Paper Group ANR 637
Exploring Disentangled Feature Representation Beyond Face Identification. Point-cloud-based place recognition using CNN feature extraction. Plan Explanations as Model Reconciliation – An Empirical Study. Side Information for Face Completion: a Robust PCA Approach. Towards fully automated protein structure elucidation with NMR spectroscopy. Exploit …
Exploring Disentangled Feature Representation Beyond Face Identification
| Title | Exploring Disentangled Feature Representation Beyond Face Identification |
| Authors | Yu Liu, Fangyin Wei, Jing Shao, Lu Sheng, Junjie Yan, Xiaogang Wang |
| Abstract | This paper proposes learning disentangled but complementary face features with minimal supervision by face identification. Specifically, we construct an identity Distilling and Dispelling Autoencoder (D2AE) framework that adversarially learns the identity-distilled features for identity verification and the identity-dispelled features to fool the verification system. Thanks to the design of two-stream cues, the learned disentangled features represent not only the identity or attribute but the complete input image. Comprehensive evaluations further demonstrate that the proposed features not only maintain state-of-the-art identity verification performance on LFW, but also acquire competitive discriminative power for face attribute recognition on CelebA and LFWA. Moreover, the proposed system is ready to semantically control the face generation/editing based on various identities and attributes in an unsupervised manner. |
| Tasks | Face Generation, Face Identification |
| Published | 2018-04-10 |
| URL | http://arxiv.org/abs/1804.03487v1 |
| http://arxiv.org/pdf/1804.03487v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-disentangled-feature-representation |
| Repo | |
| Framework | |
Point-cloud-based place recognition using CNN feature extraction
| Title | Point-cloud-based place recognition using CNN feature extraction |
| Authors | Ting Sun, Ming Liu, Haoyang Ye, Dit-Yan Yeung |
| Abstract | This paper proposes a novel point-cloud-based place recognition system that adopts a deep learning approach for feature extraction. By using a convolutional neural network pre-trained on color images to extract features from a range image without fine-tuning on extra range images, significant improvement has been observed when compared to using hand-crafted features. The resulting system is illumination invariant, rotation invariant and robust against moving objects that are unrelated to the place identity. Apart from the system itself, we also bring to the community a new place recognition dataset containing both point cloud and grayscale images covering a full $360^\circ$ environmental view. In addition, the dataset is organized in such a way that it facilitates experimental validation with respect to rotation invariance or robustness against unrelated moving objects separately. |
| Tasks | |
| Published | 2018-10-23 |
| URL | http://arxiv.org/abs/1810.09631v1 |
| http://arxiv.org/pdf/1810.09631v1.pdf | |
| PWC | https://paperswithcode.com/paper/point-cloud-based-place-recognition-using-cnn |
| Repo | |
| Framework | |
Plan Explanations as Model Reconciliation – An Empirical Study
| Title | Plan Explanations as Model Reconciliation – An Empirical Study |
| Authors | Tathagata Chakraborti, Sarath Sreedharan, Sachin Grover, Subbarao Kambhampati |
| Abstract | Recent work in explanation generation for decision making agents has looked at how unexplained behavior of autonomous systems can be understood in terms of differences in the model of the system and the human’s understanding of the same, and how the explanation process as a result of this mismatch can be then seen as a process of reconciliation of these models. Existing algorithms in such settings, while having been built on contrastive, selective and social properties of explanations as studied extensively in the psychology literature, have not, to the best of our knowledge, been evaluated in settings with actual humans in the loop. As such, the applicability of such explanations to human-AI and human-robot interactions remains suspect. In this paper, we set out to evaluate these explanation generation algorithms in a series of studies in a mock search and rescue scenario with an internal semi-autonomous robot and an external human commander. We demonstrate to what extent the properties of these algorithms hold as they are evaluated by humans, and how the dynamics of trust between the human and the robot evolve during the process of these interactions. |
