Paper Group ANR 358
Improving Multiple Object Tracking with Optical Flow and Edge Preprocessing. Semantic Segmentation Refinement by Monte Carlo Region Growing of High Confidence Detections. Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection. When Conventional machine learning meets neuromorphic engineering: Deep Temporal Network …
Improving Multiple Object Tracking with Optical Flow and Edge Preprocessing
| Title | Improving Multiple Object Tracking with Optical Flow and Edge Preprocessing |
| Authors | David-Alexandre Beaupré, Guillaume-Alexandre Bilodeau, Nicolas Saunier |
| Abstract | In this paper, we present a new method for detecting road users in an urban environment which leads to an improvement in multiple object tracking. Our method takes as an input a foreground image and improves the object detection and segmentation. This new image can be used as an input to trackers that use foreground blobs from background subtraction. The first step is to create foreground images for all the frames in an urban video. Then, starting from the original blobs of the foreground image, we merge the blobs that are close to one another and that have similar optical flow. The next step is extracting the edges of the different objects to detect multiple objects that might be very close (and be merged in the same blob) and to adjust the size of the original blobs. At the same time, we use the optical flow to detect occlusion of objects that are moving in opposite directions. Finally, we make a decision on which information we keep in order to construct a new foreground image with blobs that can be used for tracking. The system is validated on four videos of an urban traffic dataset. Our method improves the recall and precision metrics for the object detection task compared to the vanilla background subtraction method and improves the CLEAR MOT metrics in the tracking tasks for most videos. |
| Tasks | Multiple Object Tracking, Object Detection, Object Tracking, Optical Flow Estimation |
| Published | 2018-01-29 |
| URL | http://arxiv.org/abs/1801.09646v1 |
| http://arxiv.org/pdf/1801.09646v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-multiple-object-tracking-with |
| Repo | |
| Framework | |
Semantic Segmentation Refinement by Monte Carlo Region Growing of High Confidence Detections
| Title | Semantic Segmentation Refinement by Monte Carlo Region Growing of High Confidence Detections |
| Authors | Philipe A. Dias, Henry Medeiros |
| Abstract | Despite recent improvements using fully convolutional networks, in general, the segmentation produced by most state-of-the-art semantic segmentation methods does not show satisfactory adherence to the object boundaries. We propose a method to refine the segmentation results generated by such deep learning models. Our method takes as input the confidence scores generated by a pixel-dense segmentation network and re-labels pixels with low confidence levels. The re-labeling approach employs a region growing mechanism that aggregates these pixels to neighboring areas with high confidence scores and similar appearance. In order to correct the labels of pixels that were incorrectly classified with high confidence level by the semantic segmentation algorithm, we generate multiple region growing steps through a Monte Carlo sampling of the seeds of the regions. Our method improves the accuracy of a state-of-the-art fully convolutional semantic segmentation approach on the publicly available COCO and PASCAL datasets, and it shows significantly better results on selected sequences of the finely-annotated DAVIS dataset. |
| Tasks | Semantic Segmentation |
| Published | 2018-02-21 |
| URL | http://arxiv.org/abs/1802.07789v1 |
| http://arxiv.org/pdf/1802.07789v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-segmentation-refinement-by-monte |
| Repo | |
| Framework | |
Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection
| Title | Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection |
| Authors | Wei Wang, Taro Watanabe, Macduff Hughes, Tetsuji Nakagawa, Ciprian Chelba |
| Abstract | Measuring domain relevance of data and identifying or selecting well-fit domain data for machine translation (MT) is a well-studied topic, but denoising is not yet. Denoising is concerned with a different type of data quality and tries to reduce the negative impact of data noise on MT training, in particular, neural MT (NMT) training. This paper generalizes methods for measuring and selecting data for domain MT and applies them to denoising NMT training. The proposed approach uses trusted data and a denoising curriculum realized by online data selection. Intrinsic and extrinsic evaluations of the approach show its significant effectiveness for NMT to train on data with severe noise. |
