Paper Group ANR 1733
Automated Analysis of Femoral Artery Calcification Using Machine Learning Techniques. DeepLine: AutoML Tool for Pipelines Generation using Deep Reinforcement Learning and Hierarchical Actions Filtering. Unsupervised Medical Image Translation Using Cycle-MedGAN. Privacy Attacks on Network Embeddings. Shenjing: A low power reconfigurable neuromorphic …
Automated Analysis of Femoral Artery Calcification Using Machine Learning Techniques
| Title | Automated Analysis of Femoral Artery Calcification Using Machine Learning Techniques |
| Authors | Liang Zhao, Brendan Odigwe, Susan Lessner, Daniel G. Clair, Firas Mussa, Homayoun Valafar |
| Abstract | We report an object tracking algorithm that combines geometrical constraints, thresholding, and motion detection for tracking of the descending aorta and the network of major arteries that branch from the aorta including the iliac and femoral arteries. Using our automated identification and analysis, arterial system was identified with more than 85% success when compared to human annotation. Furthermore, the reported automated system is capable of producing a stenosis profile, and a calcification score similar to the Agatston score. The use of stenosis and calcification profiles will lead to the development of better-informed diagnostic and prognostic tools. |
| Tasks | Motion Detection, Object Tracking |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.06010v1 |
| https://arxiv.org/pdf/1912.06010v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-analysis-of-femoral-artery |
| Repo | |
| Framework | |
DeepLine: AutoML Tool for Pipelines Generation using Deep Reinforcement Learning and Hierarchical Actions Filtering
| Title | DeepLine: AutoML Tool for Pipelines Generation using Deep Reinforcement Learning and Hierarchical Actions Filtering |
| Authors | Yuval Heffetz, Roman Vainstein, Gilad Katz, Lior Rokach |
| Abstract | Automatic machine learning (AutoML) is an area of research aimed at automating machine learning (ML) activities that currently require human experts. One of the most challenging tasks in this field is the automatic generation of end-to-end ML pipelines: combining multiple types of ML algorithms into a single architecture used for end-to-end analysis of previously-unseen data. This task has two challenging aspects: the first is the need to explore a large search space of algorithms and pipeline architectures. The second challenge is the computational cost of training and evaluating multiple pipelines. In this study we present DeepLine, a reinforcement learning based approach for automatic pipeline generation. Our proposed approach utilizes an efficient representation of the search space and leverages past knowledge gained from previously-analyzed datasets to make the problem more tractable. Additionally, we propose a novel hierarchical-actions algorithm that serves as a plugin, mediating the environment-agent interaction in deep reinforcement learning problems. The plugin significantly speeds up the training process of our model. Evaluation on 56 datasets shows that DeepLine outperforms state-of-the-art approaches both in accuracy and in computational cost. |
| Tasks | AutoML |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1911.00061v1 |
| https://arxiv.org/pdf/1911.00061v1.pdf | |
| PWC | https://paperswithcode.com/paper/deepline-automl-tool-for-pipelines-generation |
| Repo | |
| Framework | |
Unsupervised Medical Image Translation Using Cycle-MedGAN
| Title | Unsupervised Medical Image Translation Using Cycle-MedGAN |
| Authors | Karim Armanious, Chenming Jiang, Sherif Abdulatif, Thomas Küstner, Sergios Gatidis, Bin Yang |
| Abstract | Image-to-image translation is a new field in computer vision with multiple potential applications in the medical domain. However, for supervised image translation frameworks, co-registered datasets, paired in a pixel-wise sense, are required. This is often difficult to acquire in realistic medical scenarios. On the other hand, unsupervised translation frameworks often result in blurred translated images with unrealistic details. In this work, we propose a new unsupervised translation framework which is titled Cycle-MedGAN. The proposed framework utilizes new non-adversarial cycle losses which direct the framework to minimize the textural and perceptual discrepancies in the translated images. Qualitative and quantitative comparisons against other unsupervised translation approaches demonstrate the performance of the proposed framework for PET-CT translation and MR motion correction. |
| Tasks | Image-to-Image Translation |
| Published | 2019-03-08 |
| URL | http://arxiv.org/abs/1903.03374v1 |
| http://arxiv.org/pdf/1903.03374v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-medical-image-translation-using |
| Repo | |
| Framework | |
Privacy Attacks on Network Embeddings
| Title | Privacy Attacks on Network Embeddings |
| Authors | Michael Ellers, Michael Cochez, Tobias Schumacher, Markus Strohmaier, Florian Lemmerich |