| Tasks | Decision Making |
| Published | 2018-02-03 |
| URL | http://arxiv.org/abs/1802.01013v1 |
| http://arxiv.org/pdf/1802.01013v1.pdf | |
| PWC | https://paperswithcode.com/paper/plan-explanations-as-model-reconciliation-an |
| Repo | |
| Framework | |
Side Information for Face Completion: a Robust PCA Approach
| Title | Side Information for Face Completion: a Robust PCA Approach |
| Authors | Niannan Xue, Jiankang Deng, Shiyang Cheng, Yannis Panagakis, Stefanos Zafeiriou |
| Abstract | Robust principal component analysis (RPCA) is a powerful method for learning low-rank feature representation of various visual data. However, for certain types as well as significant amount of error corruption, it fails to yield satisfactory results; a drawback that can be alleviated by exploiting domain-dependent prior knowledge or information. In this paper, we propose two models for the RPCA that take into account such side information, even in the presence of missing values. We apply this framework to the task of UV completion which is widely used in pose-invariant face recognition. Moreover, we construct a generative adversarial network (GAN) to extract side information as well as subspaces. These subspaces not only assist in the recovery but also speed up the process in case of large-scale data. We quantitatively and qualitatively evaluate the proposed approaches through both synthetic data and five real-world datasets to verify their effectiveness. |
| Tasks | Face Recognition, Facial Inpainting, Robust Face Recognition |
| Published | 2018-01-20 |
| URL | http://arxiv.org/abs/1801.07580v1 |
| http://arxiv.org/pdf/1801.07580v1.pdf | |
| PWC | https://paperswithcode.com/paper/side-information-for-face-completion-a-robust |
| Repo | |
| Framework | |
Towards fully automated protein structure elucidation with NMR spectroscopy
| Title | Towards fully automated protein structure elucidation with NMR spectroscopy |
| Authors | Piotr Klukowski, Adam Gonczarek |
| Abstract | Nuclear magnetic resonance (NMR) spectroscopy is one of the leading techniques for protein studies. The method features a number of properties, allowing to explain macromolecular interactions mechanistically and resolve structures with atomic resolution. However, due to laborious data analysis, a full potential of NMR spectroscopy remains unexploited. Here we present an approach aiming at automation of two major bottlenecks in the analysis pipeline, namely, peak picking and chemical shift assignment. Our approach combines deep learning, non-parametric models and combinatorial optimization, and is able to detect signals of interest in a multidimensional NMR data with high accuracy and match them with atoms in medium-length protein sequences, which is a preliminary step to solve protein spatial structure. |
| Tasks | Combinatorial Optimization |
| Published | 2018-07-31 |
| URL | http://arxiv.org/abs/1808.00564v1 |
| http://arxiv.org/pdf/1808.00564v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-fully-automated-protein-structure |
| Repo | |
| Framework | |
Exploiting Problem Structure in Combinatorial Landscapes: A Case Study on Pure Mathematics Application
| Title | Exploiting Problem Structure in Combinatorial Landscapes: A Case Study on Pure Mathematics Application |
| Authors | Xiao-Feng Xie, Zun-Jing Wang |
| Abstract | In this paper, we present a method using AI techniques to solve a case of pure mathematics applications for finding narrow admissible tuples. The original problem is formulated into a combinatorial optimization problem. In particular, we show how to exploit the local search structure to formulate the problem landscape for dramatic reductions in search space and for non-trivial elimination in search barriers, and then to realize intelligent search strategies for effectively escaping from local minima. Experimental results demonstrate that the proposed method is able to efficiently find best known solutions. This research sheds light on exploiting the local problem structure for an efficient search in combinatorial landscapes as an application of AI to a new problem domain. |
| Tasks | Combinatorial Optimization |
| Published | 2018-12-22 |
| URL | http://arxiv.org/abs/1812.09421v1 |
