July 27, 2019

3072 words 15 mins read

Paper Group ANR 581

On Detecting Adversarial Perturbations. Multimodal Fusion via a Series of Transfers for Noise Removal. Quantum Mechanical Approach to Modelling Reliability of Sensor Reports. Visual Decoding of Targets During Visual Search From Human Eye Fixations. Transductive Zero-Shot Learning with a Self-training dictionary approach. Challenges in Providing Aut …

On Detecting Adversarial Perturbations


Title	On Detecting Adversarial Perturbations
Authors	Jan Hendrik Metzen, Tim Genewein, Volker Fischer, Bastian Bischoff
Abstract	Machine learning and deep learning in particular has advanced tremendously on perceptual tasks in recent years. However, it remains vulnerable against adversarial perturbations of the input that have been crafted specifically to fool the system while being quasi-imperceptible to a human. In this work, we propose to augment deep neural networks with a small “detector” subnetwork which is trained on the binary classification task of distinguishing genuine data from data containing adversarial perturbations. Our method is orthogonal to prior work on addressing adversarial perturbations, which has mostly focused on making the classification network itself more robust. We show empirically that adversarial perturbations can be detected surprisingly well even though they are quasi-imperceptible to humans. Moreover, while the detectors have been trained to detect only a specific adversary, they generalize to similar and weaker adversaries. In addition, we propose an adversarial attack that fools both the classifier and the detector and a novel training procedure for the detector that counteracts this attack.
Tasks	Adversarial Attack
Published	2017-02-14
URL	http://arxiv.org/abs/1702.04267v2
PDF	http://arxiv.org/pdf/1702.04267v2.pdf
PWC	https://paperswithcode.com/paper/on-detecting-adversarial-perturbations
Repo
Framework

Multimodal Fusion via a Series of Transfers for Noise Removal


Title	Multimodal Fusion via a Series of Transfers for Noise Removal
Authors	Chang-Hwan Son, Xiao-Ping Zhang
Abstract	Near-infrared imaging has been considered as a solution to provide high quality photographs in dim lighting conditions. This imaging system captures two types of multimodal images: one is near-infrared gray image (NGI) and the other is the visible color image (VCI). NGI is noise-free but it is grayscale, whereas the VCI has colors but it contains noise. Moreover, there exist serious edge and brightness discrepancies between NGI and VCI. To deal with this problem, a new transfer-based fusion method is proposed for noise removal. Different from conventional fusion approaches, the proposed method conducts a series of transfers: contrast, detail, and color transfers. First, the proposed contrast and detail transfers aim at solving the serious discrepancy problem, thereby creating a new noise-free and detail-preserving NGI. Second, the proposed color transfer models the unknown colors from the denoised VCI via a linear transform, and then transfers natural-looking colors into the newly generated NGI. Experimental results show that the proposed transfer-based fusion method is highly successful in solving the discrepancy problem, thereby describing edges and textures clearly as well as removing noise completely on the fused images. Most of all, the proposed method is superior to conventional fusion methods and guided filtering, and even the state-of-the-art fusion methods based on scale map and layer decomposition.
Tasks
Published	2017-01-22
URL	http://arxiv.org/abs/1701.06121v1
PDF	http://arxiv.org/pdf/1701.06121v1.pdf
PWC	https://paperswithcode.com/paper/multimodal-fusion-via-a-series-of-transfers
Repo
Framework

Quantum Mechanical Approach to Modelling Reliability of Sensor Reports


Title	Quantum Mechanical Approach to Modelling Reliability of Sensor Reports
Authors	Zichang He, Wen Jiang
Abstract	Dempster-Shafer evidence theory is wildly applied in multi-sensor data fusion. However, lots of uncertainty and interference exist in practical situation, especially in the battle field. It is still an open issue to model the reliability of sensor reports. Many methods are proposed based on the relationship among collected data. In this letter, we proposed a quantum mechanical approach to evaluate the reliability of sensor reports, which is based on the properties of a sensor itself. The proposed method is used to modify the combining of evidences.
Tasks
Published	2017-04-17
URL	http://arxiv.org/abs/1705.01013v1
PDF	http://arxiv.org/pdf/1705.01013v1.pdf
PWC	https://paperswithcode.com/paper/quantum-mechanical-approach-to-modelling
Repo
Framework

