Paper Group ANR 1026
A theoretical framework for deep locally connected ReLU network. Optimizing the Trade-off between Single-Stage and Two-Stage Object Detectors using Image Difficulty Prediction. Human Indignity: From Legal AI Personhood to Selfish Memes. Density-Adaptive Kernel based Re-Ranking for Person Re-Identification. Infrared Safety of a Neural-Net Top Taggin …
A theoretical framework for deep locally connected ReLU network
| Title | A theoretical framework for deep locally connected ReLU network |
| Authors | Yuandong Tian |
| Abstract | Understanding theoretical properties of deep and locally connected nonlinear network, such as deep convolutional neural network (DCNN), is still a hard problem despite its empirical success. In this paper, we propose a novel theoretical framework for such networks with ReLU nonlinearity. The framework explicitly formulates data distribution, favors disentangled representations and is compatible with common regularization techniques such as Batch Norm. The framework is built upon teacher-student setting, by expanding the student forward/backward propagation onto the teacher’s computational graph. The resulting model does not impose unrealistic assumptions (e.g., Gaussian inputs, independence of activation, etc). Our framework could help facilitate theoretical analysis of many practical issues, e.g. overfitting, generalization, disentangled representations in deep networks. |
| Tasks | |
| Published | 2018-09-28 |
| URL | http://arxiv.org/abs/1809.10829v1 |
| http://arxiv.org/pdf/1809.10829v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-theoretical-framework-for-deep-locally |
| Repo | |
| Framework | |
Optimizing the Trade-off between Single-Stage and Two-Stage Object Detectors using Image Difficulty Prediction
| Title | Optimizing the Trade-off between Single-Stage and Two-Stage Object Detectors using Image Difficulty Prediction |
| Authors | Petru Soviany, Radu Tudor Ionescu |
| Abstract | There are mainly two types of state-of-the-art object detectors. On one hand, we have two-stage detectors, such as Faster R-CNN (Region-based Convolutional Neural Networks) or Mask R-CNN, that (i) use a Region Proposal Network to generate regions of interests in the first stage and (ii) send the region proposals down the pipeline for object classification and bounding-box regression. Such models reach the highest accuracy rates, but are typically slower. On the other hand, we have single-stage detectors, such as YOLO (You Only Look Once) and SSD (Singe Shot MultiBox Detector), that treat object detection as a simple regression problem by taking an input image and learning the class probabilities and bounding box coordinates. Such models reach lower accuracy rates, but are much faster than two-stage object detectors. In this paper, we propose to use an image difficulty predictor to achieve an optimal trade-off between accuracy and speed in object detection. The image difficulty predictor is applied on the test images to split them into easy versus hard images. Once separated, the easy images are sent to the faster single-stage detector, while the hard images are sent to the more accurate two-stage detector. Our experiments on PASCAL VOC 2007 show that using image difficulty compares favorably to a random split of the images. Our method is flexible, in that it allows to choose a desired threshold for splitting the images into easy versus hard. |
| Tasks | Object Classification, Object Detection |
| Published | 2018-03-23 |
| URL | http://arxiv.org/abs/1803.08707v3 |
| http://arxiv.org/pdf/1803.08707v3.pdf | |
| PWC | https://paperswithcode.com/paper/optimizing-the-trade-off-between-single-stage |
| Repo | |
| Framework | |
Human Indignity: From Legal AI Personhood to Selfish Memes
| Title | Human Indignity: From Legal AI Personhood to Selfish Memes |
| Authors | Roman V. Yampolskiy |
| Abstract | It is possible to rely on current corporate law to grant legal personhood to Artificially Intelligent (AI) agents. In this paper, after introducing pathways to AI personhood, we analyze consequences of such AI empowerment on human dignity, human safety and AI rights. We emphasize possibility of creating selfish memes and legal system hacking in the context of artificial entities. Finally, we consider some potential solutions for addressing described problems. |
