Paper Group ANR 1120
A Single Video Super-Resolution GAN for Multiple Downsampling Operators based on Pseudo-Inverse Image Formation Models. Application of Different Simulated Spectral Data and Machine Learning to Estimate the Chlorophyll a Concentration of Several Inland Waters. Food for thought: Ethical considerations of user trust in computer vision. Learning from M …
A Single Video Super-Resolution GAN for Multiple Downsampling Operators based on Pseudo-Inverse Image Formation Models
| Title | A Single Video Super-Resolution GAN for Multiple Downsampling Operators based on Pseudo-Inverse Image Formation Models |
| Authors | Santiago López-Tapia, Alice Lucas, Rafael Molina, Aggelos K. Katsaggelos |
| Abstract | The popularity of high and ultra-high definition displays has led to the need for methods to improve the quality of videos already obtained at much lower resolutions. Current Video Super-Resolution methods are not robust to mismatch between training and testing degradation models since they are trained against a single degradation model (usually bicubic downsampling). This causes their performance to deteriorate in real-life applications. At the same time, the use of only the Mean Squared Error during learning causes the resulting images to be too smooth. In this work we propose a new Convolutional Neural Network for video super resolution which is robust to multiple degradation models. During training, which is performed on a large dataset of scenes with slow and fast motions, it uses the pseudo-inverse image formation model as part of the network architecture in conjunction with perceptual losses, in addition to a smoothness constraint that eliminates the artifacts originating from these perceptual losses. The experimental validation shows that our approach outperforms current state-of-the-art methods and is robust to multiple degradations. |
| Tasks | Super-Resolution, Video Super-Resolution |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01399v1 |
| https://arxiv.org/pdf/1907.01399v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-single-video-super-resolution-gan-for |
| Repo | |
| Framework | |
Application of Different Simulated Spectral Data and Machine Learning to Estimate the Chlorophyll a Concentration of Several Inland Waters
| Title | Application of Different Simulated Spectral Data and Machine Learning to Estimate the Chlorophyll a Concentration of Several Inland Waters |
| Authors | Philipp M. Maier, Sina Keller |
| Abstract | Water quality is of great importance for humans and for the environment and has to be monitored continuously. It is determinable through proxies such as the chlorophyll a concentration, which can be monitored by remote sensing techniques. This study focuses on the trade-off between the spatial and the spectral resolution of six simulated satellite-based data sets when estimating the chlorophyll a concentration with supervised machine learning models. The initial dataset for the spectral simulation of the satellite missions contains spectrometer data and measured chlorophyll a concentration of 13 different inland waters. Focusing on the regression performance, it appears that the machine learning models achieve almost as good results with the simulated Sentinel data as with the simulated hyperspectral data. Regarding the applicability, the Sentinel 2 mission is the best choice for small inland waters due to its high spatial and temporal resolution in combination with a suitable spectral resolution. |
| Tasks | |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12563v2 |
| https://arxiv.org/pdf/1905.12563v2.pdf | |
| PWC | https://paperswithcode.com/paper/application-of-different-simulated-spectral |
| Repo | |
| Framework | |
Food for thought: Ethical considerations of user trust in computer vision
| Title | Food for thought: Ethical considerations of user trust in computer vision |
| Authors | Kaylen J. Pfisterer, Jennifer Boger, Alexander Wong |
| Abstract | In computer vision research, especially when novel applications of tools are developed, ethical implications around user perceptions of trust in the underlying technology should be considered and supported. Here, we describe an example of the incorporation of such considerations within the long-term care sector for tracking resident food and fluid intake. We highlight our recent user study conducted to develop a Goldilocks quality horizontal prototype designed to support trust cues in which perceived trust in our horizontal prototype was higher than the existing system in place. We discuss the importance and need for user engagement as part of ongoing computer vision-driven technology development and describe several important factors related to trust that are relevant to developing decision-making tools. |
