Paper Group ANR 72
Safety Guarantees for Planning Based on Iterative Gaussian Processes. Temporally Coherent General Dynamic Scene Reconstruction. The Pitfall of Evaluating Performance on Emerging AI Accelerators. A Dynamic Evolutionary Framework for Timeline Generation based on Distributed Representations. Disentangling neural mechanisms for perceptual grouping. Uns …
Safety Guarantees for Planning Based on Iterative Gaussian Processes
| Title | Safety Guarantees for Planning Based on Iterative Gaussian Processes |
| Authors | Kyriakos Polymenakos, Luca Laurenti, Andrea Patane, Jan-Peter Calliess, Luca Cardelli, Marta Kwiatkowska, Alessandro Abate, Stephen Roberts |
| Abstract | Gaussian Processes (GPs) are widely employed in control and learning because of their principled treatment of uncertainty. However, tracking uncertainty for iterative, multi-step predictions in general leads to an analytically intractable problem. While approximation methods exist, they do not come with guarantees, making it difficult to estimate their reliability and to trust their predictions. In this work, we derive formal probability error bounds for iterative prediction and planning with GPs. Building on GP properties, we bound the probability that random trajectories lie in specific regions around the predicted values. Namely, given a tolerance $\epsilon > 0 $, we compute regions around the predicted trajectory values, such that GP trajectories are guaranteed to lie inside them with probability at least $1-\epsilon$. We verify experimentally that our method tracks the predictive uncertainty correctly, even when current approximation techniques fail. Furthermore, we show how the proposed bounds can be employed within a safe reinforcement learning framework to verify the safety of candidate control policies, guiding the synthesis of provably safe controllers. |
| Tasks | Gaussian Processes |
| Published | 2019-11-29 |
| URL | https://arxiv.org/abs/1912.00071v2 |
| https://arxiv.org/pdf/1912.00071v2.pdf | |
| PWC | https://paperswithcode.com/paper/safety-guarantees-for-planning-based-on |
| Repo | |
| Framework | |
Temporally Coherent General Dynamic Scene Reconstruction
| Title | Temporally Coherent General Dynamic Scene Reconstruction |
| Authors | Armin Mustafa, Marco Volino, Hansung Kim, Jean-Yves Guillemaut, Adrian Hilton |
| Abstract | Existing techniques for dynamic scene reconstruction from multiple wide-baseline cameras primarily focus on reconstruction in controlled environments, with fixed calibrated cameras and strong prior constraints. This paper introduces a general approach to obtain a 4D representation of complex dynamic scenes from multi-view wide-baseline static or moving cameras without prior knowledge of the scene structure, appearance, or illumination. Contributions of the work are: An automatic method for initial coarse reconstruction to initialize joint estimation; Sparse-to-dense temporal correspondence integrated with joint multi-view segmentation and reconstruction to introduce temporal coherence; and a general robust approach for joint segmentation refinement and dense reconstruction of dynamic scenes by introducing shape constraint. Comparison with state-of-the-art approaches on a variety of complex indoor and outdoor scenes, demonstrates improved accuracy in both multi-view segmentation and dense reconstruction. This paper demonstrates unsupervised reconstruction of complete temporally coherent 4D scene models with improved non-rigid object segmentation and shape reconstruction and its application to free-viewpoint rendering and virtual reality. |
| Tasks | Semantic Segmentation |
| Published | 2019-07-18 |
| URL | https://arxiv.org/abs/1907.08195v1 |
| https://arxiv.org/pdf/1907.08195v1.pdf | |
| PWC | https://paperswithcode.com/paper/temporally-coherent-general-dynamic-scene |
| Repo | |
| Framework | |
The Pitfall of Evaluating Performance on Emerging AI Accelerators
| Title | The Pitfall of Evaluating Performance on Emerging AI Accelerators |
| Authors | Zihan Jiang, Jiansong Li, Jiangfeng Zhan |
