Paper Group ANR 1109
A novel algorithm for segmentation of leukocytes in peripheral blood. Making Classical Machine Learning Pipelines Differentiable: A Neural Translation Approach. Efficient Adversarial Training with Transferable Adversarial Examples. Visual Rhythm Prediction with Feature-Aligning Network. Long-Range Indoor Navigation with PRM-RL. Quantum Expectation- …
A novel algorithm for segmentation of leukocytes in peripheral blood
| Title | A novel algorithm for segmentation of leukocytes in peripheral blood |
| Authors | Haichao Cao, Hong Liu, Enmin Song |
| Abstract | In the detection of anemia, leukemia and other blood diseases, the number and type of leukocytes are essential evaluation parameters. However, the conventional leukocyte counting method is not only quite time-consuming but also error-prone. Consequently, many automation methods are introduced for the diagnosis of medical images. It remains difficult to accurately extract related features and count the number of cells under the variable conditions such as background, staining method, staining degree, light conditions and so on. Therefore, in order to adapt to various complex situations, we consider RGB color space, HSI color space, and the linear combination of G, H and S components, and propose a fast and accurate algorithm for the segmentation of peripheral blood leukocytes in this paper. First, the nucleus of leukocyte was separated by using the stepwise averaging method. Then based on the interval-valued fuzzy sets, the cytoplasm of leukocyte was segmented by minimizing the fuzzy divergence. Next, post-processing was carried out by using the concave-convex iterative repair algorithm and the decision mechanism of candidate mask sets. Experimental results show that the proposed method outperforms the existing non-fuzzy sets methods. Among the methods based on fuzzy sets, the interval-valued fuzzy sets perform slightly better than interval-valued intuitionistic fuzzy sets and intuitionistic fuzzy sets. |
| Tasks | |
| Published | 2019-05-21 |
| URL | https://arxiv.org/abs/1905.08416v1 |
| https://arxiv.org/pdf/1905.08416v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-algorithm-for-segmentation-of |
| Repo | |
| Framework | |
Making Classical Machine Learning Pipelines Differentiable: A Neural Translation Approach
| Title | Making Classical Machine Learning Pipelines Differentiable: A Neural Translation Approach |
| Authors | Gyeong-In Yu, Saeed Amizadeh, Sehoon Kim, Artidoro Pagnoni, Byung-Gon Chun, Markus Weimer, Matteo Interlandi |
| Abstract | Classical Machine Learning (ML) pipelines often comprise of multiple ML models where models, within a pipeline, are trained in isolation. Conversely, when training neural network models, layers composing the neural models are simultaneously trained using backpropagation. We argue that the isolated training scheme of ML pipelines is sub-optimal, since it cannot jointly optimize multiple components. To this end, we propose a framework that translates a pre-trained ML pipeline into a neural network and fine-tunes the ML models within the pipeline jointly using backpropagation. Our experiments show that fine-tuning of the translated pipelines is a promising technique able to increase the final accuracy. |
| Tasks | |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.03822v2 |
| https://arxiv.org/pdf/1906.03822v2.pdf | |
| PWC | https://paperswithcode.com/paper/making-classical-machine-learning-pipelines |
| Repo | |
| Framework | |
Efficient Adversarial Training with Transferable Adversarial Examples
| Title | Efficient Adversarial Training with Transferable Adversarial Examples |
| Authors | Haizhong Zheng, Ziqi Zhang, Juncheng Gu, Honglak Lee, Atul Prakash |
| Abstract | Adversarial training is an effective defense method to protect classification models against adversarial attacks. However, one limitation of this approach is that it can require orders of magnitude additional training time due to high cost of generating strong adversarial examples during training. In this paper, we first show that there is high transferability between models from neighboring epochs in the same training process, i.e., adversarial examples from one epoch continue to be adversarial in subsequent epochs. Leveraging this property, we propose a novel method, Adversarial Training with Transferable Adversarial Examples (ATTA), that can enhance the robustness of trained models and greatly improve the training efficiency by accumulating adversarial perturbations through epochs. Compared to state-of-the-art adversarial training methods, ATTA enhances adversarial accuracy by up to 7.2% on CIFAR10 and requires 12~14x less training time on MNIST and CIFAR10 datasets with comparable model robustness. |
