Paper Group ANR 846
Operational Calibration: Debugging Confidence Errors for DNNs in the Field. Attentional Policies for Cross-Context Multi-Agent Reinforcement Learning. Computer-supported Analysis of Positive Properties, Ultrafilters and Modal Collapse in Variants of Gödel’s Ontological Argument. Deep Direct Visual Odometry. A Keyframe-based Continuous Visual SLAM f …
Operational Calibration: Debugging Confidence Errors for DNNs in the Field
| Title | Operational Calibration: Debugging Confidence Errors for DNNs in the Field |
| Authors | Zenan Li, Xiaoxing Ma, Chang Xu, Jingwei Xu, Chun Cao, Jian Lü |
| Abstract | Trained DNN models are increasingly adopted as integral parts of software systems. However, they are often over-confident, especially in practical operation domains where slight divergence from their training data almost always exists. To minimize the loss due to inaccurate confidence, operational calibration, i.e., calibrating the confidence function of a DNN classifier against its operation domain, becomes a necessary debugging step in the engineering of the whole system. Operational calibration is difficult considering the limited budget of labeling operation data and the weak interpretability of DNN models. We propose a Bayesian approach to operational calibration that gradually corrects the confidence given by the model under calibration with a small number of labeled operational data deliberately selected from a larger set of unlabeled operational data. Exploiting the locality of the learned representation of the DNN model and modeling the calibration as Gaussian Process Regression, the approach achieves impressive efficacy and efficiency. Comprehensive experiments with various practical data sets and DNN models show that it significantly outperformed alternative methods, and in some difficult tasks it eliminated about 71% to 97% high-confidence errors with only about 10% of the minimal amount of labeled operation data needed for practical learning techniques to barely work. |
| Tasks | Calibration |
| Published | 2019-10-06 |
| URL | https://arxiv.org/abs/1910.02352v1 |
| https://arxiv.org/pdf/1910.02352v1.pdf | |
| PWC | https://paperswithcode.com/paper/operational-calibration-debugging-confidence |
| Repo | |
| Framework | |
Attentional Policies for Cross-Context Multi-Agent Reinforcement Learning
| Title | Attentional Policies for Cross-Context Multi-Agent Reinforcement Learning |
| Authors | Matthew A. Wright, Roberto Horowitz |
| Abstract | Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other methods of training an individual, discrete policy for each agent and then enforcing cooperation through some additional inter-policy mechanism, we follow the spirit of recent work on the power of relational inductive biases in deep networks by learning multi-agent relationships at the policy level via an attentional architecture. In our method, all agents share the same policy, but independently apply it in their own context to aggregate the other agents’ state information when selecting their next action. The structure of our architectures allow them to be applied on environments with varying numbers of agents. We demonstrate our architecture on a benchmark multi-agent autonomous vehicle coordination problem, obtaining superior results to a full-knowledge, fully-centralized reference solution, and significantly outperforming it when scaling to large numbers of agents. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13428v1 |
| https://arxiv.org/pdf/1905.13428v1.pdf | |
| PWC | https://paperswithcode.com/paper/attentional-policies-for-cross-context-multi |
| Repo | |
| Framework | |
Computer-supported Analysis of Positive Properties, Ultrafilters and Modal Collapse in Variants of Gödel’s Ontological Argument
| Title | Computer-supported Analysis of Positive Properties, Ultrafilters and Modal Collapse in Variants of Gödel’s Ontological Argument |
| Authors | Christoph Benzmüller, David Fuenmayor |
| Abstract | Three variants of Kurt G"odel’s ontological argument, proposed by Dana Scott, C. Anthony Anderson and Melvin Fitting, are encoded and rigorously assessed on the computer. In contrast to Scott’s version of G"odel’s argument the two variants contributed by Anderson and Fitting avoid modal collapse. Although they appear quite different on a cursory reading they are in fact closely related. This has been revealed in the computer-supported formal analysis presented in this article. Key to our formal analysis is the utilization of suitably adapted notions of (modal) ultrafilters, and a careful distinction between extensions and intensions of positive properties. |
| Tasks | |
| Published | 2019-10-20 |
| URL | https://arxiv.org/abs/1910.08955v2 |
| https://arxiv.org/pdf/1910.08955v2.pdf | |
| PWC | https://paperswithcode.com/paper/computer-supported-analysis-of-positive |
| Repo | |