| Abstract | In recent years, domain-specific hardware has brought significant performance improvements in deep learning (DL). Both industry and academia only focus on throughput when evaluating these AI accelerators, which usually are custom ASICs deployed in datacenter to speed up the inference phase of DL workloads. Pursuing higher hardware throughput such as OPS (Operation Per Second) using various optimizations seems to be their main design target. However, they ignore the importance of accuracy in the DL nature. Motivated by this, this paper argue that a single throughput metric can not comprehensively reflect the real-world performance of AI accelerators. To reveal this pitfall, we evaluates several frequently-used optimizations on a typical AI accelerator and quantifies their impact on accuracy and throughout under representative DL inference workloads. Based on our experimental results, we find that some optimizations cause significant loss on accuracy in some workloads, although it can improves the throughout. Furthermore, our results show the importance of end-to-end evaluation in DL. |
| Tasks | |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.02987v1 |
| https://arxiv.org/pdf/1911.02987v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-pitfall-of-evaluating-performance-on |
| Repo | |
| Framework | |
A Dynamic Evolutionary Framework for Timeline Generation based on Distributed Representations
| Title | A Dynamic Evolutionary Framework for Timeline Generation based on Distributed Representations |
| Authors | Dongyun Liang, Guohua Wang, Jing Nie |
| Abstract | Given the collection of timestamped web documents related to the evolving topic, timeline summarization (TS) highlights its most important events in the form of relevant summaries to represent the development of a topic over time. Most of the previous work focuses on fully-observable ranking models and depends on hand-designed features or complex mechanisms that may not generalize well. We present a novel dynamic framework for evolutionary timeline generation leveraging distributed representations, which dynamically finds the most likely sequence of evolutionary summaries in the timeline, called the Viterbi timeline, and reduces the impact of events that irrelevant or repeated to the topic. The assumptions of the coherence and the global view run through our model. We explore adjacent relevance to constrain timeline coherence and make sure the events evolve on the same topic with a global view. Experimental results demonstrate that our framework is feasible to extract summaries for timeline generation, outperforms various competitive baselines, and achieves the state-of-the-art performance as an unsupervised approach. |
| Tasks | Timeline Summarization |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05550v2 |
| https://arxiv.org/pdf/1905.05550v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-dynamic-evolutionary-framework-for-timeline |
| Repo | |
| Framework | |
Disentangling neural mechanisms for perceptual grouping
| Title | Disentangling neural mechanisms for perceptual grouping |
| Authors | Junkyung Kim, Drew Linsley, Kalpit Thakkar, Thomas Serre |
| Abstract | Forming perceptual groups and individuating objects in visual scenes is an essential step towards visual intelligence. This ability is thought to arise in the brain from computations implemented by bottom-up, horizontal, and top-down connections between neurons. However, the relative contributions of these connections to perceptual grouping are poorly understood. We address this question by systematically evaluating neural network architectures featuring combinations of these connections on two synthetic visual tasks, which stress low-level `gestalt’ vs. high-level object cues for perceptual grouping. We show that increasing the difficulty of either task strains learning for networks that rely solely on bottom-up processing. Horizontal connections resolve this limitation on tasks with gestalt cues by supporting incremental spatial propagation of activities, whereas top-down connections rescue learning on tasks featuring object cues by propagating coarse predictions about the position of the target object. Our findings disassociate the computational roles of bottom-up, horizontal and top-down connectivity, and demonstrate how a model featuring all of these interactions can more flexibly learn to form perceptual groups. | |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01558v1 |
| https://arxiv.org/pdf/1906.01558v1.pdf | |
| PWC | https://paperswithcode.com/paper/disentangling-neural-mechanisms-for |
| Repo | |
| Framework | |
Unsupervised Temporal Clustering to Monitor the Performance of Alternative Fueling Infrastructure
| Title | Unsupervised Temporal Clustering to Monitor the Performance of Alternative Fueling Infrastructure |
| Authors | Kalai Ramea |
