Paper Group ANR 252
Maximum Selection and Ranking under Noisy Comparisons. DeepBrain: Functional Representation of Neural In-Situ Hybridization Images for Gene Ontology Classification Using Deep Convolutional Autoencoders. SeeThrough: Finding Chairs in Heavily Occluded Indoor Scene Images. Deeply-Supervised CNN for Prostate Segmentation. Evaluation of PPG Biometrics f …
Maximum Selection and Ranking under Noisy Comparisons
| Title | Maximum Selection and Ranking under Noisy Comparisons |
| Authors | Moein Falahatgar, Alon Orlitsky, Venkatadheeraj Pichapati, Ananda Theertha Suresh |
| Abstract | We consider $(\epsilon,\delta)$-PAC maximum-selection and ranking for general probabilistic models whose comparisons probabilities satisfy strong stochastic transitivity and stochastic triangle inequality. Modifying the popular knockout tournament, we propose a maximum-selection algorithm that uses $\mathcal{O}\left(\frac{n}{\epsilon^2}\log \frac{1}{\delta}\right)$ comparisons, a number tight up to a constant factor. We then derive a general framework that improves the performance of many ranking algorithms, and combine it with merge sort and binary search to obtain a ranking algorithm that uses $\mathcal{O}\left(\frac{n\log n (\log \log n)^3}{\epsilon^2}\right)$ comparisons for any $\delta\ge\frac1n$, a number optimal up to a $(\log \log n)^3$ factor. |
| Tasks | |
| Published | 2017-05-15 |
| URL | http://arxiv.org/abs/1705.05366v1 |
| http://arxiv.org/pdf/1705.05366v1.pdf | |
| PWC | https://paperswithcode.com/paper/maximum-selection-and-ranking-under-noisy |
| Repo | |
| Framework | |
DeepBrain: Functional Representation of Neural In-Situ Hybridization Images for Gene Ontology Classification Using Deep Convolutional Autoencoders
| Title | DeepBrain: Functional Representation of Neural In-Situ Hybridization Images for Gene Ontology Classification Using Deep Convolutional Autoencoders |
| Authors | Ido Cohen, Eli David, Nathan S. Netanyahu, Noa Liscovitch, Gal Chechik |
| Abstract | This paper presents a novel deep learning-based method for learning a functional representation of mammalian neural images. The method uses a deep convolutional denoising autoencoder (CDAE) for generating an invariant, compact representation of in situ hybridization (ISH) images. While most existing methods for bio-imaging analysis were not developed to handle images with highly complex anatomical structures, the results presented in this paper show that functional representation extracted by CDAE can help learn features of functional gene ontology categories for their classification in a highly accurate manner. Using this CDAE representation, our method outperforms the previous state-of-the-art classification rate, by improving the average AUC from 0.92 to 0.98, i.e., achieving 75% reduction in error. The method operates on input images that were downsampled significantly with respect to the original ones to make it computationally feasible. |
| Tasks | Denoising |
| Published | 2017-11-27 |
| URL | http://arxiv.org/abs/1711.09663v1 |
| http://arxiv.org/pdf/1711.09663v1.pdf | |
| PWC | https://paperswithcode.com/paper/deepbrain-functional-representation-of-neural |
| Repo | |
| Framework | |
SeeThrough: Finding Chairs in Heavily Occluded Indoor Scene Images
| Title | SeeThrough: Finding Chairs in Heavily Occluded Indoor Scene Images |
| Authors | Moos Hueting, Pradyumna Reddy, Vladimir Kim, Ersin Yumer, Nathan Carr, Niloy Mitra |
| Abstract | Discovering 3D arrangements of objects from single indoor images is important given its many applications including interior design, content creation, etc. Although heavily researched in the recent years, existing approaches break down under medium or heavy occlusion as the core object detection module starts failing in absence of directly visible cues. Instead, we take into account holistic contextual 3D information, exploiting the fact that objects in indoor scenes co-occur mostly in typical near-regular configurations. First, we use a neural network trained on real indoor annotated images to extract 2D keypoints, and feed them to a 3D candidate object generation stage. Then, we solve a global selection problem among these 3D candidates using pairwise co-occurrence statistics discovered from a large 3D scene database. We iterate the process allowing for candidates with low keypoint response to be incrementally detected based on the location of the already discovered nearby objects. Focusing on chairs, we demonstrate significant performance improvement over combinations of state-of-the-art methods, especially for scenes with moderately to severely occluded objects. |