| Tasks | |
| Published | 2019-12-27 |
| URL | https://arxiv.org/abs/1912.11969v1 |
| https://arxiv.org/pdf/1912.11969v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-adversarial-training-with |
| Repo | |
| Framework | |
Visual Rhythm Prediction with Feature-Aligning Network
| Title | Visual Rhythm Prediction with Feature-Aligning Network |
| Authors | Yutong Xie, Haiyang Wang, Yan Hao, Zihao Xu |
| Abstract | In this paper, we propose a data-driven visual rhythm prediction method, which overcomes the previous works’ deficiency that predictions are made primarily by human-crafted hard rules. In our approach, we first extract features including original frames and their residuals, optical flow, scene change, and body pose. These visual features will be next taken into an end-to-end neural network as inputs. Here we observe that there are some slight misaligning between features over the timeline and assume that this is due to the distinctions between how different features are computed. To solve this problem, the extracted features are aligned by an elaborately designed layer, which can also be applied to other models suffering from mismatched features, and boost performance. Then these aligned features are fed into sequence labeling layers implemented with BiLSTM and CRF to predict the onsets. Due to the lack of existing public training and evaluation set, we experiment on a dataset constructed by ourselves based on professionally edited Music Videos (MVs), and the F1 score of our approach reaches 79.6. |
| Tasks | Optical Flow Estimation |
| Published | 2019-01-29 |
| URL | http://arxiv.org/abs/1901.10163v1 |
| http://arxiv.org/pdf/1901.10163v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-rhythm-prediction-with-feature |
| Repo | |
| Framework | |
Long-Range Indoor Navigation with PRM-RL
| Title | Long-Range Indoor Navigation with PRM-RL |
| Authors | Anthony Francis, Aleksandra Faust, Hao-Tien Lewis Chiang, Jasmine Hsu, J. Chase Kew, Marek Fiser, Tsang-Wei Edward Lee |
| Abstract | Long-range indoor navigation requires guiding robots with noisy sensors and controls through cluttered environments along paths that span a variety of buildings. We achieve this with PRM-RL, a hierarchical robot navigation method in which reinforcement learning agents that map noisy sensors to robot controls learn to solve short-range obstacle avoidance tasks, and then sampling-based planners map where these agents can reliably navigate in simulation; these roadmaps and agents are then deployed on robots, guiding them along the shortest path where the agents are likely to succeed. Here we use Probabilistic Roadmaps (PRMs) as the sampling-based planner, and AutoRL as the reinforcement learning method in the indoor navigation context. We evaluate the method in simulation for kinematic differential drive and kinodynamic car-like robots in several environments, and on differential-drive robots at three physical sites. Our results show PRM-RL with AutoRL is more successful than several baselines, is robust to noise, and can guide robots over hundreds of meters in the face of noise and obstacles in both simulation and on robots, including over 5.8 kilometers of physical robot navigation. Video: https://youtu.be/xN-OWX5gKvQ |
| Tasks | Robot Navigation |
| Published | 2019-02-25 |
| URL | https://arxiv.org/abs/1902.09458v2 |
| https://arxiv.org/pdf/1902.09458v2.pdf | |
| PWC | https://paperswithcode.com/paper/long-range-indoor-navigation-with-prm-rl |
| Repo | |
| Framework | |
Quantum Expectation-Maximization Algorithm
| Title | Quantum Expectation-Maximization Algorithm |
| Authors | Hideyuki Miyahara, Kazuyuki Aihara, Wolfgang Lechner |
| Abstract | Clustering algorithms are a cornerstone of machine learning applications. Recently, a quantum algorithm for clustering based on the k-means algorithm has been proposed by Kerenidis, Landman, Luongo and Prakash. Based on their work, we propose a quantum expectation-maximization (EM) algorithm for Gaussian mixture models (GMMs). The robustness and quantum speedup of the algorithm is demonstrated. We also show numerically the advantage of GMM over k-means for non-trivial cluster data. |
| Tasks | |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.06655v1 |