| Abstract | Zero Emission Vehicles (ZEV) play an important role in the decarbonization of the transportation sector. For a wider adoption of ZEVs, providing a reliable infrastructure is critical. We present a machine learning approach that uses unsupervised temporal clustering algorithm along with survey analysis to determine infrastructure performance and reliability of alternative fuels. We illustrate this approach for the hydrogen fueling stations in California, but this can be generalized for other regions and fuels. |
| Tasks | |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.03077v1 |
| https://arxiv.org/pdf/1906.03077v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-temporal-clustering-to-monitor |
| Repo | |
| Framework | |
Rethinking Generative Mode Coverage: A Pointwise Guaranteed Approach
| Title | Rethinking Generative Mode Coverage: A Pointwise Guaranteed Approach |
| Authors | Peilin Zhong, Yuchen Mo, Chang Xiao, Pengyu Chen, Changxi Zheng |
| Abstract | Many generative models have to combat $\textit{missing modes}$. The conventional wisdom to this end is by reducing through training a statistical distance (such as $f$-divergence) between the generated distribution and provided data distribution. But this is more of a heuristic than a guarantee. The statistical distance measures a $\textit{global}$, but not $\textit{local}$, similarity between two distributions. Even if it is small, it does not imply a plausible mode coverage. Rethinking this problem from a game-theoretic perspective, we show that a complete mode coverage is firmly attainable. If a generative model can approximate a data distribution moderately well under a global statistical distance measure, then we will be able to find a mixture of generators that collectively covers $\textit{every}$ data point and thus $\textit{every}$ mode, with a lower-bounded generation probability. Constructing the generator mixture has a connection to the multiplicative weights update rule, upon which we propose our algorithm. We prove that our algorithm guarantees complete mode coverage. And our experiments on real and synthetic datasets confirm better mode coverage over recent approaches, ones that also use generator mixtures but rely on global statistical distances. |
| Tasks | |
| Published | 2019-02-13 |
| URL | https://arxiv.org/abs/1902.04697v7 |
| https://arxiv.org/pdf/1902.04697v7.pdf | |
| PWC | https://paperswithcode.com/paper/rethinking-generative-coverage-a-pointwise |
| Repo | |
| Framework | |
Re-Identification and Growth Detection of Pulmonary Nodules without Image Registration Using 3D Siamese Neural Networks
| Title | Re-Identification and Growth Detection of Pulmonary Nodules without Image Registration Using 3D Siamese Neural Networks |
| Authors | Xavier Rafael-Palou, Anton Aubanell, Ilaria Bonavita, Mario Ceresa, Gemma Piella, Vicent Ribas, Miguel Ángel González Ballester |
| Abstract | Lung cancer follow-up is a complex, error prone, and time consuming task for clinical radiologists. Several lung CT scan images taken at different time points of a given patient need to be individually inspected, looking for possible cancerogenous nodules. Radiologists mainly focus their attention in nodule size, density, and growth to assess the existence of malignancy. In this study, we present a novel method based on a 3D siamese neural network, for the re-identification of nodules in a pair of CT scans of the same patient without the need for image registration. The network was integrated into a two-stage automatic pipeline to detect, match, and predict nodule growth given pairs of CT scans. Results on an independent test set reported a nodule detection sensitivity of 94.7%, an accuracy for temporal nodule matching of 88.8%, and a sensitivity of 92.0% with a precision of 88.4% for nodule growth detection. |
| Tasks | Image Registration |
| Published | 2019-12-22 |
| URL | https://arxiv.org/abs/1912.10525v1 |
| https://arxiv.org/pdf/1912.10525v1.pdf | |
| PWC | https://paperswithcode.com/paper/re-identification-and-growth-detection-of |
| Repo | |
| Framework | |
Mek: Mechanics Prototyping Tool for 2D Tile-Based Turn-Based Deterministic Games
| Title | Mek: Mechanics Prototyping Tool for 2D Tile-Based Turn-Based Deterministic Games |
| Authors | Rokas Volkovas, Michael Fairbank, John Woodward, Simon Lucas |