| Tasks | |
| Published | 2018-10-02 |
| URL | http://arxiv.org/abs/1810.02724v1 |
| http://arxiv.org/pdf/1810.02724v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-indignity-from-legal-ai-personhood-to |
| Repo | |
| Framework | |
Density-Adaptive Kernel based Re-Ranking for Person Re-Identification
| Title | Density-Adaptive Kernel based Re-Ranking for Person Re-Identification |
| Authors | Ruo-Pei Guo, Chun-Guang Li, Yonghua Li, Jiaru Lin, Jun Guo |
| Abstract | Person Re-Identification (ReID) refers to the task of verifying the identity of a pedestrian observed from non-overlapping views of surveillance cameras networks. Recently, it has been validated that re-ranking could bring remarkable performance improvements for a person ReID system. However, the current re-ranking approaches either require feedbacks from users or suffer from burdensome computation cost. In this paper, we propose to exploit a density-adaptive smooth kernel technique to perform efficient and effective re-ranking. Specifically, we adopt a smooth kernel function to formulate the neighboring relationship amongst data samples with a density-adaptive parameter. Based on the new formulation, we present two simple yet effective re-ranking methods, termed inverse Density-Adaptive Kernel based Re-ranking (inv-DAKR) and bidirectional Density-Adaptive Kernel based Re-ranking (bi-DAKR), in which the local density information around each gallery sample is elegantly exploited. Moreover, we extend the proposed inv-DAKR and bi-DAKR to incorporate the available extra probe samples and demonstrate that the extra probe samples are able to improve the local neighborhood and thus further refine the ranking result. Extensive experiments are conducted on six benchmark datasets, including PRID450s, VIPeR, CUHK03, GRID, Market-1501 and Mars. Experimental results demonstrate that our proposals are effective and efficient. |
| Tasks | Person Re-Identification |
| Published | 2018-05-20 |
| URL | http://arxiv.org/abs/1805.07698v2 |
| http://arxiv.org/pdf/1805.07698v2.pdf | |
| PWC | https://paperswithcode.com/paper/density-adaptive-kernel-based-re-ranking-for |
| Repo | |
| Framework | |
Infrared Safety of a Neural-Net Top Tagging Algorithm
| Title | Infrared Safety of a Neural-Net Top Tagging Algorithm |
| Authors | Suyong Choi, Seung J. Lee, Maxim Perelstein |
| Abstract | Neural network-based algorithms provide a promising approach to jet classification problems, such as boosted top jet tagging. To date, NN-based top taggers demonstrated excellent performance in Monte Carlo studies. In this paper, we construct a top-jet tagger based on a Convolutional Neural Network (CNN), and apply it to parton-level boosted top samples, with and without an additional gluon in the final state. We show that the jet observable defined by the CNN obeys the canonical definition of infrared safety: it is unaffected by the presence of the extra gluon, as long as it is soft or collinear with one of the quarks. Our results indicate that the CNN tagger is robust with respect to possible mis-modeling of soft and collinear final-state radiation by Monte Carlo generators. |
| Tasks | |
| Published | 2018-06-04 |
| URL | http://arxiv.org/abs/1806.01263v2 |
| http://arxiv.org/pdf/1806.01263v2.pdf | |
| PWC | https://paperswithcode.com/paper/infrared-safety-of-a-neural-net-top-tagging |
| Repo | |
| Framework | |
Adapting control policies from simulation to reality using a pairwise loss
| Title | Adapting control policies from simulation to reality using a pairwise loss |
| Authors | Ulrich Viereck, Xingchao Peng, Kate Saenko, Robert Platt |
| Abstract | This paper proposes an approach to domain transfer based on a pairwise loss function that helps transfer control policies learned in simulation onto a real robot. We explore the idea in the context of a ‘category level’ manipulation task where a control policy is learned that enables a robot to perform a mating task involving novel objects. We explore the case where depth images are used as the main form of sensor input. Our experimental results demonstrate that proposed method consistently outperforms baseline methods that train only in simulation or that combine real and simulated data in a naive way. |
| Tasks | |
| Published | 2018-07-27 |
| URL | http://arxiv.org/abs/1807.10413v2 |