| http://arxiv.org/pdf/1812.09421v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-problem-structure-in-combinatorial |
| Repo | |
| Framework | |
MagnifyMe: Aiding Cross Resolution Face Recognition via Identity Aware Synthesis
| Title | MagnifyMe: Aiding Cross Resolution Face Recognition via Identity Aware Synthesis |
| Authors | Maneet Singh, Shruti Nagpal, Richa Singh, Mayank Vatsa, Angshul Majumdar |
| Abstract | Enhancing low resolution images via super-resolution or image synthesis for cross-resolution face recognition has been well studied. Several image processing and machine learning paradigms have been explored for addressing the same. In this research, we propose Synthesis via Deep Sparse Representation algorithm for synthesizing a high resolution face image from a low resolution input image. The proposed algorithm learns multi-level sparse representation for both high and low resolution gallery images, along with an identity aware dictionary and a transformation function between the two representations for face identification scenarios. With low resolution test data as input, the high resolution test image is synthesized using the identity aware dictionary and transformation which is then used for face recognition. The performance of the proposed SDSR algorithm is evaluated on four databases, including one real world dataset. Experimental results and comparison with existing seven algorithms demonstrate the efficacy of the proposed algorithm in terms of both face identification and image quality measures. |
| Tasks | Face Identification, Face Recognition, Image Generation, Super-Resolution |
| Published | 2018-02-22 |
| URL | http://arxiv.org/abs/1802.08057v1 |
| http://arxiv.org/pdf/1802.08057v1.pdf | |
| PWC | https://paperswithcode.com/paper/magnifyme-aiding-cross-resolution-face |
| Repo | |
| Framework | |
Combinatorial Bandits for Incentivizing Agents with Dynamic Preferences
| Title | Combinatorial Bandits for Incentivizing Agents with Dynamic Preferences |
| Authors | Tanner Fiez, Shreyas Sekar, Liyuan Zheng, Lillian J. Ratliff |
| Abstract | The design of personalized incentives or recommendations to improve user engagement is gaining prominence as digital platform providers continually emerge. We propose a multi-armed bandit framework for matching incentives to users, whose preferences are unknown a priori and evolving dynamically in time, in a resource constrained environment. We design an algorithm that combines ideas from three distinct domains: (i) a greedy matching paradigm, (ii) the upper confidence bound algorithm (UCB) for bandits, and (iii) mixing times from the theory of Markov chains. For this algorithm, we provide theoretical bounds on the regret and demonstrate its performance via both synthetic and realistic (matching supply and demand in a bike-sharing platform) examples. |
| Tasks | |
| Published | 2018-07-06 |
| URL | http://arxiv.org/abs/1807.02297v1 |
| http://arxiv.org/pdf/1807.02297v1.pdf | |
| PWC | https://paperswithcode.com/paper/combinatorial-bandits-for-incentivizing |
| Repo | |
| Framework | |
Multi-View Multi-Graph Embedding for Brain Network Clustering Analysis
| Title | Multi-View Multi-Graph Embedding for Brain Network Clustering Analysis |
| Authors | Ye Liu, Lifang He, Bokai Cao, Philip S. Yu, Ann B. Ragin, Alex D. Leow |
| Abstract | Network analysis of human brain connectivity is critically important for understanding brain function and disease states. Embedding a brain network as a whole graph instance into a meaningful low-dimensional representation can be used to investigate disease mechanisms and inform therapeutic interventions. Moreover, by exploiting information from multiple neuroimaging modalities or views, we are able to obtain an embedding that is more useful than the embedding learned from an individual view. Therefore, multi-view multi-graph embedding becomes a crucial task. Currently, only a few studies have been devoted to this topic, and most of them focus on the vector-based strategy which will cause structural information contained in the original graphs lost. As a novel attempt to tackle this problem, we propose Multi-view Multi-graph Embedding (M2E) by stacking multi-graphs into multiple partially-symmetric tensors and using tensor techniques to simultaneously leverage the dependencies and correlations among multi-view and multi-graph brain networks. Extensive experiments on real HIV and bipolar disorder brain network datasets demonstrate the superior performance of M2E on clustering brain networks by leveraging the multi-view multi-graph interactions. |