Visual Decoding of Targets During Visual Search From Human Eye Fixations


Title	Visual Decoding of Targets During Visual Search From Human Eye Fixations
Authors	Hosnieh Sattar, Mario Fritz, Andreas Bulling
Abstract	What does human gaze reveal about a users’ intents and to which extend can these intents be inferred or even visualized? Gaze was proposed as an implicit source of information to predict the target of visual search and, more recently, to predict the object class and attributes of the search target. In this work, we go one step further and investigate the feasibility of combining recent advances in encoding human gaze information using deep convolutional neural networks with the power of generative image models to visually decode, i.e. create a visual representation of, the search target. Such visual decoding is challenging for two reasons: 1) the search target only resides in the user’s mind as a subjective visual pattern, and can most often not even be described verbally by the person, and 2) it is, as of yet, unclear if gaze fixations contain sufficient information for this task at all. We show, for the first time, that visual representations of search targets can indeed be decoded only from human gaze fixations. We propose to first encode fixations into a semantic representation and then decode this representation into an image. We evaluate our method on a recent gaze dataset of 14 participants searching for clothing in image collages and validate the model’s predictions using two human studies. Our results show that 62% (Chance level = 10%) of the time users were able to select the categories of the decoded image right. In our second studies we show the importance of a local gaze encoding for decoding visual search targets of user
Tasks
Published	2017-06-19
URL	http://arxiv.org/abs/1706.05993v3
PDF	http://arxiv.org/pdf/1706.05993v3.pdf
PWC	https://paperswithcode.com/paper/visual-decoding-of-targets-during-visual
Repo
Framework

Transductive Zero-Shot Learning with a Self-training dictionary approach


Title	Transductive Zero-Shot Learning with a Self-training dictionary approach
Authors	Yunlong Yu, Zhong Ji, Xi Li, Jichang Guo, Zhongfei Zhang, Haibin Ling, Fei Wu
Abstract	As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training data. To address this problem, ZSL is usually carried out in the following two aspects: 1) capturing the domain distribution connections between seen classes data and unseen classes data; and 2) modeling the semantic interactions between the image feature space and the label embedding space. Motivated by these observations, we propose a bidirectional mapping based semantic relationship modeling scheme that seeks for crossmodal knowledge transfer by simultaneously projecting the image features and label embeddings into a common latent space. Namely, we have a bidirectional connection relationship that takes place from the image feature space to the latent space as well as from the label embedding space to the latent space. To deal with the domain shift problem, we further present a transductive learning approach that formulates the class prediction problem in an iterative refining process, where the object classification capacity is progressively reinforced through bootstrapping-based model updating over highly reliable instances. Experimental results on three benchmark datasets (AwA, CUB and SUN) demonstrate the effectiveness of the proposed approach against the state-of-the-art approaches.
Tasks	Object Classification, Transfer Learning, Zero-Shot Learning
Published	2017-03-27
URL	http://arxiv.org/abs/1703.08893v1
PDF	http://arxiv.org/pdf/1703.08893v1.pdf
PWC	https://paperswithcode.com/paper/transductive-zero-shot-learning-with-a-self
Repo
Framework

Challenges in Providing Automatic Affective Feedback in Instant Messaging Applications