| Abstract | Data ownership and data protection are increasingly important topics with ethical and legal implications, e.g., with the right to erasure established in the European General Data Protection Regulation (GDPR). In this light, we investigate network embeddings, i.e., the representation of network nodes as low-dimensional vectors. We consider a typical social network scenario with nodes representing users and edges relationships between them. We assume that a network embedding of the nodes has been trained. After that, a user demands the removal of his data, requiring the full deletion of the corresponding network information, in particular the corresponding node and incident edges. In that setting, we analyze whether after the removal of the node from the network and the deletion of the vector representation of the respective node in the embedding significant information about the link structure of the removed node is still encoded in the embedding vectors of the remaining nodes. This would require a (potentially computationally expensive) retraining of the embedding. For that purpose, we deploy an attack that leverages information from the remaining network and embedding to recover information about the neighbors of the removed node. The attack is based on (i) measuring distance changes in network embeddings and (ii) a machine learning classifier that is trained on networks that are constructed by removing additional nodes. Our experiments demonstrate that substantial information about the edges of a removed node/user can be retrieved across many different datasets. This implies that to fully protect the privacy of users, node deletion requires complete retraining - or at least a significant modification - of original network embeddings. Our results suggest that deleting the corresponding vector representation from network embeddings alone is not sufficient from a privacy perspective. |
| Tasks | Network Embedding |
| Published | 2019-12-23 |
| URL | https://arxiv.org/abs/1912.10979v1 |
| https://arxiv.org/pdf/1912.10979v1.pdf | |
| PWC | https://paperswithcode.com/paper/privacy-attacks-on-network-embeddings |
| Repo | |
| Framework | |
Shenjing: A low power reconfigurable neuromorphic accelerator with partial-sum and spike networks-on-chip
| Title | Shenjing: A low power reconfigurable neuromorphic accelerator with partial-sum and spike networks-on-chip |
| Authors | Bo Wang, Jun Zhou, Weng-Fai Wong, Li-Shiuan Peh |
| Abstract | The next wave of on-device AI will likely require energy-efficient deep neural networks. Brain-inspired spiking neural networks (SNN) has been identified to be a promising candidate. Doing away with the need for multipliers significantly reduces energy. For on-device applications, besides computation, communication also incurs a significant amount of energy and time. In this paper, we propose Shenjing, a configurable SNN architecture which fully exposes all on-chip communications to software, enabling software mapping of SNN models with high accuracy at low power. Unlike prior SNN architectures like TrueNorth, Shenjing does not require any model modification and retraining for the mapping. We show that conventional artificial neural networks (ANN) such as multilayer perceptron, convolutional neural networks, as well as the latest residual neural networks can be mapped successfully onto Shenjing, realizing ANNs with SNN’s energy efficiency. For the MNIST inference problem using a multilayer perceptron, we were able to achieve an accuracy of 96% while consuming just 1.26mW using 10 Shenjing cores. |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.10741v1 |
| https://arxiv.org/pdf/1911.10741v1.pdf | |
| PWC | https://paperswithcode.com/paper/shenjing-a-low-power-reconfigurable |
| Repo | |
| Framework | |
Mix and match networks: multi-domain alignment for unpaired image-to-image translation
| Title | Mix and match networks: multi-domain alignment for unpaired image-to-image translation |
| Authors | Yaxing Wang, Luis Herranz, Joost van de Weijer |
| Abstract | This paper addresses the problem of inferring unseen cross-domain and cross-modal image-to-image translations between multiple domains and modalities. We assume that only some of the pairwise translations have been seen (i.e. trained) and infer the remaining unseen translations (where training pairs are not available). We propose mix and match networks, an approach where multiple encoders and decoders are aligned in such a way that the desired translation can be obtained by simply cascading the source encoder and the target decoder, even when they have not interacted during the training stage (i.e. unseen). The main challenge lies in the alignment of the latent representations at the bottlenecks of encoder-decoder pairs. We propose an architecture with several tools to encourage alignment, including autoencoders and robust side information and latent consistency losses. We show the benefits of our approach in terms of effectiveness and scalability compared with other pairwise image-to-image translation approaches. We also propose zero-pair cross-modal image translation, a challenging setting where the objective is inferring semantic segmentation from depth (and vice-versa) without explicit segmentation-depth pairs, and only from two (disjoint) segmentation-RGB and depth-segmentation training sets. We observe that certain part of the shared information between unseen domains might not be reachable, so we further propose a variant that leverages pseudo-pairs to exploit all shared information. |