| Tasks | Object Detection |
| Published | 2017-10-28 |
| URL | http://arxiv.org/abs/1710.10473v2 |
| http://arxiv.org/pdf/1710.10473v2.pdf | |
| PWC | https://paperswithcode.com/paper/seethrough-finding-chairs-in-heavily-occluded |
| Repo | |
| Framework | |
Deeply-Supervised CNN for Prostate Segmentation
| Title | Deeply-Supervised CNN for Prostate Segmentation |
| Authors | Qikui Zhu, Bo Du, Baris Turkbey, Peter L . Choyke, Pingkun Yan |
| Abstract | Prostate segmentation from Magnetic Resonance (MR) images plays an important role in image guided interven- tion. However, the lack of clear boundary specifically at the apex and base, and huge variation of shape and texture between the images from different patients make the task very challenging. To overcome these problems, in this paper, we propose a deeply supervised convolutional neural network (CNN) utilizing the convolutional information to accurately segment the prostate from MR images. The proposed model can effectively detect the prostate region with additional deeply supervised layers compared with other approaches. Since some information will be abandoned after convolution, it is necessary to pass the features extracted from early stages to later stages. The experimental results show that significant segmentation accuracy improvement has been achieved by our proposed method compared to other reported approaches. |
| Tasks | |
| Published | 2017-03-22 |
| URL | http://arxiv.org/abs/1703.07523v3 |
| http://arxiv.org/pdf/1703.07523v3.pdf | |
| PWC | https://paperswithcode.com/paper/deeply-supervised-cnn-for-prostate |
| Repo | |
| Framework | |
Evaluation of PPG Biometrics for Authentication in different states
| Title | Evaluation of PPG Biometrics for Authentication in different states |
| Authors | Umang Yadav, Sherif N Abbas, Dimitrios Hatzinakos |
| Abstract | Amongst all medical biometric traits, Photoplethysmograph (PPG) is the easiest to acquire. PPG records the blood volume change with just combination of Light Emitting Diode and Photodiode from any part of the body. With IoT and smart homes’ penetration, PPG recording can easily be integrated with other vital wearable devices. PPG represents peculiarity of hemodynamics and cardiovascular system for each individual. This paper presents non-fiducial method for PPG based biometric authentication. Being a physiological signal, PPG signal alters with physical/mental stress and time. For robustness, these variations cannot be ignored. While, most of the previous works focused only on single session, this paper demonstrates extensive performance evaluation of PPG biometrics against single session data, different emotions, physical exercise and time-lapse using Continuous Wavelet Transform (CWT) and Direct Linear Discriminant Analysis (DLDA). When evaluated on different states and datasets, equal error rate (EER) of $0.5%$-$6%$ was achieved for $45$-$60$s average training time. Our CWT/DLDA based technique outperformed all other dimensionality reduction techniques and previous work. |
| Tasks | Dimensionality Reduction |
| Published | 2017-12-22 |
| URL | http://arxiv.org/abs/1712.08583v1 |
| http://arxiv.org/pdf/1712.08583v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluation-of-ppg-biometrics-for |
| Repo | |
| Framework | |
Automatic Construction of Real-World Datasets for 3D Object Localization using Two Cameras
| Title | Automatic Construction of Real-World Datasets for 3D Object Localization using Two Cameras |
| Authors | Joris Guérin, Olivier Gibaru, Eric Nyiri, Stéphane Thiery |
| Abstract | Unlike classification, position labels cannot be assigned manually by humans. For this reason, generating supervision for precise object localization is a hard task. This paper details a method to create large datasets for 3D object localization, with real world images, using an industrial robot to generate position labels. By knowledge of the geometry of the robot, we are able to automatically synchronize the images of the two cameras and the object 3D position. We applied it to generate a screw-driver localization dataset with stereo images, using a KUKA LBR iiwa robot. This dataset could then be used to train a CNN regressor to learn end-to-end stereo object localization from a set of two standard uncalibrated cameras. |
| Tasks | Object Localization |
| Published | 2017-07-10 |
| URL | http://arxiv.org/abs/1707.02978v3 |