Title	Challenges in Providing Automatic Affective Feedback in Instant Messaging Applications
Authors	Chieh-Yang Huang, Ting-Hao, Huang, Lun-Wei Ku
Abstract	Instant messaging is one of the major channels of computer mediated communication. However, humans are known to be very limited in understanding others’ emotions via text-based communication. Aiming on introducing emotion sensing technologies to instant messaging, we developed EmotionPush, a system that automatically detects the emotions of the messages end-users received on Facebook Messenger and provides colored cues on their smartphones accordingly. We conducted a deployment study with 20 participants during a time span of two weeks. In this paper, we revealed five challenges, along with examples, that we observed in our study based on both user’s feedback and chat logs, including (i)the continuum of emotions, (ii)multi-user conversations, (iii)different dynamics between different users, (iv)misclassification of emotions and (v)unconventional content. We believe this discussion will benefit the future exploration of affective computing for instant messaging, and also shed light on research of conversational emotion sensing.
Tasks
Published	2017-02-09
URL	http://arxiv.org/abs/1702.02736v1
PDF	http://arxiv.org/pdf/1702.02736v1.pdf
PWC	https://paperswithcode.com/paper/challenges-in-providing-automatic-affective
Repo
Framework

Collaborative Evolution of 3D Models


Title	Collaborative Evolution of 3D Models
Authors	Juan C. Quiroz, Amit Banerjee, Sushil J. Louis, Sergiu M. Dascalu
Abstract	We present a computational model of creative design based on collaborative interactive genetic algorithms. In our model, designers individually guide interactive genetic algorithms (IGAs) to generate and explore potential design solutions quickly. Collaboration is supported by allowing designers to share solutions amongst each other while using IGAs, with the sharing of solutions adding variables to the search space. We present experiments on 3D modeling as a case study, with designers creating model transformations individually and collaboratively. The transformations were evaluated by participants in surveys and results show that individual and collaborative models were considered equally creative. However, the use of our collaborative IGAs model materially changes resulting designs compared to individual IGAs.
Tasks
Published	2017-11-27
URL	http://arxiv.org/abs/1711.09958v1
PDF	http://arxiv.org/pdf/1711.09958v1.pdf
PWC	https://paperswithcode.com/paper/collaborative-evolution-of-3d-models
Repo
Framework

Deep Learning for Explicitly Modeling Optimization Landscapes


Title	Deep Learning for Explicitly Modeling Optimization Landscapes
Authors	Shumeet Baluja
Abstract	In all but the most trivial optimization problems, the structure of the solutions exhibit complex interdependencies between the input parameters. Decades of research with stochastic search techniques has shown the benefit of explicitly modeling the interactions between sets of parameters and the overall quality of the solutions discovered. We demonstrate a novel method, based on learning deep networks, to model the global landscapes of optimization problems. To represent the search space concisely and accurately, the deep networks must encode information about the underlying parameter interactions and their contributions to the quality of the solution. Once the networks are trained, the networks are probed to reveal parameter combinations with high expected performance with respect to the optimization task. These estimates are used to initialize fast, randomized, local search algorithms, which in turn expose more information about the search space that is subsequently used to refine the models. We demonstrate the technique on multiple optimization problems that have arisen in a variety of real-world domains, including: packing, graphics, job scheduling, layout and compression. The problems include combinatoric search spaces, discontinuous and highly non-linear spaces, and span binary, higher-cardinality discrete, as well as continuous parameters. Strengths, limitations, and extensions of the approach are extensively discussed and demonstrated.
Tasks
Published	2017-03-21
URL	http://arxiv.org/abs/1703.07394v1
PDF	http://arxiv.org/pdf/1703.07394v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-explicitly-modeling
Repo
Framework

Candidates vs. Noises Estimation for Large Multi-Class Classification Problem


Title	Candidates vs. Noises Estimation for Large Multi-Class Classification Problem
Authors	Lei Han, Yiheng Huang, Tong Zhang
Abstract	This paper proposes a method for multi-class classification problems, where the number of classes K is large. The method, referred to as Candidates vs. Noises Estimation (CANE), selects a small subset of candidate classes and samples the remaining classes. We show that CANE is always consistent and computationally efficient. Moreover, the resulting estimator has low statistical variance approaching that of the maximum likelihood estimator, when the observed label belongs to the selected candidates with high probability. In practice, we use a tree structure with leaves as classes to promote fast beam search for candidate selection. We further apply the CANE method to estimate word probabilities in learning large neural language models. Extensive experimental results show that CANE achieves better prediction accuracy over the Noise-Contrastive Estimation (NCE), its variants and a number of the state-of-the-art tree classifiers, while it gains significant speedup compared to standard O(K) methods.
Tasks
Published	2017-11-02
URL	http://arxiv.org/abs/1711.00658v2
PDF	http://arxiv.org/pdf/1711.00658v2.pdf
PWC	https://paperswithcode.com/paper/candidates-vs-noises-estimation-for-large
Repo
Framework