| Tasks | Image-to-Image Translation, Semantic Segmentation |
| Published | 2019-03-08 |
| URL | http://arxiv.org/abs/1903.04294v1 |
| http://arxiv.org/pdf/1903.04294v1.pdf | |
| PWC | https://paperswithcode.com/paper/mix-and-match-networks-multi-domain-alignment |
| Repo | |
| Framework | |
Ease-of-Teaching and Language Structure from Emergent Communication
| Title | Ease-of-Teaching and Language Structure from Emergent Communication |
| Authors | Fushan Li, Michael Bowling |
| Abstract | Artificial agents have been shown to learn to communicate when needed to complete a cooperative task. Some level of language structure (e.g., compositionality) has been found in the learned communication protocols. This observed structure is often the result of specific environmental pressures during training. By introducing new agents periodically to replace old ones, sequentially and within a population, we explore such a new pressure – ease of teaching – and show its impact on the structure of the resulting language. |
| Tasks | |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02403v2 |
| https://arxiv.org/pdf/1906.02403v2.pdf | |
| PWC | https://paperswithcode.com/paper/ease-of-teaching-and-language-structure-from |
| Repo | |
| Framework | |
KoPA: Automated Kronecker Product Approximation
| Title | KoPA: Automated Kronecker Product Approximation |
| Authors | Chencheng Cai, Rong Chen, Han Xiao |
| Abstract | We consider the matrix approximation induced by the Kronecker product decomposition. We propose to approximate a given matrix by the sum of a few Kronecker products, which we refer to as the Kronecker product approximation (KoPA). Because the Kronecker product is an extensions of the outer product from vectors to matrices, KoPA extends the low rank approximation, and include the latter as a special case. KoPA also offers a greater flexibility over the low rank approximation, since it allows the user to choose the configuration, which are the dimensions of the two smaller matrices forming the Kronecker product. On the other hand, the configuration to be used is usually unknown, and has to be determined from the data in order to achieve the optimal balance between accuracy and parsimony. We propose to use extended information criteria to select the configuration. Under the paradigm of high dimensional analysis, we show that the proposed procedure is able to select the true configuration with probability tending to one, under suitable conditions on the signal-to-noise ratio. We demonstrate the superiority of KoPA over the low rank approximations through numerical studies, and a benchmark image example. |
| Tasks | |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02392v2 |
| https://arxiv.org/pdf/1912.02392v2.pdf | |
| PWC | https://paperswithcode.com/paper/kopa-automated-kronecker-product |
| Repo | |
| Framework | |
Are Anchor Points Really Indispensable in Label-Noise Learning?
| Title | Are Anchor Points Really Indispensable in Label-Noise Learning? |
| Authors | Xiaobo Xia, Tongliang Liu, Nannan Wang, Bo Han, Chen Gong, Gang Niu, Masashi Sugiyama |
| Abstract | In label-noise learning, \textit{noise transition matrix}, denoting the probabilities that clean labels flip into noisy labels, plays a central role in building \textit{statistically consistent classifiers}. Existing theories have shown that the transition matrix can be learned by exploiting \textit{anchor points} (i.e., data points that belong to a specific class almost surely). However, when there are no anchor points, the transition matrix will be poorly learned, and those current consistent classifiers will significantly degenerate. In this paper, without employing anchor points, we propose a \textit{transition-revision} ($T$-Revision) method to effectively learn transition matrices, leading to better classifiers. Specifically, to learn a transition matrix, we first initialize it by exploiting data points that are similar to anchor points, having high \textit{noisy class posterior probabilities}. Then, we modify the initialized matrix by adding a \textit{slack variable}, which can be learned and validated together with the classifier by using noisy data. Empirical results on benchmark-simulated and real-world label-noise datasets demonstrate that without using exact anchor points, the proposed method is superior to the state-of-the-art label-noise learning methods. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://arxiv.org/abs/1906.00189v2 |
| https://arxiv.org/pdf/1906.00189v2.pdf | |
| PWC | https://paperswithcode.com/paper/190600189 |
| Repo | |
| Framework | |
Moving Towards Open Set Incremental Learning: Readily Discovering New Authors
| Title | Moving Towards Open Set Incremental Learning: Readily Discovering New Authors |
| Authors | Justin Leo, Jugal Kalita |
