Paper Group ANR 1162
Can We Distinguish Machine Learning from Human Learning?. Bayesian Neural Decoding Using A Diversity-Encouraging Latent Representation Learning Method. Slot Based Image Augmentation System for Object Detection. A Generalized Framework for Agglomerative Clustering of Signed Graphs applied to Instance Segmentation. Robustness of Neural Networks: A Pr …
Can We Distinguish Machine Learning from Human Learning?
| Title | Can We Distinguish Machine Learning from Human Learning? |
| Authors | Vicki Bier, Paul B. Kantor, Gary Lupyan, Xiaojin Zhu |
| Abstract | What makes a task relatively more or less difficult for a machine compared to a human? Much AI/ML research has focused on expanding the range of tasks that machines can do, with a focus on whether machines can beat humans. Allowing for differences in scale, we can seek interesting (anomalous) pairs of tasks T, T’. We define interesting in this way: The “harder to learn” relation is reversed when comparing human intelligence (HI) to AI. While humans seems to be able to understand problems by formulating rules, ML using neural networks does not rely on constructing rules. We discuss a novel approach where the challenge is to “perform well under rules that have been created by human beings.” We suggest that this provides a rigorous and precise pathway for understanding the difference between the two kinds of learning. Specifically, we suggest a large and extensible class of learning tasks, formulated as learning under rules. With these tasks, both the AI and HI will be studied with rigor and precision. The immediate goal is to find interesting groundtruth rule pairs. In the long term, the goal will be to understand, in a generalizable way, what distinguishes interesting pairs from ordinary pairs, and to define saliency behind interesting pairs. This may open new ways of thinking about AI, and provide unexpected insights into human learning. |
| Tasks | |
| Published | 2019-10-08 |
| URL | https://arxiv.org/abs/1910.03466v1 |
| https://arxiv.org/pdf/1910.03466v1.pdf | |
| PWC | https://paperswithcode.com/paper/can-we-distinguish-machine-learning-from |
| Repo | |
| Framework | |
Bayesian Neural Decoding Using A Diversity-Encouraging Latent Representation Learning Method
| Title | Bayesian Neural Decoding Using A Diversity-Encouraging Latent Representation Learning Method |
| Authors | Tian Chen, Lingge Li, Gabriel Elias, Norbert Fortin, Babak Shahbaba |
| Abstract | It is well established that temporal organization is critical to memory, and that the ability to temporally organize information is fundamental to many perceptual, cognitive, and motor processes. While our understanding of how the brain processes the spatial context of memories has advanced considerably, our understanding of their temporal organization lags far behind. In this paper, we propose a new approach for elucidating the neural basis of complex behaviors and temporal organization of memories. More specifically, we focus on neural decoding - the prediction of behavioral or experimental conditions based on observed neural data. In general, this is a challenging classification problem, which is of immense interest in neuroscience. Our goal is to develop a new framework that not only improves the overall accuracy of decoding, but also provides a clear latent representation of the decoding process. To accomplish this, our approach uses a Variational Auto-encoder (VAE) model with a diversity-encouraging prior based on determinantal point processes (DPP) to improve latent representation learning by avoiding redundancy in the latent space. We apply our method to data collected from a novel rat experiment that involves presenting repeated sequences of odors at a single port and testing the rats’ ability to identify each odor. We show that our method leads to substantially higher accuracy rate for neural decoding and allows to discover novel biological phenomena by providing a clear latent representation of the decoding process. |
| Tasks | Point Processes, Representation Learning |
| Published | 2019-10-13 |
| URL | https://arxiv.org/abs/1910.05695v1 |
| https://arxiv.org/pdf/1910.05695v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-neural-decoding-using-a-diversity |
| Repo | |
| Framework | |
Slot Based Image Augmentation System for Object Detection
| Title | Slot Based Image Augmentation System for Object Detection |
| Authors | Yingwei Zhou |