| Tasks | Graph Embedding |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.07703v1 |
| http://arxiv.org/pdf/1806.07703v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-multi-graph-embedding-for-brain |
| Repo | |
| Framework | |
Memristor-based Deep Convolution Neural Network: A Case Study
| Title | Memristor-based Deep Convolution Neural Network: A Case Study |
| Authors | Fan Zhang, Miao Hu |
| Abstract | In this paper, we firstly introduce a method to efficiently implement large-scale high-dimensional convolution with realistic memristor-based circuit components. An experiment verified simulator is adapted for accurate prediction of analog crossbar behavior. An improved conversion algorithm is developed to convert convolution kernels to memristor-based circuits, which minimizes the error with consideration of the data and kernel patterns in CNNs. With circuit simulation for all convolution layers in ResNet-20, we found that 8-bit ADC/DAC is necessary to preserve software level classification accuracy. |
| Tasks | |
| Published | 2018-09-14 |
| URL | https://arxiv.org/abs/1810.02225v1 |
| https://arxiv.org/pdf/1810.02225v1.pdf | |
| PWC | https://paperswithcode.com/paper/memristor-based-deep-convolution-neural |
| Repo | |
| Framework | |
Uncertainty Aware AI ML: Why and How
| Title | Uncertainty Aware AI ML: Why and How |
| Authors | Lance Kaplan, Federico Cerutti, Murat Sensoy, Alun Preece, Paul Sullivan |
| Abstract | This paper argues the need for research to realize uncertainty-aware artificial intelligence and machine learning (AI&ML) systems for decision support by describing a number of motivating scenarios. Furthermore, the paper defines uncertainty-awareness and lays out the challenges along with surveying some promising research directions. A theoretical demonstration illustrates how two emerging uncertainty-aware ML and AI technologies could be integrated and be of value for a route planning operation. |
| Tasks | |
| Published | 2018-09-20 |
| URL | http://arxiv.org/abs/1809.07882v1 |
| http://arxiv.org/pdf/1809.07882v1.pdf | |
| PWC | https://paperswithcode.com/paper/uncertainty-aware-ai-ml-why-and-how |
| Repo | |
| Framework | |
Learning Spectral Transform Network on 3D Surface for Non-rigid Shape Analysis
| Title | Learning Spectral Transform Network on 3D Surface for Non-rigid Shape Analysis |
| Authors | Ruixuan Yu, Jian Sun, Huibin Li |
| Abstract | Designing a network on 3D surface for non-rigid shape analysis is a challenging task. In this work, we propose a novel spectral transform network on 3D surface to learn shape descriptors. The proposed network architecture consists of four stages: raw descriptor extraction, surface second-order pooling, mixture of power function-based spectral transform, and metric learning. The proposed network is simple and shallow. Quantitative experiments on challenging benchmarks show its effectiveness for non-rigid shape retrieval and classification, e.g., it achieved the highest accuracies on SHREC14, 15 datasets as well as the Range subset of SHREC17 dataset. |
| Tasks | Metric Learning |
| Published | 2018-10-21 |
| URL | http://arxiv.org/abs/1810.08950v1 |
| http://arxiv.org/pdf/1810.08950v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-spectral-transform-network-on-3d |
| Repo | |
| Framework | |
Less is More: Simultaneous View Classification and Landmark Detection for Abdominal Ultrasound Images
| Title | Less is More: Simultaneous View Classification and Landmark Detection for Abdominal Ultrasound Images |
| Authors | Zhoubing Xu, Yuankai Huo, JinHyeong Park, Bennett Landman, Andy Milkowski, Sasa Grbic, Shaohua Zhou |