| Tasks | Decision Making |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12487v1 |
| https://arxiv.org/pdf/1905.12487v1.pdf | |
| PWC | https://paperswithcode.com/paper/food-for-thought-ethical-considerations-of |
| Repo | |
| Framework | |
Learning from My Partner’s Actions: Roles in Decentralized Robot Teams
| Title | Learning from My Partner’s Actions: Roles in Decentralized Robot Teams |
| Authors | Dylan P. Losey, Mengxi Li, Jeannette Bohg, Dorsa Sadigh |
| Abstract | When teams of robots collaborate to complete a task, communication is often necessary. Like humans, robot teammates should implicitly communicate through their actions: but interpreting our partner’s actions is typically difficult, since a given action may have many different underlying reasons. Here we propose an alternate approach: instead of not being able to infer whether an action is due to exploration, exploitation, or communication, we define separate roles for each agent. Because each role defines a distinct reason for acting (e.g., only exploit, only communicate), teammates now correctly interpret the meaning behind their partner’s actions. Our results suggest that leveraging and alternating roles leads to performance comparable to teams that explicitly exchange messages. You can find more images and videos of our experimental setups at http://ai.stanford.edu/blog/learning-from-partners/. |
| Tasks | |
| Published | 2019-10-16 |
| URL | https://arxiv.org/abs/1910.07613v2 |
| https://arxiv.org/pdf/1910.07613v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-my-partners-actions-roles-in |
| Repo | |
| Framework | |
A Multivariate Extreme Value Theory Approach to Anomaly Clustering and Visualization
| Title | A Multivariate Extreme Value Theory Approach to Anomaly Clustering and Visualization |
| Authors | Maël Chiapino, Stéphan Clémençon, Vincent Feuillard, Anne Sabourin |
| Abstract | In a wide variety of situations, anomalies in the behaviour of a complex system, whose health is monitored through the observation of a random vector X = (X1,. .. , X d) valued in R d , correspond to the simultaneous occurrence of extreme values for certain subgroups $\alpha$ $\subset$ {1,. .. , d} of variables Xj. Under the heavy-tail assumption, which is precisely appropriate for modeling these phenomena, statistical methods relying on multivariate extreme value theory have been developed in the past few years for identifying such events/subgroups. This paper exploits this approach much further by means of a novel mixture model that permits to describe the distribution of extremal observations and where the anomaly type $\alpha$ is viewed as a latent variable. One may then take advantage of the model by assigning to any extreme point a posterior probability for each anomaly type $\alpha$, defining implicitly a similarity measure between anomalies. It is explained at length how the latter permits to cluster extreme observations and obtain an informative planar representation of anomalies using standard graph-mining tools. The relevance and usefulness of the clustering and 2-d visual display thus designed is illustrated on simulated datasets and on real observations as well, in the aeronautics application domain. |
| Tasks | |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.07523v1 |
| https://arxiv.org/pdf/1907.07523v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-multivariate-extreme-value-theory-approach |
| Repo | |
| Framework | |
Productization Challenges of Contextual Multi-Armed Bandits
| Title | Productization Challenges of Contextual Multi-Armed Bandits |
| Authors | David Abensur, Ivan Balashov, Shaked Bar, Ronny Lempel, Nurit Moscovici, Ilan Orlov, Danny Rosenstein, Ido Tamir |
| Abstract | Contextual Multi-Armed Bandits is a well-known and accepted online optimization algorithm, that is used in many Web experiences to tailor content or presentation to users’ traffic. Much has been published on theoretical guarantees (e.g. regret bounds) of proposed algorithmic variants, but relatively little attention has been devoted to the challenges encountered while productizing contextual bandits schemes in large scale settings. This work enumerates several productization challenges we encountered while leveraging contextual bandits for two concrete use cases at scale. We discuss how to (1) determine the context (engineer the features) that model the bandit arms; (2) sanity check the health of the optimization process; (3) evaluate the process in an offline manner; (4) add potential actions (arms) on the fly to a running process; (5) subject the decision process to constraints; and (6) iteratively improve the online learning algorithm. For each such challenge, we explain the issue, provide our approach, and relate to prior art where applicable. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04884v1 |