| http://arxiv.org/pdf/1707.02978v3.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-construction-of-real-world-datasets |
| Repo | |
| Framework | |
Layer-wise Learning of Stochastic Neural Networks with Information Bottleneck
| Title | Layer-wise Learning of Stochastic Neural Networks with Information Bottleneck |
| Authors | Thanh T. Nguyen, Jaesik Choi |
| Abstract | Information Bottleneck (IB) is a generalization of rate-distortion theory that naturally incorporates compression and relevance trade-offs for learning. Though the original IB has been extensively studied, there has not been much understanding of multiple bottlenecks which better fit in the context of neural networks. In this work, we propose Information Multi-Bottlenecks (IMBs) as an extension of IB to multiple bottlenecks which has a direct application to training neural networks by considering layers as multiple bottlenecks and weights as parameterized encoders and decoders. We show that the multiple optimality of IMB is not simultaneously achievable for stochastic encoders. We thus propose a simple compromised scheme of IMB which in turn generalizes maximum likelihood estimate (MLE) principle in the context of stochastic neural networks. We demonstrate the effectiveness of IMB on classification tasks and adversarial robustness in MNIST and CIFAR10. |
| Tasks | |
| Published | 2017-12-04 |
| URL | https://arxiv.org/abs/1712.01272v6 |
| https://arxiv.org/pdf/1712.01272v6.pdf | |
| PWC | https://paperswithcode.com/paper/layer-wise-learning-of-stochastic-neural |
| Repo | |
| Framework | |
Posterior Sampling for Large Scale Reinforcement Learning
| Title | Posterior Sampling for Large Scale Reinforcement Learning |
| Authors | Georgios Theocharous, Zheng Wen, Yasin Abbasi-Yadkori, Nikos Vlassis |
| Abstract | We propose a practical non-episodic PSRL algorithm that unlike recent state-of-the-art PSRL algorithms uses a deterministic, model-independent episode switching schedule. Our algorithm termed deterministic schedule PSRL (DS-PSRL) is efficient in terms of time, sample, and space complexity. We prove a Bayesian regret bound under mild assumptions. Our result is more generally applicable to multiple parameters and continuous state action problems. We compare our algorithm with state-of-the-art PSRL algorithms on standard discrete and continuous problems from the literature. Finally, we show how the assumptions of our algorithm satisfy a sensible parametrization for a large class of problems in sequential recommendations. |
| Tasks | |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.07979v3 |
| http://arxiv.org/pdf/1711.07979v3.pdf | |
| PWC | https://paperswithcode.com/paper/posterior-sampling-for-large-scale |
| Repo | |
| Framework | |
A Random Sample Partition Data Model for Big Data Analysis
| Title | A Random Sample Partition Data Model for Big Data Analysis |
| Authors | Salman Salloum, Yulin He, Joshua Zhexue Huang, Xiaoliang Zhang, Tamer Z. Emara, Chenghao Wei, Heping He |
| Abstract | Big data sets must be carefully partitioned into statistically similar data subsets that can be used as representative samples for big data analysis tasks. In this paper, we propose the random sample partition (RSP) data model to represent a big data set as a set of non-overlapping data subsets, called RSP data blocks, where each RSP data block has a probability distribution similar to the whole big data set. Under this data model, efficient block level sampling is used to randomly select RSP data blocks, replacing expensive record level sampling to select sample data from a big distributed data set on a computing cluster. We show how RSP data blocks can be employed to estimate statistics of a big data set and build models which are equivalent to those built from the whole big data set. In this approach, analysis of a big data set becomes analysis of few RSP data blocks which have been generated in advance on the computing cluster. Therefore, the new method for data analysis based on RSP data blocks is scalable to big data. |
| Tasks | |
| Published | 2017-12-12 |
| URL | http://arxiv.org/abs/1712.04146v2 |
| http://arxiv.org/pdf/1712.04146v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-random-sample-partition-data-model-for-big |
| Repo | |
| Framework | |
Lung Cancer Screening Using Adaptive Memory-Augmented Recurrent Networks
| Title | Lung Cancer Screening Using Adaptive Memory-Augmented Recurrent Networks |
| Authors | Aryan Mobiny, Supratik Moulik, Hien Van Nguyen |