Revisiting stochastic off-policy action-value gradients


Title	Revisiting stochastic off-policy action-value gradients
Authors	Yemi Okesanjo, Victor Kofia
Abstract	Off-policy stochastic actor-critic methods rely on approximating the stochastic policy gradient in order to derive an optimal policy. One may also derive the optimal policy by approximating the action-value gradient. The use of action-value gradients is desirable as policy improvement occurs along the direction of steepest ascent. This has been studied extensively within the context of natural gradient actor-critic algorithms and more recently within the context of deterministic policy gradients. In this paper we briefly discuss the off-policy stochastic counterpart to deterministic action-value gradients, as well as an incremental approach for following the policy gradient in lieu of the natural gradient.
Tasks
Published	2017-03-06
URL	http://arxiv.org/abs/1703.02102v2
PDF	http://arxiv.org/pdf/1703.02102v2.pdf
PWC	https://paperswithcode.com/paper/revisiting-stochastic-off-policy-action-value
Repo
Framework

Variational Policy for Guiding Point Processes


Title	Variational Policy for Guiding Point Processes
Authors	Yichen Wang, Grady Williams, Evangelos Theodorou, Le Song
Abstract	Temporal point processes have been widely applied to model event sequence data generated by online users. In this paper, we consider the problem of how to design the optimal control policy for point processes, such that the stochastic system driven by the point process is steered to a target state. In particular, we exploit the key insight to view the stochastic optimal control problem from the perspective of optimal measure and variational inference. We further propose a convex optimization framework and an efficient algorithm to update the policy adaptively to the current system state. Experiments on synthetic and real-world data show that our algorithm can steer the user activities much more accurately and efficiently than other stochastic control methods.
Tasks	Point Processes
Published	2017-01-30
URL	http://arxiv.org/abs/1701.08585v4
PDF	http://arxiv.org/pdf/1701.08585v4.pdf
PWC	https://paperswithcode.com/paper/variational-policy-for-guiding-point
Repo
Framework

An Analysis of Human-centered Geolocation


Title	An Analysis of Human-centered Geolocation
Authors	Kaili Wang, Yu-Hui Huang, Jose Oramas, Luc Van Gool, Tinne Tuytelaars
Abstract	Online social networks contain a constantly increasing amount of images - most of them focusing on people. Due to cultural and climate factors, fashion trends and physical appearance of individuals differ from city to city. In this paper we investigate to what extent such cues can be exploited in order to infer the geographic location, i.e. the city, where a picture was taken. We conduct a user study, as well as an evaluation of automatic methods based on convolutional neural networks. Experiments on the Fashion 144k and a Pinterest-based dataset show that the automatic methods succeed at this task to a reasonable extent. As a matter of fact, our empirical results suggest that automatic methods can surpass human performance by a large margin. Further inspection of the trained models shows that human-centered characteristics, like clothing style, physical features, and accessories, are informative for the task at hand. Moreover, it reveals that also contextual features, e.g. wall type, natural environment, etc., are taken into account by the automatic methods.
Tasks
Published	2017-07-10
URL	http://arxiv.org/abs/1707.02905v3
PDF	http://arxiv.org/pdf/1707.02905v3.pdf
PWC	https://paperswithcode.com/paper/an-analysis-of-human-centered-geolocation
Repo
Framework