| https://arxiv.org/pdf/1907.04884v1.pdf | |
| PWC | https://paperswithcode.com/paper/productization-challenges-of-contextual-multi |
| Repo | |
| Framework | |
Learning in Restless Multi-Armed Bandits via Adaptive Arm Sequencing Rules
| Title | Learning in Restless Multi-Armed Bandits via Adaptive Arm Sequencing Rules |
| Authors | Tomer Gafni, Kobi Cohen |
| Abstract | We consider a class of restless multi-armed bandit (RMAB) problems with unknown arm dynamics. At each time, a player chooses an arm out of N arms to play, referred to as an active arm, and receives a random reward from a finite set of reward states. The reward state of the active arm transits according to an unknown Markovian dynamics. The reward state of passive arms (which are not chosen to play at time t) evolves according to an arbitrary unknown random process. The objective is an arm-selection policy that minimizes the regret, defined as the reward loss with respect to a player that always plays the most rewarding arm. This class of RMAB problems has been studied recently in the context of communication networks and financial investment applications. We develop a strategy that selects arms to be played in a consecutive manner, dubbed Adaptive Sequencing Rules (ASR) algorithm. The sequencing rules for selecting arms under the ASR algorithm are adaptively updated and controlled by the current sample reward means. By designing judiciously the adaptive sequencing rules, we show that the ASR algorithm achieves a logarithmic regret order with time, and a finite-sample bound on the regret is established. Although existing methods have shown a logarithmic regret order with time in this RMAB setting, the theoretical analysis shows a significant improvement in the regret scaling with respect to the system parameters under ASR. Extensive simulation results support the theoretical study and demonstrate strong performance of the algorithm as compared to existing methods. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.08120v1 |
| https://arxiv.org/pdf/1906.08120v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-in-restless-multi-armed-bandits-via |
| Repo | |
| Framework | |
Stochastic quasi-Newton with line-search regularization
| Title | Stochastic quasi-Newton with line-search regularization |
| Authors | Adrian Wills, Thomas Schön |
| Abstract | In this paper we present a novel quasi-Newton algorithm for use in stochastic optimisation. Quasi-Newton methods have had an enormous impact on deterministic optimisation problems because they afford rapid convergence and computationally attractive algorithms. In essence, this is achieved by learning the second-order (Hessian) information based on observing first-order gradients. We extend these ideas to the stochastic setting by employing a highly flexible model for the Hessian and infer its value based on observing noisy gradients. In addition, we propose a stochastic counterpart to standard line-search procedures and demonstrate the utility of this combination on maximum likelihood identification for general nonlinear state space models. |
| Tasks | |
| Published | 2019-09-03 |
| URL | https://arxiv.org/abs/1909.01238v1 |
| https://arxiv.org/pdf/1909.01238v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-quasi-newton-with-line-search |
| Repo | |
| Framework | |
One Man’s Trash is Another Man’s Treasure: Resisting Adversarial Examples by Adversarial Examples
| Title | One Man’s Trash is Another Man’s Treasure: Resisting Adversarial Examples by Adversarial Examples |
| Authors | Chang Xiao, Changxi Zheng |
| Abstract | Modern image classification systems are often built on deep neural networks, which suffer from adversarial examples–images with deliberately crafted, imperceptible noise to mislead the network’s classification. To defend against adversarial examples, a plausible idea is to obfuscate the network’s gradient with respect to the input image. This general idea has inspired a long line of defense methods. Yet, almost all of them have proven vulnerable. We revisit this seemingly flawed idea from a radically different perspective. We embrace the omnipresence of adversarial examples and the numerical procedure of crafting them, and turn this harmful attacking process into a useful defense mechanism. Our defense method is conceptually simple: before feeding an input image for classification, transform it by finding an adversarial example on a pre-trained external model. We evaluate our method against a wide range of possible attacks. On both CIFAR-10 and Tiny ImageNet datasets, our method is significantly more robust than state-of-the-art methods. Particularly, in comparison to adversarial training, our method offers lower training cost as well as stronger robustness. |