| https://arxiv.org/pdf/1908.06655v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-expectation-maximization-algorithm |
| Repo | |
| Framework | |
Exogenous Rewards for Promoting Cooperation in Scale-Free Networks
| Title | Exogenous Rewards for Promoting Cooperation in Scale-Free Networks |
| Authors | Theodor Cimpeanu, The Anh Han, Francisco C. Santos |
| Abstract | The design of mechanisms that encourage pro-social behaviours in populations of self-regarding agents is recognised as a major theoretical challenge within several areas of social, life and engineering sciences. When interference from external parties is considered, several heuristics have been identified as capable of engineering a desired collective behaviour at a minimal cost. However, these studies neglect the diverse nature of contexts and social structures that characterise real-world populations. Here we analyse the impact of diversity by means of scale-free interaction networks with high and low levels of clustering, and test various interference paradigms using simulations of agents facing a cooperative dilemma. Our results show that interference on scale-free networks is not trivial and that distinct levels of clustering react differently to each interference strategy. As such, we argue that no tailored response fits all scale-free networks and present which strategies are more efficient at fostering cooperation in both types of networks. Finally, we discuss the pitfalls of considering reckless interference strategies. |
| Tasks | |
| Published | 2019-05-13 |
| URL | http://arxiv.org/abs/1905.04964v1 |
| http://arxiv.org/pdf/1905.04964v1.pdf | |
| PWC | https://paperswithcode.com/paper/exogenous-rewards-for-promoting-cooperation |
| Repo | |
| Framework | |
Localization of Fetal Head in Ultrasound Images by Multiscale View and Deep Neural Networks
| Title | Localization of Fetal Head in Ultrasound Images by Multiscale View and Deep Neural Networks |
| Authors | Zahra Sobhaninia, Ali Emami, Nader Karimi, Shadrokh Samavi |
| Abstract | One of the routine examinations that are used for prenatal care in many countries is ultrasound imaging. This procedure provides various information about fetus health and development, the progress of the pregnancy and, the baby’s due date. Some of the biometric parameters of the fetus, like fetal head circumference (HC), must be measured to check the fetus’s health and growth. In this paper, we investigated the effects of using multi-scale inputs in the network. We also propose a light convolutional neural network for automatic HC measurement. Experimental results on an ultrasound dataset of the fetus in different trimesters of pregnancy show that the segmentation accuracy and HC evaluations performed by a light convolutional neural network are comparable to deep convolutional neural networks. The proposed network has fewer parameters and requires less training time. |
| Tasks | |
| Published | 2019-11-03 |
| URL | https://arxiv.org/abs/1911.00908v1 |
| https://arxiv.org/pdf/1911.00908v1.pdf | |
| PWC | https://paperswithcode.com/paper/localization-of-fetal-head-in-ultrasound |
| Repo | |
| Framework | |
Fluorescence Image Histology Pattern Transformation using Image Style Transfer
| Title | Fluorescence Image Histology Pattern Transformation using Image Style Transfer |
| Authors | Mohammadhassan Izadyyazdanabadi, Evgenii Belykh, Xiaochun Zhao, Leandro Borba Moreira, Sirin Gandhi, Claudio Cavallo, Jennifer Eschbacher, Peter Nakaji, Mark C. Preul, Yezhou Yang |
| Abstract | Confocal laser endomicroscopy (CLE) allow on-the-fly in vivo intraoperative imaging in a discreet field of view, especially for brain tumors, rather than extracting tissue for examination ex vivo with conventional light microscopy. Fluorescein sodium-driven CLE imaging is more interactive, rapid, and portable than conventional hematoxylin and eosin (H&E)-staining. However, it has several limitations: CLE images may be contaminated with artifacts (motion, red blood cells, noise), and neuropathologists are mainly trained on colorful stained histology slides like H&E while the CLE images are gray. To improve the diagnostic quality of CLE, we used a micrograph of an H&E slide from a glioma tumor biopsy and image style transfer, a neural network method for integrating the content and style of two images. This was done through minimizing the deviation of the target image from both the content (CLE) and style (H&E) images. The style transferred images were assessed and compared to conventional H&E histology by neurosurgeons and a neuropathologist who then validated the quality enhancement in 100 pairs of original and transformed images. Average reviewers’ score on test images showed 84 out of 100 transformed images had fewer artifacts and more noticeable critical structures compared to their original CLE form. By providing images that are more interpretable than the original CLE images and more rapidly acquired than H&E slides, the style transfer method allows a real-time, cellular-level tissue examination using CLE technology that closely resembles the conventional appearance of H&E staining and may yield better diagnostic recognition than original CLE grayscale images. |