| http://arxiv.org/pdf/1807.10413v2.pdf | |
| PWC | https://paperswithcode.com/paper/adapting-control-policies-from-simulation-to |
| Repo | |
| Framework | |
Robust Regression for Automatic Fusion Plasma Analysis based on Generative Modeling
| Title | Robust Regression for Automatic Fusion Plasma Analysis based on Generative Modeling |
| Authors | Keisuke Fujii, Chihiro Suzuki, Masahiro Hasuo |
| Abstract | The first step to realize automatic experimental data analysis for fusion plasma experiments is fitting noisy data of temperature and density spatial profiles, which are obtained routinely. However, it has been difficult to construct algorithms that fit all the data without over- and under-fitting. In this paper, we show that this difficulty originates from the lack of knowledge of the probability distribution that the measurement data follow. We demonstrate the use of a machine learning technique to estimate the data distribution and to construct an optimal generative model. We show that the fitting algorithm based on the generative modeling outperforms classical heuristic methods in terms of the stability as well as the accuracy. |
| Tasks | |
| Published | 2018-08-03 |
| URL | https://arxiv.org/abs/1808.01056v2 |
| https://arxiv.org/pdf/1808.01056v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-regression-for-automatic-fusion-plasma |
| Repo | |
| Framework | |
A comparative study of feature selection methods for stress hotspot classification in materials
| Title | A comparative study of feature selection methods for stress hotspot classification in materials |
| Authors | Ankita Mangal, Elizabeth A. Holm |
| Abstract | The first step in constructing a machine learning model is defining the features of the data set that can be used for optimal learning. In this work we discuss feature selection methods, which can be used to build better models, as well as achieve model interpretability. We applied these methods in the context of stress hotspot classification problem, to determine what microstructural characteristics can cause stress to build up in certain grains during uniaxial tensile deformation. The results show how some feature selection techniques are biased and demonstrate a preferred technique to get feature rankings for physical interpretations. |
| Tasks | Feature Selection |
| Published | 2018-04-19 |
| URL | http://arxiv.org/abs/1804.09604v1 |
| http://arxiv.org/pdf/1804.09604v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comparative-study-of-feature-selection-1 |
| Repo | |
| Framework | |
Photorealistic Style Transfer for Videos
| Title | Photorealistic Style Transfer for Videos |
| Authors | Michael Honke, Rahul Iyer, Dishant Mittal |
| Abstract | Photorealistic style transfer is a technique which transfers colour from one reference domain to another domain by using deep learning and optimization techniques. Here, we present a technique which we use to transfer style and colour from a reference image to a video. |
| Tasks | Style Transfer |
| Published | 2018-07-01 |
| URL | http://arxiv.org/abs/1807.00273v1 |
| http://arxiv.org/pdf/1807.00273v1.pdf | |
| PWC | https://paperswithcode.com/paper/photorealistic-style-transfer-for-videos |
| Repo | |
| Framework | |
Geometrical Stem Detection from Image Data for Precision Agriculture
| Title | Geometrical Stem Detection from Image Data for Precision Agriculture |
| Authors | F. Langer, L. Mandtler, A. Milioto, E. Palazzolo, C. Stachniss |
| Abstract | High efficiency in precision farming depends on accurate tools to perform weed detection and mapping of crops. This allows for precise removal of harmful weeds with a lower amount of pesticides, as well as increase of the harvest’s yield by providing the farmer with valuable information. In this paper, we address the problem of fully automatic stem detection from image data for this purpose. Our approach runs on mobile agricultural robots taking RGB images. After processing the images to obtain a vegetation mask, our approach separates each plant into its individual leaves and later estimates a precise stem position. This allows an upstream mapping algorithm to add the high-resolution stem positions as a semantic aggregate to the global map of the robot, which can be used for weeding and for analyzing crop statistics. We implemented our approach and thoroughly tested it on three different datasets with vegetation masks and stem position ground truth. The experiments presented in this paper conclude that our module is able to detect leaves and estimate the stem’s position at a rate of 56 Hz on a single CPU. We furthermore provide the software to the community. |