| Framework | |
Deep Direct Visual Odometry
| Title | Deep Direct Visual Odometry |
| Authors | Chaoqiang Zhao, Yang Tang, Qiyu Sun |
| Abstract | Monocular direct visual odometry (DVO) relies heavily on high-quality images and good initial pose estimation for accuracy tracking process, which means that DVO may fail if the image quality is poor or the initial value is incorrect. In this study, we present a new architecture to overcome the above limitations by embedding deep learning into DVO. A novel self-supervised network architecture for effectively predicting 6-DOF pose is proposed in this paper, and we incorporate the pose prediction into Direct Sparse Odometry (DSO) for robust initialization and tracking process. Furthermore, the attention mechanism is included to select useful features for accurate pose regression. The experiments on the KITTI dataset show that the proposed network achieves an outstanding performance compared with previous self-supervised methods, and the integration with pose network makes the initialization and tracking of DSO more robust and accurate. |
| Tasks | Pose Estimation, Pose Prediction, Visual Odometry |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05101v1 |
| https://arxiv.org/pdf/1912.05101v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-direct-visual-odometry |
| Repo | |
| Framework | |
A Keyframe-based Continuous Visual SLAM for RGB-D Cameras via Nonparametric Joint Geometric and Appearance Representation
| Title | A Keyframe-based Continuous Visual SLAM for RGB-D Cameras via Nonparametric Joint Geometric and Appearance Representation |
| Authors | Xi Lin, Dingyi Sun, Tzu-Yuan Lin, Ryan M. Eustice, Maani Ghaffari |
| Abstract | This paper reports on a robust RGB-D SLAM system that performs well in scarcely textured and structured environments. We present a novel keyframe-based continuous visual odometry that builds on the recently developed continuous sensor registration framework. A joint geometric and appearance representation is the result of transforming the RGB-D images into functions that live in a Reproducing Kernel Hilbert Space (RKHS). We solve both registration and keyframe selection problems via the inner product structure available in the RKHS. We also extend the proposed keyframe-based odometry method to a SLAM system using indirect ORB loop-closure constraints. The experimental evaluations using publicly available RGB-D benchmarks show that the developed keyframe selection technique using continuous visual odometry outperforms its robust dense (and direct) visual odometry equivalent. In addition, the developed SLAM system has better generalization across different training and validation sequences; it is robust to the lack of texture and structure in the scene; and shows comparable performance with the state-of-the-art SLAM systems. |
| Tasks | Visual Odometry |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.01064v1 |
| https://arxiv.org/pdf/1912.01064v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-keyframe-based-continuous-visual-slam-for |
| Repo | |
| Framework | |
Patchwork: A Patch-wise Attention Network for Efficient Object Detection and Segmentation in Video Streams
| Title | Patchwork: A Patch-wise Attention Network for Efficient Object Detection and Segmentation in Video Streams |
| Authors | Yuning Chai |
| Abstract | Recent advances in single-frame object detection and segmentation techniques have motivated a wide range of works to extend these methods to process video streams. In this paper, we explore the idea of hard attention aimed for latency-sensitive applications. Instead of reasoning about every frame separately, our method selects and only processes a small sub-window of the frame. Our technique then makes predictions for the full frame based on the sub-windows from previous frames and the update from the current sub-window. The latency reduction by this hard attention mechanism comes at the cost of degraded accuracy. We made two contributions to address this. First, we propose a specialized memory cell that recovers lost context when processing sub-windows. Secondly, we adopt a Q-learning-based policy training strategy that enables our approach to intelligently select the sub-windows such that the staleness in the memory hurts the performance the least. Our experiments suggest that our approach reduces the latency by approximately four times without significantly sacrificing the accuracy on the ImageNet VID video object detection dataset and the DAVIS video object segmentation dataset. We further demonstrate that we can reinvest the saved computation into other parts of the network, and thus resulting in an accuracy increase at a comparable computational cost as the original system and beating other recently proposed state-of-the-art methods in the low latency range. |
