Title | Advances in Deep Space Exploration via Simulators & Deep Learning |
| Authors | James Bird, Linda Petzold, Philip Lubin, Dulia Deacon |
| Abstract | The StarLight program conceptualizes fast interstellar travel via small wafer satellites (wafersats) that are propelled by directed energy. This process is wildly different from traditional space travel and trades large and slow spacecraft for small, fast, inexpensive, and fragile ones. The main goal of these wafer satellites is to gather useful images during their deep space journey. We introduce and solve some of the main problems that accompany this concept. First, we need an object detection system that can detect planets that we have never seen before, some containing features that we may not even know exist in the universe. Second, once we have images of exoplanets, we need a way to take these images and rank them by importance. Equipment fails and data rates are slow, thus we need a method to ensure that the most important images to humankind are the ones that are prioritized for data transfer. Finally, the energy on board is minimal and must be conserved and used sparingly. No exoplanet images should be missed, but using energy erroneously would be detrimental. We introduce simulator-based methods that leverage artificial intelligence, mostly in the form of computer vision, in order to solve all three of these issues. Our results confirm that simulators provide an extremely rich training environment that surpasses that of real images, and can be used to train models on features that have yet to be observed by humans. We also show that the immersive and adaptable environment provided by the simulator, combined with deep learning, lets us navigate and save energy in an otherwise implausible way. |
| Tasks | Object Detection |
| Published | 2020-02-10 |
| URL | https://arxiv.org/abs/2002.04051v1 |
| https://arxiv.org/pdf/2002.04051v1.pdf | |
| PWC | https://paperswithcode.com/paper/advances-in-deep-space-exploration-via |
| Repo | |
| Framework | |