| Tasks | |
| Published | 2018-12-13 |
| URL | http://arxiv.org/abs/1812.05415v1 |
| http://arxiv.org/pdf/1812.05415v1.pdf | |
| PWC | https://paperswithcode.com/paper/geometrical-stem-detection-from-image-data |
| Repo | |
| Framework | |
Budgeted Multi-Objective Optimization with a Focus on the Central Part of the Pareto Front – Extended Version
| Title | Budgeted Multi-Objective Optimization with a Focus on the Central Part of the Pareto Front – Extended Version |
| Authors | David Gaudrie, Rodolphe Le Riche, Victor Picheny, Benoit Enaux, Vincent Herbert |
| Abstract | Optimizing nonlinear systems involving expensive computer experiments with regard to conflicting objectives is a common challenge. When the number of experiments is severely restricted and/or when the number of objectives increases, uncovering the whole set of Pareto optimal solutions is out of reach, even for surrogate-based approaches: the proposed solutions are sub-optimal or do not cover the front well. As non-compromising optimal solutions have usually little point in applications, this work restricts the search to solutions that are close to the Pareto front center. The article starts by characterizing this center, which is defined for any type of front. Next, a Bayesian multi-objective optimization method for directing the search towards it is proposed. Targeting a subset of the Pareto front allows an improved optimality of the solutions and a better coverage of this zone, which is our main concern. A criterion for detecting convergence to the center is described. If the criterion is triggered, a widened central part of the Pareto front is targeted such that sufficiently accurate convergence to it is forecasted within the remaining budget. Numerical experiments show how the resulting algorithm, C-EHI, better locates the central part of the Pareto front when compared to state-of-the-art Bayesian algorithms. |
| Tasks | |
| Published | 2018-09-27 |
| URL | https://arxiv.org/abs/1809.10482v4 |
| https://arxiv.org/pdf/1809.10482v4.pdf | |
| PWC | https://paperswithcode.com/paper/budgeted-multi-objective-optimization-with-a |
| Repo | |
| Framework | |
Hessian-Aware Zeroth-Order Optimization for Black-Box Adversarial Attack
| Title | Hessian-Aware Zeroth-Order Optimization for Black-Box Adversarial Attack |
| Authors | Haishan Ye, Zhichao Huang, Cong Fang, Chris Junchi Li, Tong Zhang |
| Abstract | Zeroth-order optimization is an important research topic in machine learning. In recent years, it has become a key tool in black-box adversarial attack to neural network based image classifiers. However, existing zeroth-order optimization algorithms rarely extract second-order information of the model function. In this paper, we utilize the second-order information of the objective function and propose a novel \textit{Hessian-aware zeroth-order algorithm} called \texttt{ZO-HessAware}. Our theoretical result shows that \texttt{ZO-HessAware} has an improved zeroth-order convergence rate and query complexity under structured Hessian approximation, where we propose a few approximation methods for estimating Hessian. Our empirical studies on the black-box adversarial attack problem validate that our algorithm can achieve improved success rates with a lower query complexity. |
| Tasks | Adversarial Attack |
| Published | 2018-12-29 |
| URL | http://arxiv.org/abs/1812.11377v2 |
| http://arxiv.org/pdf/1812.11377v2.pdf | |
| PWC | https://paperswithcode.com/paper/hessian-aware-zeroth-order-optimization-for |
| Repo | |
| Framework | |
Automatic Exposure Compensation for Multi-Exposure Image Fusion
| Title | Automatic Exposure Compensation for Multi-Exposure Image Fusion |
| Authors | Yuma Kinoshita, Sayaka Shiota, Hitoshi Kiya |