| Tasks | Object Detection, Q-Learning, Semantic Segmentation, Video Object Detection, Video Object Segmentation, Video Semantic Segmentation |
| Published | 2019-04-03 |
| URL | https://arxiv.org/abs/1904.01784v2 |
| https://arxiv.org/pdf/1904.01784v2.pdf | |
| PWC | https://paperswithcode.com/paper/patchwork-a-patch-wise-attention-network-for |
| Repo | |
| Framework | |
Energy Efficient Federated Learning Over Wireless Communication Networks
| Title | Energy Efficient Federated Learning Over Wireless Communication Networks |
| Authors | Zhaohui Yang, Mingzhe Chen, Walid Saad, Choong Seon Hong, Mohammad Shikh-Bahaei |
| Abstract | In this paper, the problem of energy efficient transmission and computation resource allocation for federated learning (FL) over wireless communication networks is investigated. In the considered model, each user exploits limited local computational resources to train a local FL model with its collected data and, then, sends the trained FL model parameters to a base station (BS) which aggregates the local FL model and broadcasts it back to all of the users. Since FL involves an exchange of a learning model between users and the BS, both computation and communication latencies are determined by the learning accuracy level. Meanwhile, due to the limited energy budget of the wireless users, both local computation energy and transmission energy must be considered during the FL process. This joint learning and communication problem is formulated as an optimization problem whose goal is to minimize a weighted sum of the completion time of FL, local computation energy, and transmission energy of all users, that captures the tradeoff of latency and energy consumption for FL. To solve this problem, an iterative algorithm is proposed where, at every step, closed-form solutions for time allocation, bandwidth allocation, power control, computation frequency, and learning accuracy are derived. For the special case that only minimizes the completion time, a bisection-based algorithm is proposed to obtain the optimal solution. Numerical results show that the proposed algorithms can reduce up to 25.6% delay and 37.6% energy consumption compared to conventional FL methods. |
| Tasks | |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02417v1 |
| https://arxiv.org/pdf/1911.02417v1.pdf | |
| PWC | https://paperswithcode.com/paper/energy-efficient-federated-learning-over |
| Repo | |
| Framework | |
A Heuristic for Efficient Reduction in Hidden Layer Combinations For Feedforward Neural Networks
| Title | A Heuristic for Efficient Reduction in Hidden Layer Combinations For Feedforward Neural Networks |
| Authors | Wei Hao Khoong |
| Abstract | In this paper, we describe the hyper-parameter search problem in the field of machine learning and present a heuristic approach in an attempt to tackle it. In most learning algorithms, a set of hyper-parameters must be determined before training commences. The choice of hyper-parameters can affect the final model’s performance significantly, but yet determining a good choice of hyper-parameters is in most cases complex and consumes large amount of computing resources. In this paper, we show the differences between an exhaustive search of hyper-parameters and a heuristic search, and show that there is a significant reduction in time taken to obtain the resulting model with marginal differences in evaluation metrics when compared to the benchmark case. |
| Tasks | |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.12226v3 |
| https://arxiv.org/pdf/1909.12226v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-heuristic-for-efficient-reduction-in-hidden |
| Repo | |
| Framework | |
Improving Semantic Segmentation via Dilated Affinity
| Title | Improving Semantic Segmentation via Dilated Affinity |
| Authors | Boxi Wu, Shuai Zhao, Wenqing Chu, Zheng Yang, Deng Cai |
| Abstract | Introducing explicit constraints on the structural predictions has been an effective way to improve the performance of semantic segmentation models. Existing methods are mainly based on insufficient hand-crafted rules that only partially capture the image structure, and some methods can also suffer from the efficiency issue. As a result, most of the state-of-the-art fully convolutional networks did not adopt these techniques. In this work, we propose a simple, fast yet effective method that exploits structural information through direct supervision with minor additional expense. To be specific, our method explicitly requires the network to predict semantic segmentation as well as dilated affinity, which is a sparse version of pair-wise pixel affinity. The capability of telling the relationships between pixels are directly built into the model and enhance the quality of segmentation in two stages. 1) Joint training with dilated affinity can provide robust feature representations and thus lead to finer segmentation results. 2) The extra output of affinity information can be further utilized to refine the original segmentation with a fast propagation process. Consistent improvements are observed on various benchmark datasets when applying our framework to the existing state-of-the-art model. Codes will be released soon. |