| Abstract | The classification of textual data often yields important information. Most classifiers work in a closed world setting where the classifier is trained on a known corpus, and then it is tested on unseen examples that belong to one of the classes seen during training. Despite the usefulness of this design, often there is a need to classify unseen examples that do not belong to any of the classes on which the classifier was trained. This paper describes the open set scenario where unseen examples from previously unseen classes are handled while testing. This further examines a process of enhanced open set classification with a deep neural network that discovers new classes by clustering the examples identified as belonging to unknown classes, followed by a process of retraining the classifier with newly recognized classes. Through this process the model moves to an incremental learning model where it continuously finds and learns from novel classes of data that have been identified automatically. This paper also develops a new metric that measures multiple attributes of clustering open set data. Multiple experiments across two author attribution data sets demonstrate the creation an incremental model that produces excellent results. |
| Tasks | |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.12944v1 |
| https://arxiv.org/pdf/1910.12944v1.pdf | |
| PWC | https://paperswithcode.com/paper/moving-towards-open-set-incremental-learning |
| Repo | |
| Framework | |
Two-phase Hair Image Synthesis by Self-Enhancing Generative Model
| Title | Two-phase Hair Image Synthesis by Self-Enhancing Generative Model |
| Authors | Haonan Qiu, Chuan Wang, Hang Zhu, Xiangyu Zhu, Jinjin Gu, Xiaoguang Han |
| Abstract | Generating plausible hair image given limited guidance, such as sparse sketches or low-resolution image, has been made possible with the rise of Generative Adversarial Networks (GANs). Traditional image-to-image translation networks can generate recognizable results, but finer textures are usually lost and blur artifacts commonly exist. In this paper, we propose a two-phase generative model for high-quality hair image synthesis. The two-phase pipeline first generates a coarse image by an existing image translation model, then applies a re-generating network with self-enhancing capability to the coarse image. The self-enhancing capability is achieved by a proposed structure extraction layer, which extracts the texture and orientation map from a hair image. Extensive experiments on two tasks, Sketch2Hair and Hair Super-Resolution, demonstrate that our approach is able to synthesize plausible hair image with finer details, and outperforms the state-of-the-art. |
| Tasks | Image Generation, Image-to-Image Translation, Super-Resolution |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.11203v1 |
| http://arxiv.org/pdf/1902.11203v1.pdf | |
| PWC | https://paperswithcode.com/paper/two-phase-hair-image-synthesis-by-self |
| Repo | |
| Framework | |
Adversarial target-invariant representation learning for domain generalization
| Title | Adversarial target-invariant representation learning for domain generalization |
| Authors | Isabela Albuquerque, João Monteiro, Tiago H. Falk, Ioannis Mitliagkas |
| Abstract | In many applications of machine learning, the training and test set data come from different distributions, or domains. A number of domain generalization strategies have been introduced with the goal of achieving good performance on out-of-distribution data. In this paper, we propose an adversarial approach to the problem. We propose a process that enforces pair-wise domain invariance while training a feature extractor over a diverse set of domains. We show that this process ensures invariance to any distribution that can be expressed as a mixture of the training domains. Following this insight, we then introduce an adversarial approach in which pair-wise divergences are estimated and minimized. Experiments on two domain generalization benchmarks for object recognition (i.e., PACS and VLCS) show that the proposed method yields higher average accuracy on the target domains in comparison to previously introduced adversarial strategies, as well as recently proposed methods based on learning invariant representations. |
| Tasks | Domain Generalization, Object Recognition, Representation Learning |
| Published | 2019-11-03 |
| URL | https://arxiv.org/abs/1911.00804v1 |
| https://arxiv.org/pdf/1911.00804v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-target-invariant-representation |
| Repo | |
| Framework | |
Safer Deep RL with Shallow MCTS: A Case Study in Pommerman
| Title | Safer Deep RL with Shallow MCTS: A Case Study in Pommerman |
| Authors | Bilal Kartal, Pablo Hernandez-Leal, Chao Gao, Matthew E. Taylor |