| Abstract | In this paper, we investigate the effectiveness of deep learning techniques for lung nodule classification in computed tomography scans. Using less than 10,000 training examples, our deep networks perform two times better than a standard radiology software. Visualization of the networks’ neurons reveals semantically meaningful features that are consistent with the clinical knowledge and radiologists’ perception. Our paper also proposes a novel framework for rapidly adapting deep networks to the radiologists’ feedback, or change in the data due to the shift in sensor’s resolution or patient population. The classification accuracy of our approach remains above 80% while popular deep networks’ accuracy is around chance. Finally, we provide in-depth analysis of our framework by asking a radiologist to examine important networks’ features and perform blind re-labeling of networks’ mistakes. |
| Tasks | Lung Nodule Classification |
| Published | 2017-10-11 |
| URL | http://arxiv.org/abs/1710.05719v2 |
| http://arxiv.org/pdf/1710.05719v2.pdf | |
| PWC | https://paperswithcode.com/paper/lung-cancer-screening-using-adaptive-memory |
| Repo | |
| Framework | |
Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention
| Title | Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention |
| Authors | Marcella Cornia, Lorenzo Baraldi, Giuseppe Serra, Rita Cucchiara |
| Abstract | Image captioning has been recently gaining a lot of attention thanks to the impressive achievements shown by deep captioning architectures, which combine Convolutional Neural Networks to extract image representations, and Recurrent Neural Networks to generate the corresponding captions. At the same time, a significant research effort has been dedicated to the development of saliency prediction models, which can predict human eye fixations. Even though saliency information could be useful to condition an image captioning architecture, by providing an indication of what is salient and what is not, research is still struggling to incorporate these two techniques. In this work, we propose an image captioning approach in which a generative recurrent neural network can focus on different parts of the input image during the generation of the caption, by exploiting the conditioning given by a saliency prediction model on which parts of the image are salient and which are contextual. We show, through extensive quantitative and qualitative experiments on large scale datasets, that our model achieves superior performances with respect to captioning baselines with and without saliency, and to different state of the art approaches combining saliency and captioning. |
| Tasks | Image Captioning, Saliency Prediction |
| Published | 2017-06-26 |
| URL | http://arxiv.org/abs/1706.08474v4 |
| http://arxiv.org/pdf/1706.08474v4.pdf | |
| PWC | https://paperswithcode.com/paper/paying-more-attention-to-saliency-image |
| Repo | |
| Framework | |
Fullie and Wiselie: A Dual-Stream Recurrent Convolutional Attention Model for Activity Recognition
| Title | Fullie and Wiselie: A Dual-Stream Recurrent Convolutional Attention Model for Activity Recognition |
| Authors | Kaixuan Chen, Lina Yao, Tao Gu, Zhiwen Yu, Xianzhi Wang, Dalin Zhang |
| Abstract | Multimodal features play a key role in wearable sensor based Human Activity Recognition (HAR). Selecting the most salient features adaptively is a promising way to maximize the effectiveness of multimodal sensor data. In this regard, we propose a “collect fully and select wisely (Fullie and Wiselie)” principle as well as a dual-stream recurrent convolutional attention model, Recurrent Attention and Activity Frame (RAAF), to improve the recognition performance. We first collect modality features and the relations between each pair of features to generate activity frames, and then introduce an attention mechanism to select the most prominent regions from activity frames precisely. The selected frames not only maximize the utilization of valid features but also reduce the number of features to be computed effectively. We further analyze the hyper-parameters, accuracy, interpretability, and annotation dependency of the proposed model based on extensive experiments. The results show that RAAF achieves competitive performance on two benchmarked datasets and works well in real life scenarios. |
| Tasks | Activity Recognition, Human Activity Recognition |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.07661v1 |
| http://arxiv.org/pdf/1711.07661v1.pdf | |
| PWC | https://paperswithcode.com/paper/fullie-and-wiselie-a-dual-stream-recurrent |
| Repo | |
| Framework | |