| Abstract | Object Detection has been a significant topic in computer vision. As the continuous development of Deep Learning, many advanced academic and industrial outcomes are established on localising and classifying the target objects, such as instance segmentation, video tracking and robotic vision. As the core concept of Deep Learning, Deep Neural Networks (DNNs) and associated training are highly integrated with task-driven modelling, having great effects on accurate detection. The main focus of improving detection performance is proposing DNNs with extra layers and novel topological connections to extract the desired features from input data. However, training these models can be computationally expensive and laborious progress as the complicated model architecture and enormous parameters. Besides, the dataset is another reason causing this issue and low detection accuracy, because of insufficient data samples or difficult instances. To address these training difficulties, this thesis presents two different approaches to improve the detection performance in the relatively light-weight way. As the intrinsic feature of data-driven in deep learning, the first approach is “slot-based image augmentation” to enrich the dataset with extra foreground and background combinations. Instead of the commonly used image flipping method, the proposed system achieved similar mAP improvement with less extra images which decrease training time. This proposed augmentation system has extra flexibility adapting to various scenarios and the performance-driven analysis provides an alternative aspect of conducting image augmentation |
| Tasks | Image Augmentation, Instance Segmentation, Object Detection, Semantic Segmentation |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.12900v1 |
| https://arxiv.org/pdf/1907.12900v1.pdf | |
| PWC | https://paperswithcode.com/paper/slot-based-image-augmentation-system-for |
| Repo | |
| Framework | |
A Generalized Framework for Agglomerative Clustering of Signed Graphs applied to Instance Segmentation
| Title | A Generalized Framework for Agglomerative Clustering of Signed Graphs applied to Instance Segmentation |
| Authors | Alberto Bailoni, Constantin Pape, Steffen Wolf, Thorsten Beier, Anna Kreshuk, Fred A. Hamprecht |
| Abstract | We propose a novel theoretical framework that generalizes algorithms for hierarchical agglomerative clustering to weighted graphs with both attractive and repulsive interactions between the nodes. This framework defines GASP, a Generalized Algorithm for Signed graph Partitioning, and allows us to explore many combinations of different linkage criteria and cannot-link constraints. We prove the equivalence of existing clustering methods to some of those combinations, and introduce new algorithms for combinations which have not been studied. An extensive comparison is performed to evaluate properties of the clustering algorithms in the context of instance segmentation in images, including robustness to noise and efficiency. We show how one of the new algorithms proposed in our framework outperforms all previously known agglomerative methods for signed graphs, both on the competitive CREMI 2016 EM segmentation benchmark and on the CityScapes dataset. |
| Tasks | graph partitioning, Instance Segmentation, Semantic Segmentation |
| Published | 2019-06-27 |
| URL | https://arxiv.org/abs/1906.11713v1 |
| https://arxiv.org/pdf/1906.11713v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-generalized-framework-for-agglomerative |
| Repo | |
| Framework | |
Robustness of Neural Networks: A Probabilistic and Practical Approach
| Title | Robustness of Neural Networks: A Probabilistic and Practical Approach |
| Authors | Ravi Mangal, Aditya V. Nori, Alessandro Orso |
| Abstract | Neural networks are becoming increasingly prevalent in software, and it is therefore important to be able to verify their behavior. Because verifying the correctness of neural networks is extremely challenging, it is common to focus on the verification of other properties of these systems. One important property, in particular, is robustness. Most existing definitions of robustness, however, focus on the worst-case scenario where the inputs are adversarial. Such notions of robustness are too strong, and unlikely to be satisfied by-and verifiable for-practical neural networks. Observing that real-world inputs to neural networks are drawn from non-adversarial probability distributions, we propose a novel notion of robustness: probabilistic robustness, which requires the neural network to be robust with at least $(1 - \epsilon)$ probability with respect to the input distribution. This probabilistic approach is practical and provides a principled way of estimating the robustness of a neural network. We also present an algorithm, based on abstract interpretation and importance sampling, for checking whether a neural network is probabilistically robust. Our algorithm uses abstract interpretation to approximate the behavior of a neural network and compute an overapproximation of the input regions that violate robustness. It then uses importance sampling to counter the effect of such overapproximation and compute an accurate estimate of the probability that the neural network violates the robustness property. |
| Tasks | |
| Published | 2019-02-15 |
| URL | http://arxiv.org/abs/1902.05983v1 |
| http://arxiv.org/pdf/1902.05983v1.pdf | |
| PWC | https://paperswithcode.com/paper/robustness-of-neural-networks-a-probabilistic |
| Repo | |
| Framework | |
High Quality ELMo Embeddings for Seven Less-Resourced Languages