| Tasks | Semantic Segmentation |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.07011v2 |
| https://arxiv.org/pdf/1907.07011v2.pdf | |
| PWC | https://paperswithcode.com/paper/improving-semantic-segmentation-via-dilated |
| Repo | |
| Framework | |
RadGrad: Active learning with loss gradients
| Title | RadGrad: Active learning with loss gradients |
| Authors | Paul Budnarain, Renato Ferreira Pinto Junior, Ilan Kogan |
| Abstract | Solving sequential decision prediction problems, including those in imitation learning settings, requires mitigating the problem of covariate shift. The standard approach, DAgger, relies on capturing expert behaviour in all states that the agent reaches. In real-world settings, querying an expert is costly. We propose a new active learning algorithm that selectively queries the expert, based on both a prediction of agent error and a proxy for agent risk, that maintains the performance of unrestrained expert querying systems while substantially reducing the number of expert queries made. We show that our approach, RadGrad, has the potential to improve upon existing safety-aware algorithms, and matches or exceeds the performance of DAgger and variants (i.e., SafeDAgger) in one simulated environment. However, we also find that a more complex environment poses challenges not only to our proposed method, but also to existing safety-aware algorithms, which do not match the performance of DAgger in our experiments. |
| Tasks | Active Learning, Imitation Learning |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07838v1 |
| https://arxiv.org/pdf/1906.07838v1.pdf | |
| PWC | https://paperswithcode.com/paper/radgrad-active-learning-with-loss-gradients |
| Repo | |
| Framework | |
A Formal Proof of PAC Learnability for Decision Stumps
| Title | A Formal Proof of PAC Learnability for Decision Stumps |
| Authors | Joseph Tassarotti, Jean-Baptiste Tristan, Koundinya Vajjha |
| Abstract | We present a machine-checked, formal proof of PAC learnability of the concept class of decision stumps. A formal proof has every step checked and justified using fundamental axioms of mathematics. We construct and check our proof using the Lean theorem prover. Though such a proof appears simple, a few analytic and measure-theoretic subtleties arise when carrying it out fully formally. We explain how we can cleanly separate out the parts that deal with these subtleties by using Lean features and a category theoretic construction called the Giry monad. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.00385v2 |
| https://arxiv.org/pdf/1911.00385v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-formal-proof-of-pac-learnability-for |
| Repo | |
| Framework | |
Classificação de espécies de peixe utilizando redes neurais convolucional
| Title | Classificação de espécies de peixe utilizando redes neurais convolucional |
| Authors | Andre G. C. Pacheco |
| Abstract | Data classification is present in different real problems, such as recognizing patterns in images, differentiating defective parts in a production line, classifying benign and malignant tumors, among many others. Many of these problems have data patterns that are hard to identify, which requires more advanced techniques for resolution. Recently, several works addressing different artificial neural network architectures have been applied to solve classification problems. When the classification problem must be obtained through images, currently, the standard methodology is the use of convolutional neural networks. Thus, in this report convolutional neural networks are used to classify fish species. Classifica\c{c}~ao de dados est'a presente em diversos problemas reais, tais como: reconhecer padr~oes em imagens, diferenciar pe\c{c}as defeituosas em uma linha de produ\c{c}~ao, classificar tumores benignos e malignos, dentre diversas outras. Muitos desses problemas possuem padr~oes de dados dif'iceis de serem identificados, o que requer, consequentemente, t'ecnicas mais avan\c{c}adas para sua resolu\c{c}~ao. Recentemente, diversos trabalhos abordando diferentes arquiteturas de redes neurais artificiais v^em sendo aplicados para solucionar problemas de classifica\c{c}~ao. Quando a classifica\c{c}~ao do problema deve ser obtida por meio de imagens, atualmente a metodologia padr~ao 'e uso de redes neurais convolucionais. Sendo assim, neste trabalho s~ao utilizadas redes neurais convolucionais para classifica\c{c}~ao de esp'ecies de peixes. |
| Tasks | |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.03642v1 |