| Tasks | Image Classification |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.11219v2 |
| https://arxiv.org/pdf/1911.11219v2.pdf | |
| PWC | https://paperswithcode.com/paper/one-mans-trash-is-another-mans-treasure |
| Repo | |
| Framework | |
Converting a Common Document Scanner to a Multispectral Scanner
| Title | Converting a Common Document Scanner to a Multispectral Scanner |
| Authors | Zohaib Khan, Faisal Shafait, Ajmal Mian |
| Abstract | We propose the construction of a prototype scanner designed to capture multispectral images of documents. A standard sheet-feed scanner is modified by disconnecting its internal light source and connecting an external multispectral light source comprising of narrow band light emitting diodes (LED). A document is scanned by illuminating the scanner light guide successively with different LEDs and capturing a scan of the document. The system is portable and can be used for potential applications in verification of questioned documents, cheques, receipts and bank notes. |
| Tasks | |
| Published | 2019-04-17 |
| URL | http://arxiv.org/abs/1904.12603v1 |
| http://arxiv.org/pdf/1904.12603v1.pdf | |
| PWC | https://paperswithcode.com/paper/190412603 |
| Repo | |
| Framework | |
Safe Trajectory Generation for Complex Urban Environments Using Spatio-temporal Semantic Corridor
| Title | Safe Trajectory Generation for Complex Urban Environments Using Spatio-temporal Semantic Corridor |
| Authors | Wenchao Ding, Lu Zhang, Jing Chen, Shaojie Shen |
| Abstract | Planning safe trajectories for autonomous vehicles in complex urban environments is challenging since there are numerous semantic elements (such as dynamic agents, traffic lights and speed limits) to consider. These semantic elements may have different mathematical descriptions such as obstacle, constraint and cost. It is non-trivial to tune the effects from different combinations of semantic elements for a stable and generalizable behavior. In this paper, we propose a novel unified spatio-temporal semantic corridor (SSC) structure, which provides a level of abstraction for different types of semantic elements. The SSC consists of a series of mutually connected collision-free cubes with dynamical constraints posed by the semantic elements in the spatio-temporal domain. The trajectory generation problem then boils down to a general quadratic programming (QP) formulation. Thanks to the unified SSC representation, our framework can generalize to any combination of semantic elements. Moreover, our formulation provides a theoretical guarantee that the entire trajectory is safe and constraint-satisfied, by using the convex hull and hodograph properties of piecewise Bezier curve parameterization. We also release the code of our method to accommodate benchmarking. |
| Tasks | Autonomous Vehicles |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.09788v1 |
| https://arxiv.org/pdf/1906.09788v1.pdf | |
| PWC | https://paperswithcode.com/paper/safe-trajectory-generation-for-complex-urban |
| Repo | |
| Framework | |
MatchZoo: A Learning, Practicing, and Developing System for Neural Text Matching
| Title | MatchZoo: A Learning, Practicing, and Developing System for Neural Text Matching |
| Authors | Jiafeng Guo, Yixing Fan, Xiang Ji, Xueqi Cheng |
| Abstract | Text matching is the core problem in many natural language processing (NLP) tasks, such as information retrieval, question answering, and conversation. Recently, deep leaning technology has been widely adopted for text matching, making neural text matching a new and active research domain. With a large number of neural matching models emerging rapidly, it becomes more and more difficult for researchers, especially those newcomers, to learn and understand these new models. Moreover, it is usually difficult to try these models due to the tedious data pre-processing, complicated parameter configuration, and massive optimization tricks, not to mention the unavailability of public codes sometimes. Finally, for researchers who want to develop new models, it is also not an easy task to implement a neural text matching model from scratch, and to compare with a bunch of existing models. In this paper, therefore, we present a novel system, namely MatchZoo, to facilitate the learning, practicing and designing of neural text matching models. The system consists of a powerful matching library and a user-friendly and interactive studio, which can help researchers: 1) to learn state-of-the-art neural text matching models systematically, 2) to train, test and apply these models with simple configurable steps; and 3) to develop their own models with rich APIs and assistance. |