| Abstract | There are few digital tools to help designers create game mechanics. A general language to express game mechanics is necessary for rapid game design iteration. The first iteration of a mechanics-focused language, together with its interfacing tool, are introduced in this paper. The language is restricted to two-dimensional, turn-based, tile-based, deterministic, complete-information games. The tool is compared to the existing alternatives for game mechanics prototyping and shown to be capable of succinctly implementing a range of well-known game mechanics. |
| Tasks | |
| Published | 2019-04-06 |
| URL | http://arxiv.org/abs/1904.03540v1 |
| http://arxiv.org/pdf/1904.03540v1.pdf | |
| PWC | https://paperswithcode.com/paper/mek-mechanics-prototyping-tool-for-2d-tile |
| Repo | |
| Framework | |
Non-local Recurrent Neural Memory for Supervised Sequence Modeling
| Title | Non-local Recurrent Neural Memory for Supervised Sequence Modeling |
| Authors | Canmiao Fu, Wenjie Pei, Qiong Cao, Chaopeng Zhang, Yong Zhao, Xiaoyong Shen, Yu-Wing Tai |
| Abstract | Typical methods for supervised sequence modeling are built upon the recurrent neural networks to capture temporal dependencies. One potential limitation of these methods is that they only model explicitly information interactions between adjacent time steps in a sequence, hence the high-order interactions between nonadjacent time steps are not fully exploited. It greatly limits the capability of modeling the long-range temporal dependencies since one-order interactions cannot be maintained for a long term due to information dilution and gradient vanishing. To tackle this limitation, we propose the Non-local Recurrent Neural Memory (NRNM) for supervised sequence modeling, which performs non-local operations to learn full-order interactions within a sliding temporal block and models global interactions between blocks in a gated recurrent manner. Consequently, our model is able to capture the long-range dependencies. Besides, the latent high-level features contained in high-order interactions can be distilled by our model. We demonstrate the merits of our NRNM on two different tasks: action recognition and sentiment analysis. |
| Tasks | Sentiment Analysis |
| Published | 2019-08-26 |
| URL | https://arxiv.org/abs/1908.09535v1 |
| https://arxiv.org/pdf/1908.09535v1.pdf | |
| PWC | https://paperswithcode.com/paper/non-local-recurrent-neural-memory-for |
| Repo | |
| Framework | |
ADMM-SOFTMAX : An ADMM Approach for Multinomial Logistic Regression
| Title | ADMM-SOFTMAX : An ADMM Approach for Multinomial Logistic Regression |
| Authors | Samy Wu Fung, Sanna Tyrväinen, Lars Ruthotto, Eldad Haber |
| Abstract | We present ADMM-Softmax, an alternating direction method of multipliers (ADMM) for solving multinomial logistic regression (MLR) problems. Our method is geared toward supervised classification tasks with many examples and features. It decouples the nonlinear optimization problem in MLR into three steps that can be solved efficiently. In particular, each iteration of ADMM-Softmax consists of a linear least-squares problem, a set of independent small-scale smooth, convex problems, and a trivial dual variable update. Solution of the least-squares problem can be be accelerated by pre-computing a factorization or preconditioner, and the separability in the smooth, convex problem can be easily parallelized across examples. For two image classification problems, we demonstrate that ADMM-Softmax leads to improved generalization compared to a Newton-Krylov, a quasi Newton, and a stochastic gradient descent method. |
| Tasks | Image Classification, Transfer Learning |
| Published | 2019-01-27 |
| URL | https://arxiv.org/abs/1901.09450v2 |
| https://arxiv.org/pdf/1901.09450v2.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-classification-using-multinomial |
| Repo | |
| Framework | |
Grasping Using Tactile Sensing and Deep Calibration
| Title | Grasping Using Tactile Sensing and Deep Calibration |
| Authors | Masoud Baghbahari, Aman Behal |
| Abstract | Tactile perception is an essential ability of intelligent robots in interaction with their surrounding environments. This perception as an intermediate level acts between sensation and action and has to be defined properly to generate suitable action in response to sensed data. In this paper, we propose a feedback approach to address robot grasping task using force-torque tactile sensing. While visual perception is an essential part for gross reaching, constant utilization of this sensing modality can negatively affect the grasping process with overwhelming computation. In such case, human being utilizes tactile sensing to interact with objects. Inspired by, the proposed approach is presented and evaluated on a real robot to demonstrate the effectiveness of the suggested framework. Moreover, we utilize a deep learning framework called Deep Calibration in order to eliminate the effect of bias in the collected data from the robot sensors. |