| Title | High Quality ELMo Embeddings for Seven Less-Resourced Languages |
| Authors | Matej Ulčar, Marko Robnik-Šikonja |
| Abstract | Recent results show that deep neural networks using contextual embeddings significantly outperform non-contextual embeddings on a majority of text classification task. We offer precomputed embeddings from popular contextual ELMo model for seven languages: Croatian, Estonian, Finnish, Latvian, Lithuanian, Slovenian, and Swedish. We demonstrate that the quality of embeddings strongly depends on the size of training set and show that existing publicly available ELMo embeddings for listed languages shall be improved. We train new ELMo embeddings on much larger training sets and show their advantage over baseline non-contextual FastText embeddings. In evaluation, we use two benchmarks, the analogy task and the NER task. |
| Tasks | Text Classification |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.10049v2 |
| https://arxiv.org/pdf/1911.10049v2.pdf | |
| PWC | https://paperswithcode.com/paper/high-quality-elmo-embeddings-for-seven-less |
| Repo | |
| Framework | |
Multi-Contrast Super-Resolution MRI Through a Progressive Network
| Title | Multi-Contrast Super-Resolution MRI Through a Progressive Network |
| Authors | Qing Lyu, Hongming Shan, Ge Wang |
| Abstract | Magnetic resonance imaging (MRI) is widely used for screening, diagnosis, image-guided therapy, and scientific research. A significant advantage of MRI over other imaging modalities such as computed tomography (CT) and nuclear imaging is that it clearly shows soft tissues in multi-contrasts. Compared with other medical image super-resolution (SR) methods that are in a single contrast, multi-contrast super-resolution studies can synergize multiple contrast images to achieve better super-resolution results. In this paper, we propose a one-level non-progressive neural network for low up-sampling multi-contrast super-resolution and a two-level progressive network for high up-sampling multi-contrast super-resolution. Multi-contrast information is combined in high-level feature space. Our experimental results demonstrate that the proposed networks can produce MRI super-resolution images with good image quality and outperform other multi-contrast super-resolution methods in terms of structural similarity and peak signal-to-noise ratio. Also, the progressive network produces a better SR image quality than the non-progressive network, even if the original low-resolution images were highly down-sampled. |
| Tasks | Computed Tomography (CT), Image Super-Resolution, Super-Resolution |
| Published | 2019-08-05 |
| URL | https://arxiv.org/abs/1908.01612v2 |
| https://arxiv.org/pdf/1908.01612v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-contrast-super-resolution-mri-through-a |
| Repo | |
| Framework | |
Exploring Fine-Tuned Embeddings that Model Intensifiers for Emotion Analysis
| Title | Exploring Fine-Tuned Embeddings that Model Intensifiers for Emotion Analysis |
| Authors | Laura Bostan, Roman Klinger |
| Abstract | Adjective phrases like “a little bit surprised”, “completely shocked”, or “not stunned at all” are not handled properly by currently published state-of-the-art emotion classification and intensity prediction systems which use pre-dominantly non-contextualized word embeddings as input. Based on this finding, we analyze differences between embeddings used by these systems in regard to their capability of handling such cases. Furthermore, we argue that intensifiers in context of emotion words need special treatment, as is established for sentiment polarity classification, but not for more fine-grained emotion prediction. To resolve this issue, we analyze different aspects of a post-processing pipeline which enriches the word representations of such phrases. This includes expansion of semantic spaces at the phrase level and sub-word level followed by retrofitting to emotion lexica. We evaluate the impact of these steps with A La Carte and Bag-of-Substrings extensions based on pretrained GloVe, Word2vec, and fastText embeddings against a crowd-sourced corpus of intensity annotations for tweets containing our focus phrases. We show that the fastText-based models do not gain from handling these specific phrases under inspection. For Word2vec embeddings, we show that our post-processing pipeline improves the results by up to 8% on a novel dataset densely populated with intensifiers. |
| Tasks | Emotion Classification, Emotion Recognition, Word Embeddings |
| Published | 2019-04-05 |
| URL | http://arxiv.org/abs/1904.03164v1 |
| http://arxiv.org/pdf/1904.03164v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-fine-tuned-embeddings-that-model |
| Repo | |
| Framework | |
Estimating physical properties from liquid crystal textures via machine learning and complexity-entropy methods
| Title | Estimating physical properties from liquid crystal textures via machine learning and complexity-entropy methods |
| Authors | H. Y. D. Sigaki, R. F. de Souza, R. T. de Souza, R. S. Zola, H. V. Ribeiro |