| Abstract | Safe reinforcement learning has many variants and it is still an open research problem. Here, we focus on how to use action guidance by means of a non-expert demonstrator to avoid catastrophic events in a domain with sparse, delayed, and deceptive rewards: the recently-proposed multi-agent benchmark of Pommerman. This domain is very challenging for reinforcement learning (RL) — past work has shown that model-free RL algorithms fail to achieve significant learning. In this paper, we shed light into the reasons behind this failure by exemplifying and analyzing the high rate of catastrophic events (i.e., suicides) that happen under random exploration in this domain. While model-free random exploration is typically futile, we propose a new framework where even a non-expert simulated demonstrator, e.g., planning algorithms such as Monte Carlo tree search with small number of rollouts, can be integrated to asynchronous distributed deep reinforcement learning methods. Compared to vanilla deep RL algorithms, our proposed methods both learn faster and converge to better policies on a two-player mini version of the Pommerman game. |
| Tasks | |
| Published | 2019-04-10 |
| URL | http://arxiv.org/abs/1904.05759v1 |
| http://arxiv.org/pdf/1904.05759v1.pdf | |
| PWC | https://paperswithcode.com/paper/safer-deep-rl-with-shallow-mcts-a-case-study |
| Repo | |
| Framework | |
Using CycleGANs for effectively reducing image variability across OCT devices and improving retinal fluid segmentation
| Title | Using CycleGANs for effectively reducing image variability across OCT devices and improving retinal fluid segmentation |
| Authors | Philipp Seeböck, David Romo-Bucheli, Sebastian Waldstein, Hrvoje Bogunović, José Ignacio Orlando, Bianca S. Gerendas, Georg Langs, Ursula Schmidt-Erfurth |
| Abstract | Optical coherence tomography (OCT) has become the most important imaging modality in ophthalmology. A substantial amount of research has recently been devoted to the development of machine learning (ML) models for the identification and quantification of pathological features in OCT images. Among the several sources of variability the ML models have to deal with, a major factor is the acquisition device, which can limit the ML model’s generalizability. In this paper, we propose to reduce the image variability across different OCT devices (Spectralis and Cirrus) by using CycleGAN, an unsupervised unpaired image transformation algorithm. The usefulness of this approach is evaluated in the setting of retinal fluid segmentation, namely intraretinal cystoid fluid (IRC) and subretinal fluid (SRF). First, we train a segmentation model on images acquired with a source OCT device. Then we evaluate the model on (1) source, (2) target and (3) transformed versions of the target OCT images. The presented transformation strategy shows an F1 score of 0.4 (0.51) for IRC (SRF) segmentations. Compared with traditional transformation approaches, this means an F1 score gain of 0.2 (0.12). |
| Tasks | |
| Published | 2019-01-24 |
| URL | http://arxiv.org/abs/1901.08379v2 |
| http://arxiv.org/pdf/1901.08379v2.pdf | |
| PWC | https://paperswithcode.com/paper/using-cyclegans-for-effectively-reducing |
| Repo | |
| Framework | |
Processsing Simple Geometric Attributes with Autoencoders
| Title | Processsing Simple Geometric Attributes with Autoencoders |
| Authors | Alasdair Newson, Andrés Almansa, Yann Gousseau, Saïd Ladjal |
| Abstract | Image synthesis is a core problem in modern deep learning, and many recent architectures such as autoencoders and Generative Adversarial networks produce spectacular results on highly complex data, such as images of faces or landscapes. While these results open up a wide range of new, advanced synthesis applications, there is also a severe lack of theoretical understanding of how these networks work. This results in a wide range of practical problems, such as difficulties in training, the tendency to sample images with little or no variability, and generalisation problems. In this paper, we propose to analyse the ability of the simplest generative network, the autoencoder, to encode and decode two simple geometric attributes : size and position. We believe that, in order to understand more complicated tasks, it is necessary to first understand how these networks process simple attributes. For the first property, we analyse the case of images of centred disks with variable radii. We explain how the autoencoder projects these images to and from a latent space of smallest possible dimension, a scalar. In particular, we describe a closed-form solution to the decoding training problem in a network without biases, and show that during training, the network indeed finds this solution. We then investigate the best regularisation approaches which yield networks that generalise well. For the second property, position, we look at the encoding and decoding of Dirac delta functions, also known as `one-hot’ vectors. We describe a hand-crafted filter that achieves encoding perfectly, and show that the network naturally finds this filter during training. We also show experimentally that the decoding can be achieved if the dataset is sampled in an appropriate manner. | |
| Tasks | Image Generation |
| Published | 2019-04-15 |
| URL | http://arxiv.org/abs/1904.07099v1 |
| http://arxiv.org/pdf/1904.07099v1.pdf | |
| PWC | https://paperswithcode.com/paper/processsing-simple-geometric-attributes-with |
| Repo | |
| Framework | |