Predicting Adolescent Suicide Attempts with Neural Networks


Title	Predicting Adolescent Suicide Attempts with Neural Networks
Authors	Harish S. Bhat, Sidra J. Goldman-Mellor
Abstract	Though suicide is a major public health problem in the US, machine learning methods are not commonly used to predict an individual’s risk of attempting/committing suicide. In the present work, starting with an anonymized collection of electronic health records for 522,056 unique, California-resident adolescents, we develop neural network models to predict suicide attempts. We frame the problem as a binary classification problem in which we use a patient’s data from 2006-2009 to predict either the presence (1) or absence (0) of a suicide attempt in 2010. After addressing issues such as severely imbalanced classes and the variable length of a patient’s history, we build neural networks with depths varying from two to eight hidden layers. For test set observations where we have at least five ED/hospital visits’ worth of data on a patient, our depth-4 model achieves a sensitivity of 0.703, specificity of 0.980, and AUC of 0.958.
Tasks
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10057v2
PDF	http://arxiv.org/pdf/1711.10057v2.pdf
PWC	https://paperswithcode.com/paper/predicting-adolescent-suicide-attempts-with
Repo
Framework

User and Developer Interaction with Editable and Readable Ontologies


Title	User and Developer Interaction with Editable and Readable Ontologies
Authors	Aisha Blfgeh, Phillip Lord
Abstract	The process of building ontologies is a difficult task that involves collaboration between ontology developers and domain experts and requires an ongoing interaction between them. This collaboration is made more difficult, because they tend to use different tool sets, which can hamper this interaction. In this paper, we propose to decrease this distance between domain experts and ontology developers by creating more readable forms of ontologies, and further to enable editing in normal office environments. Building on a programmatic ontology development environment, such as Tawny-OWL, we are now able to generate these readable/editable from the raw ontological source and its embedded comments. We have this translation to HTML for reading; this environment provides rich hyperlinking as well as active features such as hiding the source code in favour of comments. We are now working on translation to a Word document that also enables editing. Taken together this should provide a significant new route for collaboration between the ontologist and domain specialist.
Tasks
Published	2017-09-26
URL	http://arxiv.org/abs/1709.08982v2
PDF	http://arxiv.org/pdf/1709.08982v2.pdf
PWC	https://paperswithcode.com/paper/user-and-developer-interaction-with-editable
Repo
Framework

Deep Learning for identifying radiogenomic associations in breast cancer


Title	Deep Learning for identifying radiogenomic associations in breast cancer
Authors	Zhe Zhu, Ehab Albadawy, Ashirbani Saha, Jun Zhang, Michael R. Harowicz, Maciej A. Mazurowski
Abstract	Purpose: To determine whether deep learning models can distinguish between breast cancer molecular subtypes based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Materials and methods: In this institutional review board-approved single-center study, we analyzed DCE-MR images of 270 patients at our institution. Lesions of interest were identified by radiologists. The task was to automatically determine whether the tumor is of the Luminal A subtype or of another subtype based on the MR image patches representing the tumor. Three different deep learning approaches were used to classify the tumor according to their molecular subtypes: learning from scratch where only tumor patches were used for training, transfer learning where networks pre-trained on natural images were fine-tuned using tumor patches, and off-the-shelf deep features where the features extracted by neural networks trained on natural images were used for classification with a support vector machine. Network architectures utilized in our experiments were GoogleNet, VGG, and CIFAR. We used 10-fold crossvalidation method for validation and area under the receiver operating characteristic (AUC) as the measure of performance. Results: The best AUC performance for distinguishing molecular subtypes was 0.65 (95% CI:[0.57,0.71]) and was achieved by the off-the-shelf deep features approach. The highest AUC performance for training from scratch was 0.58 (95% CI:[0.51,0.64]) and the best AUC performance for transfer learning was 0.60 (95% CI:[0.52,0.65]) respectively. For the off-the-shelf approach, the features extracted from the fully connected layer performed the best. Conclusion: Deep learning may play a role in discovering radiogenomic associations in breast cancer.
Tasks	Transfer Learning
Published	2017-11-29
URL	http://arxiv.org/abs/1711.11097v1
PDF	http://arxiv.org/pdf/1711.11097v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-identifying-radiogenomic
Repo
Framework