| Tasks | Denoising, Machine Translation |
| Published | 2018-08-31 |
| URL | http://arxiv.org/abs/1809.00068v1 |
| http://arxiv.org/pdf/1809.00068v1.pdf | |
| PWC | https://paperswithcode.com/paper/denoising-neural-machine-translation-training |
| Repo | |
| Framework | |
When Conventional machine learning meets neuromorphic engineering: Deep Temporal Networks (DTNets) a machine learning frawmework allowing to operate on Events and Frames and implantable on Tensor Flow Like Hardware
| Title | When Conventional machine learning meets neuromorphic engineering: Deep Temporal Networks (DTNets) a machine learning frawmework allowing to operate on Events and Frames and implantable on Tensor Flow Like Hardware |
| Authors | Marco Macanovic, Fabian Chersi, Felix Rutard, Sio-Hoi Ieng, Ryad Benosman |
| Abstract | We introduce in this paper the principle of Deep Temporal Networks that allow to add time to convolutional networks by allowing deep integration principles not only using spatial information but also increasingly large temporal window. The concept can be used for conventional image inputs but also event based data. Although inspired by the architecture of brain that inegrates information over increasingly larger spatial but also temporal scales it can operate on conventional hardware using existing architectures. We introduce preliminary results to show the efficiency of the method. More in-depth results and analysis will be reported soon! |
| Tasks | |
| Published | 2018-11-19 |
| URL | http://arxiv.org/abs/1811.07672v1 |
| http://arxiv.org/pdf/1811.07672v1.pdf | |
| PWC | https://paperswithcode.com/paper/when-conventional-machine-learning-meets |
| Repo | |
| Framework | |
Convolutional Neural Networks In Classifying Cancer Through DNA Methylation
| Title | Convolutional Neural Networks In Classifying Cancer Through DNA Methylation |
| Authors | Soham Chatterjee, Archana Iyer, Satya Avva, Abhai Kollara, Malaikannan Sankarasubbu |
| Abstract | DNA Methylation has been the most extensively studied epigenetic mark. Usually a change in the genotype, DNA sequence, leads to a change in the phenotype, observable characteristics of the individual. But DNA methylation, which happens in the context of CpG (cytosine and guanine bases linked by phosphate backbone) dinucleotides, does not lead to a change in the original DNA sequence but has the potential to change the phenotype. DNA methylation is implicated in various biological processes and diseases including cancer. Hence there is a strong interest in understanding the DNA methylation patterns across various epigenetic related ailments in order to distinguish and diagnose the type of disease in its early stages. In this work, the relationship between methylated versus unmethylated CpG regions and cancer types is explored using Convolutional Neural Networks (CNNs). A CNN based Deep Learning model that can classify the cancer of a new DNA methylation profile based on the learning from publicly available DNA methylation datasets is then proposed. |
| Tasks | |
| Published | 2018-07-24 |
| URL | http://arxiv.org/abs/1807.09617v1 |
| http://arxiv.org/pdf/1807.09617v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-networks-in-classifying |
| Repo | |
| Framework | |
Toward Formalizing Teleportation of Pedagogical Artificial Agents
| Title | Toward Formalizing Teleportation of Pedagogical Artificial Agents |
| Authors | John Angel, Naveen Sundar Govindarajulu, Selmer Bringsjord |
| Abstract | Our paradigm for the use of artificial agents to teach requires among other things that they persist through time in their interaction with human students, in such a way that they “teleport” or “migrate” from an embodiment at one time t to a different embodiment at later time t’. In this short paper, we report on initial steps toward the formalization of such teleportation, in order to enable an overseeing AI system to establish, mechanically, and verifiably, that the human students in question will likely believe that the very same artificial agent has persisted across such times despite the different embodiments. |
| Tasks | |
| Published | 2018-04-10 |
| URL | http://arxiv.org/abs/1804.03342v1 |
| http://arxiv.org/pdf/1804.03342v1.pdf | |
| PWC | https://paperswithcode.com/paper/toward-formalizing-teleportation-of |
| Repo | |
| Framework | |
Quality expectations of machine translation
| Title | Quality expectations of machine translation |
| Authors | Andy Way |