| Tasks | Style Transfer |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.06442v1 |
| https://arxiv.org/pdf/1905.06442v1.pdf | |
| PWC | https://paperswithcode.com/paper/fluorescence-image-histology-pattern |
| Repo | |
| Framework | |
The Value Function Polytope in Reinforcement Learning
| Title | The Value Function Polytope in Reinforcement Learning |
| Authors | Robert Dadashi, Adrien Ali Taïga, Nicolas Le Roux, Dale Schuurmans, Marc G. Bellemare |
| Abstract | We establish geometric and topological properties of the space of value functions in finite state-action Markov decision processes. Our main contribution is the characterization of the nature of its shape: a general polytope (Aigner et al., 2010). To demonstrate this result, we exhibit several properties of the structural relationship between policies and value functions including the line theorem, which shows that the value functions of policies constrained on all but one state describe a line segment. Finally, we use this novel perspective to introduce visualizations to enhance the understanding of the dynamics of reinforcement learning algorithms. |
| Tasks | |
| Published | 2019-01-31 |
| URL | https://arxiv.org/abs/1901.11524v3 |
| https://arxiv.org/pdf/1901.11524v3.pdf | |
| PWC | https://paperswithcode.com/paper/the-value-function-polytope-in-reinforcement |
| Repo | |
| Framework | |
Programming multi-level quantum gates in disordered computing reservoirs via machine learning and TensorFlow
| Title | Programming multi-level quantum gates in disordered computing reservoirs via machine learning and TensorFlow |
| Authors | Giulia Marcucci, Davide Pierangeli, Pepijn Pinkse, Mehul Malik, Claudio Conti |
| Abstract | Novel machine learning computational tools open new perspectives for quantum information systems. Here we adopt the open-source programming library TensorFlow to design multi-level quantum gates including a computing reservoir represented by a random unitary matrix. In optics, the reservoir is a disordered medium or a multi-modal fiber. We show that trainable operators at the input and the readout enable one to realize multi-level gates. We study various qudit gates, including the scaling properties of the algorithms with the size of the reservoir. Despite an initial low slop learning stage, TensorFlow turns out to be an extremely versatile resource for designing gates with complex media, including different models that use spatial light modulators with quantized modulation levels. |
| Tasks | |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.05264v3 |
| https://arxiv.org/pdf/1905.05264v3.pdf | |
| PWC | https://paperswithcode.com/paper/programming-multi-level-quantum-gates-in |
| Repo | |
| Framework | |
Data augmentation in microscopic images for material data mining
| Title | Data augmentation in microscopic images for material data mining |
| Authors | Boyuan Ma, Xiaoyan Wei, Chuni Liu, Xiaojuan Ban, Haiyou Huang, Hao Wang, Weihua Xue, Stephen Wu, Mingfei Gao, Qing Shen, Adnan Omer Abuassba, Haokai Shen, Yanjing Su |
| Abstract | Recent progress in material data mining has been driven by high-capacity models trained on large datasets. However, collecting experimental data (real data) has been extremely costly since the amount of human effort and expertise required. Here, we develop a novel transfer learning strategy to address small or insufficient data problem. This strategy realizes the fusion of real and simulated data, and the augmentation of training data in data mining procedure. For a specific task of image segmentation, this strategy can generate synthetic images by fusing physical mechanism of simulated images and “image style” of real images. The result shows that the model trained with the acquired synthetic images and 35% of the real images outperforms the model trained on all real images. As the time required to generate synthetic data is almost negligible, this strategy is able to reduce the time cost of real data preparation by roughly 65%. |