MUSE: Modularizing Unsupervised Sense Embeddings
| Title | MUSE: Modularizing Unsupervised Sense Embeddings |
| Authors | Guang-He Lee, Yun-Nung Chen |
| Abstract | This paper proposes to address the word sense ambiguity issue in an unsupervised manner, where word sense representations are learned along a word sense selection mechanism given contexts. Prior work focused on designing a single model to deliver both mechanisms, and thus suffered from either coarse-grained representation learning or inefficient sense selection. The proposed modular approach, MUSE, implements flexible modules to optimize distinct mechanisms, achieving the first purely sense-level representation learning system with linear-time sense selection. We leverage reinforcement learning to enable joint training on the proposed modules, and introduce various exploration techniques on sense selection for better robustness. The experiments on benchmark data show that the proposed approach achieves the state-of-the-art performance on synonym selection as well as on contextual word similarities in terms of MaxSimC. |
| Tasks | Representation Learning |
| Published | 2017-04-15 |
| URL | http://arxiv.org/abs/1704.04601v2 |
| http://arxiv.org/pdf/1704.04601v2.pdf | |
| PWC | https://paperswithcode.com/paper/muse-modularizing-unsupervised-sense |
| Repo | |
| Framework | |
mAnI: Movie Amalgamation using Neural Imitation
| Title | mAnI: Movie Amalgamation using Neural Imitation |
| Authors | Naveen Panwar, Shreya Khare, Neelamadhav Gantayat, Rahul Aralikatte, Senthil Mani, Anush Sankaran |
| Abstract | Cross-modal data retrieval has been the basis of various creative tasks performed by Artificial Intelligence (AI). One such highly challenging task for AI is to convert a book into its corresponding movie, which most of the creative film makers do as of today. In this research, we take the first step towards it by visualizing the content of a book using its corresponding movie visuals. Given a set of sentences from a book or even a fan-fiction written in the same universe, we employ deep learning models to visualize the input by stitching together relevant frames from the movie. We studied and compared three different types of setting to match the book with the movie content: (i) Dialog model: using only the dialog from the movie, (ii) Visual model: using only the visual content from the movie, and (iii) Hybrid model: using the dialog and the visual content from the movie. Experiments on the publicly available MovieBook dataset shows the effectiveness of the proposed models. |
| Tasks | |
| Published | 2017-08-16 |
| URL | http://arxiv.org/abs/1708.04923v1 |
| http://arxiv.org/pdf/1708.04923v1.pdf | |
| PWC | https://paperswithcode.com/paper/mani-movie-amalgamation-using-neural |
| Repo | |
| Framework | |
Human Activity Recognition Using Robust Adaptive Privileged Probabilistic Learning
| Title | Human Activity Recognition Using Robust Adaptive Privileged Probabilistic Learning |
| Authors | Michalis Vrigkas, Evangelos Kazakos, Christophoros Nikou, Ioannis A. Kakadiaris |
| Abstract | In this work, a novel method based on the learning using privileged information (LUPI) paradigm for recognizing complex human activities is proposed that handles missing information during testing. We present a supervised probabilistic approach that integrates LUPI into a hidden conditional random field (HCRF) model. The proposed model is called HCRF+ and may be trained using both maximum likelihood and maximum margin approaches. It employs a self-training technique for automatic estimation of the regularization parameters of the objective functions. Moreover, the method provides robustness to outliers (such as noise or missing data) by modeling the conditional distribution of the privileged information by a Student’s \textit{t}-density function, which is naturally integrated into the HCRF+ framework. Different forms of privileged information were investigated. The proposed method was evaluated using four challenging publicly available datasets and the experimental results demonstrate its effectiveness with respect to the-state-of-the-art in the LUPI framework using both hand-crafted features and features extracted from a convolutional neural network. |
| Tasks | Activity Recognition, Human Activity Recognition |
| Published | 2017-09-19 |
| URL | http://arxiv.org/abs/1709.06447v1 |
| http://arxiv.org/pdf/1709.06447v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-activity-recognition-using-robust |
| Repo | |
| Framework | |