| Abstract | Machine Translation (MT) is being deployed for a range of use-cases by millions of people on a daily basis. There should, therefore, be no doubt as to the utility of MT. However, not everyone is convinced that MT can be useful, especially as a productivity enhancer for human translators. In this chapter, I address this issue, describing how MT is currently deployed, how its output is evaluated and how this could be enhanced, especially as MT quality itself improves. Central to these issues is the acceptance that there is no longer a single ‘gold standard’ measure of quality, such that the situation in which MT is deployed needs to be borne in mind, especially with respect to the expected ‘shelf-life’ of the translation itself. |
| Tasks | Machine Translation |
| Published | 2018-03-22 |
| URL | http://arxiv.org/abs/1803.08409v1 |
| http://arxiv.org/pdf/1803.08409v1.pdf | |
| PWC | https://paperswithcode.com/paper/quality-expectations-of-machine-translation |
| Repo | |
| Framework | |
Risk-Averse Classification
| Title | Risk-Averse Classification |
| Authors | Constantine Vitt, Darinka Dentcheva, Hui Xiong |
| Abstract | We develop a new approach to solving classification problems, which is bases on the theory of coherent measures of risk and risk sharing ideas. The proposed approach aims at designing a risk-averse classifier. The new approach allows for associating distinct risk functional to each classes. The risk may be measured by different (non-linear in probability) measures, We analyze the structure of the new classifier design problem and establish its theoretical relation to known risk-neutral design problems. In particular, we show that the risk-sharing classification problem is equivalent to an implicitly defined optimization problem with unequal, implicitly defined but unknown, weights for each data point. We implement our methodology in a binary classification scenario on several different data sets and carry out numerical comparison with classifiers which are obtained using the Huber loss function and other loss functions known in the literature. We formulate specific risk-averse support vector machines in order to demonstrate the viability of our method. |
| Tasks | |
| Published | 2018-04-30 |
| URL | http://arxiv.org/abs/1805.00119v2 |
| http://arxiv.org/pdf/1805.00119v2.pdf | |
| PWC | https://paperswithcode.com/paper/risk-averse-classification |
| Repo | |
| Framework | |
Multivariate Spatiotemporal Hawkes Processes and Network Reconstruction
| Title | Multivariate Spatiotemporal Hawkes Processes and Network Reconstruction |
| Authors | Baichuan Yuan, Hao Li, Andrea L. Bertozzi, P. Jeffrey Brantingham, Mason A. Porter |
| Abstract | There is often latent network structure in spatial and temporal data and the tools of network analysis can yield fascinating insights into such data. In this paper, we develop a nonparametric method for network reconstruction from spatiotemporal data sets using multivariate Hawkes processes. In contrast to prior work on network reconstruction with point-process models, which has often focused on exclusively temporal information, our approach uses both temporal and spatial information and does not assume a specific parametric form of network dynamics. This leads to an effective way of recovering an underlying network. We illustrate our approach using both synthetic networks and networks constructed from real-world data sets (a location-based social media network, a narrative of crime events, and violent gang crimes). Our results demonstrate that, in comparison to using only temporal data, our spatiotemporal approach yields improved network reconstruction, providing a basis for meaningful subsequent analysis — such as community structure and motif analysis — of the reconstructed networks. |
| Tasks | |
| Published | 2018-11-15 |
| URL | http://arxiv.org/abs/1811.06321v1 |
| http://arxiv.org/pdf/1811.06321v1.pdf | |
| PWC | https://paperswithcode.com/paper/multivariate-spatiotemporal-hawkes-processes |
| Repo | |
| Framework | |
Network Transplanting
| Title | Network Transplanting |
| Authors | Quanshi Zhang, Yu Yang, Qian Yu, Ying Nian Wu |