| Tasks | Calibration |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.09656v1 |
| https://arxiv.org/pdf/1907.09656v1.pdf | |
| PWC | https://paperswithcode.com/paper/grasping-using-tactile-sensing-and-deep |
| Repo | |
| Framework | |
Classification under local differential privacy
| Title | Classification under local differential privacy |
| Authors | Thomas Berrett, Cristina Butucea |
| Abstract | We consider the binary classification problem in a setup that preserves the privacy of the original sample. We provide a privacy mechanism that is locally differentially private and then construct a classifier based on the private sample that is universally consistent in Euclidean spaces. Under stronger assumptions, we establish the minimax rates of convergence of the excess risk and see that they are slower than in the case when the original sample is available. |
| Tasks | |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04629v1 |
| https://arxiv.org/pdf/1912.04629v1.pdf | |
| PWC | https://paperswithcode.com/paper/classification-under-local-differential |
| Repo | |
| Framework | |
REAPS: Towards Better Recognition of Fine-grained Images by Region Attending and Part Sequencing
| Title | REAPS: Towards Better Recognition of Fine-grained Images by Region Attending and Part Sequencing |
| Authors | Peng Zhang, Xinyu Zhu, Zhanzhan Cheng, Shuigeng Zhou, Yi Niu |
| Abstract | Fine-grained image recognition has been a hot research topic in computer vision due to its various applications. The-state-of-the-art is the part/region-based approaches that first localize discriminative parts/regions, and then learn their fine-grained features. However, these approaches have some inherent drawbacks: 1) the discriminative feature representation of an object is prone to be disturbed by complicated background; 2) it is unreasonable and inflexible to fix the number of salient parts, because the intended parts may be unavailable under certain circumstances due to occlusion or incompleteness, and 3) the spatial correlation among different salient parts has not been thoroughly exploited (if not completely neglected). To overcome these drawbacks, in this paper we propose a new, simple yet robust method by building part sequence model on the attended object region. Concretely, we first try to alleviate the background effect by using a region attention mechanism to generate the attended region from the original image. Then, instead of localizing different salient parts and extracting their features separately, we learn the part representation implicitly by applying a mapping function on the serialized features of the object. Finally, we combine the region attending network and the part sequence learning network into a unified framework that can be trained end-to-end with only image-level labels. Our extensive experiments on three fine-grained benchmarks show that the proposed method achieves the state of the art performance. |
| Tasks | Fine-Grained Image Recognition |
| Published | 2019-08-06 |
| URL | https://arxiv.org/abs/1908.01962v1 |
| https://arxiv.org/pdf/1908.01962v1.pdf | |
| PWC | https://paperswithcode.com/paper/reaps-towards-better-recognition-of-fine |
| Repo | |
| Framework | |
Online Control with Adversarial Disturbances
| Title | Online Control with Adversarial Disturbances |
| Authors | Naman Agarwal, Brian Bullins, Elad Hazan, Sham M. Kakade, Karan Singh |
| Abstract | We study the control of a linear dynamical system with adversarial disturbances (as opposed to statistical noise). The objective we consider is one of regret: we desire an online control procedure that can do nearly as well as that of a procedure that has full knowledge of the disturbances in hindsight. Our main result is an efficient algorithm that provides nearly tight regret bounds for this problem. From a technical standpoint, this work generalizes upon previous work in two main aspects: our model allows for adversarial noise in the dynamics, and allows for general convex costs. |
| Tasks | |
| Published | 2019-02-23 |
| URL | http://arxiv.org/abs/1902.08721v1 |
| http://arxiv.org/pdf/1902.08721v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-control-with-adversarial-disturbances |
| Repo | |
| Framework | |