| Tasks | Data Augmentation, Semantic Segmentation, Style Transfer, Transfer Learning |
| Published | 2019-05-12 |
| URL | https://arxiv.org/abs/1905.04711v3 |
| https://arxiv.org/pdf/1905.04711v3.pdf | |
| PWC | https://paperswithcode.com/paper/style-transfer-based-data-augmentation-in |
| Repo | |
| Framework | |
GOT: An Optimal Transport framework for Graph comparison
| Title | GOT: An Optimal Transport framework for Graph comparison |
| Authors | Hermina Petric Maretic, Mireille EL Gheche, Giovanni Chierchia, Pascal Frossard |
| Abstract | We present a novel framework based on optimal transport for the challenging problem of comparing graphs. Specifically, we exploit the probabilistic distribution of smooth graph signals defined with respect to the graph topology. This allows us to derive an explicit expression of the Wasserstein distance between graph signal distributions in terms of the graph Laplacian matrices. This leads to a structurally meaningful measure for comparing graphs, which is able to take into account the global structure of graphs, while most other measures merely observe local changes independently. Our measure is then used for formulating a new graph alignment problem, whose objective is to estimate the permutation that minimizes the distance between two graphs. We further propose an efficient stochastic algorithm based on Bayesian exploration to accommodate for the non-convexity of the graph alignment problem. We finally demonstrate the performance of our novel framework on different tasks like graph alignment, graph classification and graph signal prediction, and we show that our method leads to significant improvement with respect to the-state-of-art algorithms. |
| Tasks | Graph Classification |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.02085v2 |
| https://arxiv.org/pdf/1906.02085v2.pdf | |
| PWC | https://paperswithcode.com/paper/got-an-optimal-transport-framework-for-graph |
| Repo | |
| Framework | |
Transferring Multiscale Map Styles Using Generative Adversarial Networks
| Title | Transferring Multiscale Map Styles Using Generative Adversarial Networks |
| Authors | Yuhao Kang, Song Gao, Robert E. Roth |
| Abstract | The advancement of the Artificial Intelligence (AI) technologies makes it possible to learn stylistic design criteria from existing maps or other visual art and transfer these styles to make new digital maps. In this paper, we propose a novel framework using AI for map style transfer applicable across multiple map scales. Specifically, we identify and transfer the stylistic elements from a target group of visual examples, including Google Maps, OpenStreetMap, and artistic paintings, to unstylized GIS vector data through two generative adversarial network (GAN) models. We then train a binary classifier based on a deep convolutional neural network to evaluate whether the transfer styled map images preserve the original map design characteristics. Our experiment results show that GANs have a great potential for multiscale map style transferring, but many challenges remain requiring future research. |
| Tasks | Style Transfer |
| Published | 2019-05-06 |
| URL | https://arxiv.org/abs/1905.02200v2 |
| https://arxiv.org/pdf/1905.02200v2.pdf | |
| PWC | https://paperswithcode.com/paper/transferring-multiscale-map-styles-using |
| Repo | |
| Framework | |
TunaGAN: Interpretable GAN for Smart Editing
| Title | TunaGAN: Interpretable GAN for Smart Editing |
| Authors | Weiquan Mao, Beicheng Lou, Jiyao Yuan |
| Abstract | In this paper, we introduce a tunable generative adversary network (TunaGAN) that uses an auxiliary network on top of existing generator networks (Style-GAN) to modify high-resolution face images according to user’s high-level instructions, with good qualitative and quantitative performance. To optimize for feature disentanglement, we also investigate two different latent space that could be traversed for modification. The problem of mode collapse is characterized in detail for model robustness. This work could be easily extended to content-aware image editor based on other GANs and provide insight on mode collapse problems in more general settings. |
| Tasks | |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.06163v1 |
| https://arxiv.org/pdf/1908.06163v1.pdf | |
| PWC | https://paperswithcode.com/paper/tunagan-interpretable-gan-for-smart-editing |
| Repo | |
| Framework | |