| Abstract | This paper focuses on a new task, i.e., transplanting a category-and-task-specific neural network to a generic, modular network without strong supervision. We design an functionally interpretable structure for the generic network. Like building LEGO blocks, we teach the generic network a new category by directly transplanting the module corresponding to the category from a pre-trained network with a few or even without sample annotations. Our method incrementally adds new categories to the generic network but does not affect representations of existing categories. In this way, our method breaks the typical bottleneck of learning a net for massive tasks and categories, i.e. the requirement of collecting samples for all tasks and categories at the same time before the learning begins. Thus, we use a new distillation algorithm, namely back-distillation, to overcome specific challenges of network transplanting. Our method without training samples even outperformed the baseline with 100 training samples. |
| Tasks | |
| Published | 2018-04-26 |
| URL | http://arxiv.org/abs/1804.10272v2 |
| http://arxiv.org/pdf/1804.10272v2.pdf | |
| PWC | https://paperswithcode.com/paper/network-transplanting |
| Repo | |
| Framework | |
USAR: an Interactive User-specific Aesthetic Ranking Framework for Images
| Title | USAR: an Interactive User-specific Aesthetic Ranking Framework for Images |
| Authors | Pei Lv, Meng Wang, Yongbo Xu, Ze Peng, Junyi Sun, Shimei Su, Bing Zhou, Mingliang Xu |
| Abstract | When assessing whether an image is of high or low quality, it is indispensable to take personal preference into account. Existing aesthetic models lay emphasis on hand-crafted features or deep features commonly shared by high quality images, but with limited or no consideration for personal preference and user interaction. To that end, we propose a novel and user-friendly aesthetic ranking framework via powerful deep neural network and a small amount of user interaction, which can automatically estimate and rank the aesthetic characteristics of images in accordance with users’ preference. Our framework takes as input a series of photos that users prefer, and produces as output a reliable, user-specific aesthetic ranking model matching with users’ preference. Considering the subjectivity of personal preference and the uncertainty of user’s single selection, a unique and exclusive dataset will be constructed interactively to describe the preference of one individual by retrieving the most similar images with regard to those specified by users. Based on this unique user-specific dataset and sufficient well-designed aesthetic attributes, a customized aesthetic distribution model can be learned, which concatenates both personalized preference and aesthetic rules. We conduct extensive experiments and user studies on two large-scale public datasets, and demonstrate that our framework outperforms those work based on conventional aesthetic assessment or ranking model. |
| Tasks | |
| Published | 2018-05-03 |
| URL | http://arxiv.org/abs/1805.01091v2 |
| http://arxiv.org/pdf/1805.01091v2.pdf | |
| PWC | https://paperswithcode.com/paper/usar-an-interactive-user-specific-aesthetic |
| Repo | |
| Framework | |
Evolving Agents for the Hanabi 2018 CIG Competition
| Title | Evolving Agents for the Hanabi 2018 CIG Competition |
| Authors | Rodrigo Canaan, Haotian Shen, Ruben Rodriguez Torrado, Julian Togelius, Andy Nealen, Stefan Menzel |
| Abstract | Hanabi is a cooperative card game with hidden information that has won important awards in the industry and received some recent academic attention. A two-track competition of agents for the game will take place in the 2018 CIG conference. In this paper, we develop a genetic algorithm that builds rule-based agents by determining the best sequence of rules from a fixed rule set to use as strategy. In three separate experiments, we remove human assumptions regarding the ordering of rules, add new, more expressive rules to the rule set and independently evolve agents specialized at specific game sizes. As result, we achieve scores superior to previously published research for the mirror and mixed evaluation of agents. |
| Tasks | |
| Published | 2018-09-26 |
| URL | http://arxiv.org/abs/1809.09764v1 |
| http://arxiv.org/pdf/1809.09764v1.pdf | |
| PWC | https://paperswithcode.com/paper/evolving-agents-for-the-hanabi-2018-cig |
| Repo | |
| Framework | |
Pathology Segmentation using Distributional Differences to Images of Healthy Origin
| Title | Pathology Segmentation using Distributional Differences to Images of Healthy Origin |
| Authors | Simon Andermatt, Antal Horváth, Simon Pezold, Philippe Cattin |