| Abstract | Imaging techniques are essential tools for inquiring a number of properties from different materials. Liquid crystals are often investigated via optical and image processing methods. In spite of that, considerably less attention has been paid to the problem of extracting physical properties of liquid crystals directly from textures images of these materials. Here we present an approach that combines two physics-inspired image quantifiers (permutation entropy and statistical complexity) with machine learning techniques for extracting physical properties of nematic and cholesteric liquid crystals directly from their textures images. We demonstrate the usefulness and accuracy of our approach in a series of applications involving simulated and experimental textures, in which physical properties of these materials (namely: average order parameter, sample temperature, and cholesteric pitch length) are predicted with significant precision. Finally, we believe our approach can be useful in more complex liquid crystal experiments as well as for probing physical properties of other materials that are investigated via imaging techniques. |
| Tasks | |
| Published | 2019-01-07 |
| URL | http://arxiv.org/abs/1901.01754v1 |
| http://arxiv.org/pdf/1901.01754v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-physical-properties-from-liquid |
| Repo | |
| Framework | |
Logarithmic Regret for Online Control
| Title | Logarithmic Regret for Online Control |
| Authors | Naman Agarwal, Elad Hazan, Karan Singh |
| Abstract | We study optimal regret bounds for control in linear dynamical systems under adversarially changing strongly convex cost functions, given the knowledge of transition dynamics. This includes several well studied and fundamental frameworks such as the Kalman filter and the linear quadratic regulator. State of the art methods achieve regret which scales as $O(\sqrt{T})$, where $T$ is the time horizon. We show that the optimal regret in this setting can be significantly smaller, scaling as $O(\text{poly}(\log T))$. This regret bound is achieved by two different efficient iterative methods, online gradient descent and online natural gradient. |
| Tasks | |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.05062v1 |
| https://arxiv.org/pdf/1909.05062v1.pdf | |
| PWC | https://paperswithcode.com/paper/logarithmic-regret-for-online-control |
| Repo | |
| Framework | |
Multi-modal Graph Fusion for Inductive Disease Classification in Incomplete Datasets
| Title | Multi-modal Graph Fusion for Inductive Disease Classification in Incomplete Datasets |
| Authors | Gerome Vivar, Hendrik Burwinkel, Anees Kazi, Andreas Zwergal, Nassir Navab, Seyed-Ahmad Ahmadi |
| Abstract | Clinical diagnostic decision making and population-based studies often rely on multi-modal data which is noisy and incomplete. Recently, several works proposed geometric deep learning approaches to solve disease classification, by modeling patients as nodes in a graph, along with graph signal processing of multi-modal features. Many of these approaches are limited by assuming modality- and feature-completeness, and by transductive inference, which requires re-training of the entire model for each new test sample. In this work, we propose a novel inductive graph-based approach that can generalize to out-of-sample patients, despite missing features from entire modalities per patient. We propose multi-modal graph fusion which is trained end-to-end towards node-level classification. We demonstrate the fundamental working principle of this method on a simplified MNIST toy dataset. In experiments on medical data, our method outperforms single static graph approach in multi-modal disease classification. |
| Tasks | Decision Making |
| Published | 2019-05-08 |
| URL | https://arxiv.org/abs/1905.03053v1 |
| https://arxiv.org/pdf/1905.03053v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-modal-graph-fusion-for-inductive |
| Repo | |
| Framework | |
Comparing of Term Clustering Frameworks for Modular Ontology Learning
| Title | Comparing of Term Clustering Frameworks for Modular Ontology Learning |
| Authors | Ziwei Xu, Mounira Harzallah, Fabrice Guillet |
| Abstract | This paper aims to use term clustering to build a modular ontology according to core ontology from domain-specific text. The acquisition of semantic knowledge focuses on noun phrase appearing with the same syntactic roles in relation to a verb or its preposition combination in a sentence. The construction of this co-occurrence matrix from context helps to build feature space of noun phrases, which is then transformed to several encoding representations including feature selection and dimensionality reduction. In addition, the content has also been presented with the construction of word vectors. These representations are clustered respectively with K-Means and Affinity Propagation (AP) methods, which differentiate into the term clustering frameworks. Due to the randomness of K-Means, iteration efforts are adopted to find the optimal parameter. The frameworks are evaluated extensively where AP shows dominant effectiveness for co-occurred terms and NMF encoding technique is salient by its promising facilities in feature compression. |