| Abstract | This paper proposes a novel luminance adjustment method based on automatic exposure compensation for multi-exposure image fusion. Multi-exposure image fusion is a method to produce images without saturation regions, by using photos with different exposures. In conventional works, it has been pointed out that the quality of those multi-exposure images can be improved by adjusting the luminance of them. However, how to determine the degree of adjustment has never been discussed. This paper therefore proposes a way to automatically determines the degree on the basis of the luminance distribution of input multi-exposure images. Moreover, new weights, called “simple weights”, for image fusion are also considered for the proposed luminance adjustment method. Experimental results show that the multi-exposure images adjusted by the proposed method have better quality than the input multi-exposure ones in terms of the well-exposedness. It is also confirmed that the proposed simple weights provide the highest score of statistical naturalness and discrete entropy in all fusion methods. |
| Tasks | |
| Published | 2018-05-29 |
| URL | http://arxiv.org/abs/1805.11211v1 |
| http://arxiv.org/pdf/1805.11211v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-exposure-compensation-for-multi |
| Repo | |
| Framework | |
Affective Recommendation System for Tourists by Using Emotion Generating Calculations
| Title | Affective Recommendation System for Tourists by Using Emotion Generating Calculations |
| Authors | Takumi Ichimura, Issei Tachibana |
| Abstract | An emotion orientated intelligent interface consists of Emotion Generating Calculations (EGC) and Mental State Transition Network (MSTN). We have developed the Android EGC application software which the agent works to evaluate the feelings in the conversation. In this paper, we develop the tourist information system which can estimate the user’s feelings at the sightseeing spot. The system can recommend the sightseeing spot and the local food corresponded to the user’s feeling. The system calculates the recommendation list by the estimate function which consists of Google search results, the important degree of a term at the sightseeing website, and the the aroused emotion by EGC. In order to show the effectiveness, this paper describes the experimental results for some situations during Hiroshima sightseeing. |
| Tasks | |
| Published | 2018-04-09 |
| URL | http://arxiv.org/abs/1804.04946v1 |
| http://arxiv.org/pdf/1804.04946v1.pdf | |
| PWC | https://paperswithcode.com/paper/affective-recommendation-system-for-tourists |
| Repo | |
| Framework | |
Deepwound: Automated Postoperative Wound Assessment and Surgical Site Surveillance through Convolutional Neural Networks
| Title | Deepwound: Automated Postoperative Wound Assessment and Surgical Site Surveillance through Convolutional Neural Networks |
| Authors | Varun Shenoy, Elizabeth Foster, Lauren Aalami, Bakar Majeed, Oliver Aalami |
| Abstract | Postoperative wound complications are a significant cause of expense for hospitals, doctors, and patients. Hence, an effective method to diagnose the onset of wound complications is strongly desired. Algorithmically classifying wound images is a difficult task due to the variability in the appearance of wound sites. Convolutional neural networks (CNNs), a subgroup of artificial neural networks that have shown great promise in analyzing visual imagery, can be leveraged to categorize surgical wounds. We present a multi-label CNN ensemble, Deepwound, trained to classify wound images using only image pixels and corresponding labels as inputs. Our final computational model can accurately identify the presence of nine labels: drainage, fibrinous exudate, granulation tissue, surgical site infection, open wound, staples, steri strips, and sutures. Our model achieves receiver operating curve (ROC) area under curve (AUC) scores, sensitivity, specificity, and F1 scores superior to prior work in this area. Smartphones provide a means to deliver accessible wound care due to their increasing ubiquity. Paired with deep neural networks, they offer the capability to provide clinical insight to assist surgeons during postoperative care. We also present a mobile application frontend to Deepwound that assists patients in tracking their wound and surgical recovery from the comfort of their home. |
| Tasks | |
| Published | 2018-07-11 |
| URL | http://arxiv.org/abs/1807.04355v1 |
| http://arxiv.org/pdf/1807.04355v1.pdf | |
| PWC | https://paperswithcode.com/paper/deepwound-automated-postoperative-wound |
| Repo | |
| Framework | |