| Abstract | Fully supervised segmentation methods require a large training cohort of already segmented images, providing information at the pixel level of each image. We present a method to automatically segment and model pathologies in medical images, trained solely on data labelled on the image level as either healthy or containing a visual defect. We base our method on CycleGAN, an image-to-image translation technique, to translate images between the domains of healthy and pathological images. We extend the core idea with two key contributions. Implementing the generators as residual generators allows us to explicitly model the segmentation of the pathology. Realizing the translation from the healthy to the pathological domain using a variational autoencoder allows us to specify one representation of the pathology, as this transformation is otherwise not unique. Our model hence not only allows us to create pixelwise semantic segmentations, it is also able to create inpaintings for the segmentations to render the pathological image healthy. Furthermore, we can draw new unseen pathology samples from this model based on the distribution in the data. We show quantitatively, that our method is able to segment pathologies with a surprising accuracy being only slightly inferior to a state-of-the-art fully supervised method, although the latter has per-pixel rather than per-image training information. Moreover, we show qualitative results of both the segmentations and inpaintings. Our findings motivate further research into weakly-supervised segmentation using image level annotations, allowing for faster and cheaper acquisition of training data without a large sacrifice in segmentation accuracy. |
| Tasks | Image-to-Image Translation |
| Published | 2018-05-25 |
| URL | https://arxiv.org/abs/1805.10344v2 |
| https://arxiv.org/pdf/1805.10344v2.pdf | |
| PWC | https://paperswithcode.com/paper/pathology-segmentation-using-distributional |
| Repo | |
| Framework | |
Toward a language-theoretic foundation for planning and filtering
| Title | Toward a language-theoretic foundation for planning and filtering |
| Authors | Fatemeh Zahra Saberifar, Shervin Ghasemlou, Dylan A. Shell, Jason M. O’Kane |
| Abstract | We address problems underlying the algorithmic question of automating the co-design of robot hardware in tandem with its apposite software. Specifically, we consider the impact that degradations of a robot’s sensor and actuation suites may have on the ability of that robot to complete its tasks. We introduce a new formal structure that generalizes and consolidates a variety of well-known structures including many forms of plans, planning problems, and filters, into a single data structure called a procrustean graph, and give these graph structures semantics in terms of ideas based in formal language theory. We describe a collection of operations on procrustean graphs (both semantics-preserving and semantics-mutating), and show how a family of questions about the destructiveness of a change to the robot hardware can be answered by applying these operations. We also highlight the connections between this new approach and existing threads of research, including combinatorial filtering, Erdmann’s strategy complexes, and hybrid automata. |
| Tasks | |
| Published | 2018-07-23 |
| URL | http://arxiv.org/abs/1807.08856v1 |
| http://arxiv.org/pdf/1807.08856v1.pdf | |
| PWC | https://paperswithcode.com/paper/toward-a-language-theoretic-foundation-for |
| Repo | |
| Framework | |
Modeling Preemptive Behaviors for Uncommon Hazardous Situations From Demonstrations
| Title | Modeling Preemptive Behaviors for Uncommon Hazardous Situations From Demonstrations |
| Authors | Priyam Parashar, Akansel Cosgun, Alireza Nakhaei, Kikuo Fujimura |
| Abstract | This paper presents a learning from demonstration approach to programming safe, autonomous behaviors for uncommon driving scenarios. Simulation is used to re-create a targeted driving situation, one containing a road-side hazard creating a significant occlusion in an urban neighborhood, and collect optimal driving behaviors from 24 users. Paper employs a key-frame based approach combined with an algorithm to linearly combine models in order to extend the behavior to novel variations of the target situation. This approach is theoretically agnostic to the kind of LfD framework used for modeling data and our results suggest it generalizes well to variations containing an additional number of hazards occurring in sequence. The linear combination algorithm is informed by analysis of driving data, which also suggests that decision-making algorithms need to consider a trade-off between road-rules and immediate rewards to tackle some complex cases. |
| Tasks | Decision Making |
| Published | 2018-06-01 |
| URL | http://arxiv.org/abs/1806.00143v1 |
| http://arxiv.org/pdf/1806.00143v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-preemptive-behaviors-for-uncommon |
| Repo | |
| Framework | |