| Tasks | Dimensionality Reduction, Feature Selection |
| Published | 2019-01-25 |
| URL | http://arxiv.org/abs/1901.09037v1 |
| http://arxiv.org/pdf/1901.09037v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparing-of-term-clustering-frameworks-for |
| Repo | |
| Framework | |
Abnormal Colon Polyp Image Synthesis Using Conditional Adversarial Networks for Improved Detection Performance
| Title | Abnormal Colon Polyp Image Synthesis Using Conditional Adversarial Networks for Improved Detection Performance |
| Authors | Younghak Shin, Hemin Ali Qadir, Ilangko Balasingham |
| Abstract | One of the major obstacles in automatic polyp detection during colonoscopy is the lack of labeled polyp training images. In this paper, we propose a framework of conditional adversarial networks to increase the number of training samples by generating synthetic polyp images. Using a normal binary form of polyp mask which represents only the polyp position as an input conditioned image, realistic polyp image generation is a difficult task in a generative adversarial networks approach. We propose an edge filtering-based combined input conditioned image to train our proposed networks. This enables realistic polyp image generations while maintaining the original structures of the colonoscopy image frames. More importantly, our proposed framework generates synthetic polyp images from normal colonoscopy images which have the advantage of being relatively easy to obtain. The network architecture is based on the use of multiple dilated convolutions in each encoding part of our generator network to consider large receptive fields and avoid many contractions of a feature map size. An image resizing with convolution for upsampling in the decoding layers is considered to prevent artifacts on generated images. We show that the generated polyp images are not only qualitatively realistic but also help to improve polyp detection performance. |
| Tasks | Image Generation |
| Published | 2019-06-27 |
| URL | https://arxiv.org/abs/1906.11467v1 |
| https://arxiv.org/pdf/1906.11467v1.pdf | |
| PWC | https://paperswithcode.com/paper/abnormal-colon-polyp-image-synthesis-using |
| Repo | |
| Framework | |
Multi-view Subspace Clustering via Partition Fusion
| Title | Multi-view Subspace Clustering via Partition Fusion |
| Authors | Juncheng Lv, Zhao Kang, Boyu Wang, Luping Ji, Zenglin Xu |
| Abstract | Multi-view clustering is an important approach to analyze multi-view data in an unsupervised way. Among various methods, the multi-view subspace clustering approach has gained increasing attention due to its encouraging performance. Basically, it integrates multi-view information into graphs, which are then fed into spectral clustering algorithm for final result. However, its performance may degrade due to noises existing in each individual view or inconsistency between heterogeneous features. Orthogonal to current work, we propose to fuse multi-view information in a partition space, which enhances the robustness of Multi-view clustering. Specifically, we generate multiple partitions and integrate them to find the shared partition. The proposed model unifies graph learning, generation of basic partitions, and view weight learning. These three components co-evolve towards better quality outputs. We have conducted comprehensive experiments on benchmark datasets and our empirical results verify the effectiveness and robustness of our approach. |
| Tasks | Multi-view Subspace Clustering |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01201v1 |
| https://arxiv.org/pdf/1912.01201v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-subspace-clustering-via-partition |
| Repo | |
| Framework | |
Nonzero-sum Adversarial Hypothesis Testing Games
| Title | Nonzero-sum Adversarial Hypothesis Testing Games |
| Authors | Sarath Yasodharan, Patrick Loiseau |
| Abstract | We study nonzero-sum hypothesis testing games that arise in the context of adversarial classification, in both the Bayesian as well as the Neyman-Pearson frameworks. We first show that these games admit mixed strategy Nash equilibria, and then we examine some interesting concentration phenomena of these equilibria. Our main results are on the exponential rates of convergence of classification errors at equilibrium, which are analogous to the well-known Chernoff-Stein lemma and Chernoff information that describe the error exponents in the classical binary hypothesis testing problem, but with parameters derived from the adversarial model. The results are validated through numerical experiments. |
| Tasks | |
| Published | 2019-09-28 |
| URL | https://arxiv.org/abs/1909.13031v1 |
| https://arxiv.org/pdf/1909.13031v1.pdf | |
| PWC | https://paperswithcode.com/paper/nonzero-sum-adversarial-hypothesis-testing |
| Repo | |
| Framework | |