| https://arxiv.org/pdf/1905.03642v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503642 |
| Repo | |
| Framework | |
Progressive Sparse Local Attention for Video object detection
| Title | Progressive Sparse Local Attention for Video object detection |
| Authors | Chaoxu Guo, Bin Fan, Jie Gu, Qian Zhang, Shiming Xiang, Veronique Prinet, Chunhong Pan |
| Abstract | Transferring image-based object detectors to the domain of videos remains a challenging problem. Previous efforts mostly exploit optical flow to propagate features across frames, aiming to achieve a good trade-off between accuracy and efficiency. However, introducing an extra model to estimate optical flow can significantly increase the overall model size. The gap between optical flow and high-level features can also hinder it from establishing spatial correspondence accurately. Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressively sparser stride and uses the correspondence to propagate features. Based on PSLA, Recursive Feature Updating (RFU) and Dense Feature Transforming (DenseFT) are proposed to model temporal appearance and enrich feature representation respectively in a novel video object detection framework. Experiments on ImageNet VID show that our method achieves the best accuracy compared to existing methods with smaller model size and acceptable runtime speed. |
| Tasks | Object Detection, Optical Flow Estimation, Video Object Detection |
| Published | 2019-03-21 |
| URL | https://arxiv.org/abs/1903.09126v3 |
| https://arxiv.org/pdf/1903.09126v3.pdf | |
| PWC | https://paperswithcode.com/paper/progressive-sparse-local-attention-for-video |
| Repo | |
| Framework | |
Thompson Sampling for Contextual Bandit Problems with Auxiliary Safety Constraints
| Title | Thompson Sampling for Contextual Bandit Problems with Auxiliary Safety Constraints |
| Authors | Samuel Daulton, Shaun Singh, Vashist Avadhanula, Drew Dimmery, Eytan Bakshy |
| Abstract | Recent advances in contextual bandit optimization and reinforcement learning have garnered interest in applying these methods to real-world sequential decision making problems. Real-world applications frequently have constraints with respect to a currently deployed policy. Many of the existing constraint-aware algorithms consider problems with a single objective (the reward) and a constraint on the reward with respect to a baseline policy. However, many important applications involve multiple competing objectives and auxiliary constraints. In this paper, we propose a novel Thompson sampling algorithm for multi-outcome contextual bandit problems with auxiliary constraints. We empirically evaluate our algorithm on a synthetic problem. Lastly, we apply our method to a real world video transcoding problem and provide a practical way for navigating the trade-off between safety and performance using Bayesian optimization. |
| Tasks | Decision Making |
| Published | 2019-11-02 |
| URL | https://arxiv.org/abs/1911.00638v1 |
| https://arxiv.org/pdf/1911.00638v1.pdf | |
| PWC | https://paperswithcode.com/paper/thompson-sampling-for-contextual-bandit |
| Repo | |
| Framework | |
Respiratory Motion Correction in Abdominal MRI using a Densely Connected U-Net with GAN-guided Training
| Title | Respiratory Motion Correction in Abdominal MRI using a Densely Connected U-Net with GAN-guided Training |
| Authors | Wenhao Jiang, Zhiyu Liu, Kit-Hang Lee, Shihui Chen, Yui-Lun Ng, Qi Dou, Hing-Chiu Chang, Ka-Wai Kwok |
| Abstract | Abdominal magnetic resonance imaging (MRI) provides a straightforward way of characterizing tissue and locating lesions of patients as in standard diagnosis. However, abdominal MRI often suffers from respiratory motion artifacts, which leads to blurring and ghosting that significantly deteriorate the imaging quality. Conventional methods to reduce or eliminate these motion artifacts include breath holding, patient sedation, respiratory gating, and image post-processing, but these strategies inevitably involve extra scanning time and patient discomfort. In this paper, we propose a novel deep-learning-based model to recover MR images from respiratory motion artifacts. The proposed model comprises a densely connected U-net with generative adversarial network (GAN)-guided training and a perceptual loss function. We validate the model using a diverse collection of MRI data that are adversely affected by both synthetic and authentic respiration artifacts. Effective outcomes of motion removal are demonstrated. Our experimental results show the great potential of utilizing deep-learning-based methods in respiratory motion correction for abdominal MRI. |
| Tasks | |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.09745v1 |
| https://arxiv.org/pdf/1906.09745v1.pdf | |
| PWC | https://paperswithcode.com/paper/respiratory-motion-correction-in-abdominal |
| Repo | |
| Framework | |