| Abstract | An abdominal ultrasound examination, which is the most common ultrasound examination, requires substantial manual efforts to acquire standard abdominal organ views, annotate the views in texts, and record clinically relevant organ measurements. Hence, automatic view classification and landmark detection of the organs can be instrumental to streamline the examination workflow. However, this is a challenging problem given not only the inherent difficulties from the ultrasound modality, e.g., low contrast and large variations, but also the heterogeneity across tasks, i.e., one classification task for all views, and then one landmark detection task for each relevant view. While convolutional neural networks (CNN) have demonstrated more promising outcomes on ultrasound image analytics than traditional machine learning approaches, it becomes impractical to deploy multiple networks (one for each task) due to the limited computational and memory resources on most existing ultrasound scanners. To overcome such limits, we propose a multi-task learning framework to handle all the tasks by a single network. This network is integrated to perform view classification and landmark detection simultaneously; it is also equipped with global convolutional kernels, coordinate constraints, and a conditional adversarial module to leverage the performances. In an experimental study based on 187,219 ultrasound images, with the proposed simplified approach we achieve (1) view classification accuracy better than the agreement between two clinical experts and (2) landmark-based measurement errors on par with inter-user variability. The multi-task approach also benefits from sharing the feature extraction during the training process across all tasks and, as a result, outperforms the approaches that address each task individually. |
| Tasks | Multi-Task Learning |
| Published | 2018-05-25 |
| URL | http://arxiv.org/abs/1805.10376v2 |
| http://arxiv.org/pdf/1805.10376v2.pdf | |
| PWC | https://paperswithcode.com/paper/less-is-more-simultaneous-view-classification |
| Repo | |
| Framework | |
Enhanced Image Classification With Data Augmentation Using Position Coordinates
| Title | Enhanced Image Classification With Data Augmentation Using Position Coordinates |
| Authors | Avinash Kori, Ganapathy Krishnamurthi, Balaji Srinivasan |
| Abstract | In this paper we propose the use of image pixel position coordinate system to improve image classification accuracy in various applications. Specifically, we hypothesize that the use of pixel coordinates will lead to (a) Resolution invariant performance. Here, by resolution we mean the spacing between the pixels rather than the size of the image matrix. (b) Overall improvement in classification accuracy in comparison with network models trained without local pixel coordinates. This is due to position coordinates enabling the network to learn relationship between parts of objects, mimicking the human vision system. We demonstrate our hypothesis using empirical results and intuitive explanations of the feature maps learnt by deep neural networks. Specifically, our approach showed improvements in MNIST digit classification and beats state of the results on the SVHN database. We also show that the performance of our networks is unaffected despite training the same using blurred images of the MNIST database and predicting on the high resolution database. |
| Tasks | Data Augmentation, Image Classification |
| Published | 2018-01-05 |
| URL | http://arxiv.org/abs/1802.02183v1 |
| http://arxiv.org/pdf/1802.02183v1.pdf | |
| PWC | https://paperswithcode.com/paper/enhanced-image-classification-with-data |
| Repo | |
| Framework | |
Towards Automated Tuberculosis detection using Deep Learning
| Title | Towards Automated Tuberculosis detection using Deep Learning |
| Authors | Sonaal Kant, Muktabh Mayank Srivastava |
| Abstract | Tuberculosis(TB) in India is the world’s largest TB epidemic. TB leads to 480,000 deaths every year. Between the years 2006 and 2014, Indian economy lost US$340 Billion due to TB. This combined with the emergence of drug resistant bacteria in India makes the problem worse. The government of India has hence come up with a new strategy which requires a high-sensitivity microscopy based TB diagnosis mechanism. We propose a new Deep Neural Network based drug sensitive TB detection methodology with recall and precision of 83.78% and 67.55% respectively for bacillus detection. This method takes a microscopy image with proper zoom level as input and returns location of suspected TB germs as output. The high accuracy of our method gives it the potential to evolve into a high sensitivity system to diagnose TB when trained at scale. |
| Tasks | |
| Published | 2018-01-22 |
| URL | http://arxiv.org/abs/1801.07080v1 |
| http://arxiv.org/pdf/1801.07080v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-automated-tuberculosis-detection |
| Repo | |
| Framework | |