| Tasks | Information Retrieval, Question Answering, Text Matching |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10289v2 |
| https://arxiv.org/pdf/1905.10289v2.pdf | |
| PWC | https://paperswithcode.com/paper/matchzoo-a-learning-practicing-and-developing |
| Repo | |
| Framework | |
Probabilistic Bias Mitigation in Word Embeddings
| Title | Probabilistic Bias Mitigation in Word Embeddings |
| Authors | Hailey James-Sorenson, David Alvarez-Melis |
| Abstract | It has been shown that word embeddings derived from large corpora tend to incorporate biases present in their training data. Various methods for mitigating these biases have been proposed, but recent work has demonstrated that these methods hide but fail to truly remove the biases, which can still be observed in word nearest-neighbor statistics. In this work we propose a probabilistic view of word embedding bias. We leverage this framework to present a novel method for mitigating bias which relies on probabilistic observations to yield a more robust bias mitigation algorithm. We demonstrate that this method effectively reduces bias according to three separate measures of bias while maintaining embedding quality across various popular benchmark semantic tasks |
| Tasks | Word Embeddings |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1910.14497v1 |
| https://arxiv.org/pdf/1910.14497v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-bias-mitigation-in-word |
| Repo | |
| Framework | |
IF-TTN: Information Fused Temporal Transformation Network for Video Action Recognition
| Title | IF-TTN: Information Fused Temporal Transformation Network for Video Action Recognition |
| Authors | Ke Yang, Peng Qiao, Dongsheng Li, Yong Dou |
| Abstract | Effective spatiotemporal feature representation is crucial to the video-based action recognition task. Focusing on discriminate spatiotemporal feature learning, we propose Information Fused Temporal Transformation Network (IF-TTN) for action recognition on top of popular Temporal Segment Network (TSN) framework. In the network, Information Fusion Module (IFM) is designed to fuse the appearance and motion features at multiple ConvNet levels for each video snippet, forming a short-term video descriptor. With fused features as inputs, Temporal Transformation Networks (TTN) are employed to model middle-term temporal transformation between the neighboring snippets following a sequential order. As TSN itself depicts long-term temporal structure by segmental consensus, the proposed network comprehensively considers multiple granularity temporal features. Our IF-TTN achieves the state-of-the-art results on two most popular action recognition datasets: UCF101 and HMDB51. Empirical investigation reveals that our architecture is robust to the input motion map quality. Replacing optical flow with the motion vectors from compressed video stream, the performance is still comparable to the flow-based methods while the testing speed is 10x faster. |
| Tasks | Optical Flow Estimation, Temporal Action Localization |
| Published | 2019-02-26 |
| URL | http://arxiv.org/abs/1902.09928v2 |
| http://arxiv.org/pdf/1902.09928v2.pdf | |
| PWC | https://paperswithcode.com/paper/if-ttn-information-fused-temporal |
| Repo | |
| Framework | |
A Comprehensive Study on Pedestrians’ Evacuation
| Title | A Comprehensive Study on Pedestrians’ Evacuation |
| Authors | Danial A. Muhammed, Soran Saeed, Tarik A. Rashid |
| Abstract | Human beings face threats because of unexpected happenings, which can be avoided through an adequate crisis evacuation plan, which is vital to stop wound and demise as its negative results. Consequently, different typical evacuation pedestrians have been created. Moreover, through applied research, these models for various applications, reproductions, and conditions have been examined to present an operational model. Furthermore, new models have been developed to cooperate with system evacuation in residential places in case of unexpected events. This research has taken into account an inclusive and a ‘systematic survey of pedestrian evacuation’ to demonstrate models methods by focusing on the applications’ features, techniques, implications, and after that gather them under various types, for example, classical models, hybridized models, and generic model. The current analysis assists scholars in this field of study to write their forthcoming papers about it, which can suggest a novel structure to recent typical intelligent reproduction with novel features. |
| Tasks | |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01165v1 |
| https://arxiv.org/pdf/1911.01165v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comprehensive-study-on-pedestrians |
| Repo | |
| Framework | |
