Paper Group ANR 82
Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis. Identification and Classification of Phenomena in Multispectral Satellite Imagery Using a New Image Smoother Method and its Applications in Environmental Remote Sensing. Biological Random Walks: integrating heterogeneous data in disease gene prioritization. An Inex …
Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis
| Title | Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis |
| Authors | Mang Tik Chiu, Xingqian Xu, Yunchao Wei, Zilong Huang, Alexander Schwing, Robert Brunner, Hrant Khachatrian, Hovnatan Karapetyan, Ivan Dozier, Greg Rose, David Wilson, Adrian Tudor, Naira Hovakimyan, Thomas S. Huang, Honghui Shi |
| Abstract | The success of deep learning in visual recognition tasks has driven advancements in multiple fields of research. Particularly, increasing attention has been drawn towards its application in agriculture. Nevertheless, while visual pattern recognition on farmlands carries enormous economic values, little progress has been made to merge computer vision and crop sciences due to the lack of suitable agricultural image datasets. Meanwhile, problems in agriculture also pose new challenges in computer vision. For example, semantic segmentation of aerial farmland images requires inference over extremely large-size images with extreme annotation sparsity. These challenges are not present in most of the common object datasets, and we show that they are more challenging than many other aerial image datasets. To encourage research in computer vision for agriculture, we present Agriculture-Vision: a large-scale aerial farmland image dataset for semantic segmentation of agricultural patterns. We collected 94,986 high-quality aerial images from 3,432 farmlands across the US, where each image consists of RGB and Near-infrared (NIR) channels with resolution as high as 10 cm per pixel. We annotate nine types of field anomaly patterns that are most important to farmers. As a pilot study of aerial agricultural semantic segmentation, we perform comprehensive experiments using popular semantic segmentation models; we also propose an effective model designed for aerial agricultural pattern recognition. Our experiments demonstrate several challenges Agriculture-Vision poses to both the computer vision and agriculture communities. Future versions of this dataset will include even more aerial images, anomaly patterns and image channels. More information at https://www.agriculture-vision.com. |
| Tasks | Semantic Segmentation |
| Published | 2020-01-05 |
| URL | https://arxiv.org/abs/2001.01306v2 |
| https://arxiv.org/pdf/2001.01306v2.pdf | |
| PWC | https://paperswithcode.com/paper/agriculture-vision-a-large-aerial-image |
| Repo | |
| Framework | |
Identification and Classification of Phenomena in Multispectral Satellite Imagery Using a New Image Smoother Method and its Applications in Environmental Remote Sensing
| Title | Identification and Classification of Phenomena in Multispectral Satellite Imagery Using a New Image Smoother Method and its Applications in Environmental Remote Sensing |
| Authors | M. Kiani |
| Abstract | In this paper a new method of image smoothing for satellite imagery and its applications in environmental remote sensing are presented. This method is based on the global gradient minimization over the whole image. With respect to the image discrete identity, the continuous minimization problem is discretized. Using the finite difference numerical method of differentiation, a simple yet efficient 5*5-pixel template is derived. Convolution of the derived template with the image in different bands results in the discrimination of various image elements. This method is extremely fast, besides being highly precise. A case study is presented for the northern Iran, covering parts of the Caspian Sea. Comparison of the method with the usual Laplacian template reveals that it is more capable of distinguishing phenomena in the image. |
| Tasks | |
| Published | 2020-03-17 |
| URL | https://arxiv.org/abs/2003.08209v1 |
| https://arxiv.org/pdf/2003.08209v1.pdf | |
| PWC | https://paperswithcode.com/paper/identification-and-classification-of-1 |
| Repo | |
| Framework | |
Biological Random Walks: integrating heterogeneous data in disease gene prioritization
| Title | Biological Random Walks: integrating heterogeneous data in disease gene prioritization |
| Authors | Michele Gentili, Leonardo Martini, Manuela Petti, Lorenzo Farina, Luca Becchetti |
| Abstract | This work proposes a unified framework to leverage biological information in network propagation-based gene prioritization algorithms. Preliminary results on breast cancer data show significant improvements over state-of-the-art baselines, such as the prioritization of genes that are not identified as potential candidates by interactome-based algorithms, but that appear to be involved in/or potentially related to breast cancer, according to a functional analysis based on recent literature. |
| Tasks | |
| Published | 2020-02-14 |
| URL | https://arxiv.org/abs/2002.07064v1 |
| https://arxiv.org/pdf/2002.07064v1.pdf | |
| PWC | https://paperswithcode.com/paper/biological-random-walks-integrating |
| Repo | |
| Framework | |
An Inexact Manifold Augmented Lagrangian Method for Adaptive Sparse Canonical Correlation Analysis with Trace Lasso Regularization
| Title | An Inexact Manifold Augmented Lagrangian Method for Adaptive Sparse Canonical Correlation Analysis with Trace Lasso Regularization |
| Authors | Kangkang Deng, Zheng Peng |
| Abstract | Canonical correlation analysis (CCA for short) describes the relationship between two sets of variables by finding some linear combinations of these variables that maximizing the correlation coefficient. However, in high-dimensional settings where the number of variables exceeds sample size, or in the case of that the variables are highly correlated, the traditional CCA is no longer appropriate. In this paper, an adaptive sparse version of CCA (ASCCA for short) is proposed by using the trace Lasso regularization. The proposed ASCCA reduces the instability of the estimator when the covariates are highly correlated, and thus improves its interpretation. The ASCCA is further reformulated to an optimization problem on Riemannian manifolds, and an manifold inexact augmented Lagrangian method is then proposed for the resulting optimization problem. The performance of the ASCCA is compared with the other sparse CCA techniques in different simulation settings, which illustrates that the ASCCA is feasible and efficient. |
| Tasks | |
| Published | 2020-03-20 |
| URL | https://arxiv.org/abs/2003.09195v1 |
| https://arxiv.org/pdf/2003.09195v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-inexact-manifold-augmented-lagrangian |
| Repo | |
| Framework | |
Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks
| Title | Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks |
| Authors | Micah Goldblum, Steven Reich, Liam Fowl, Renkun Ni, Valeriia Cherepanova, Tom Goldstein |
| Abstract | Meta-learning algorithms produce feature extractors which achieve state-of-the-art performance on few-shot classification. While the literature is rich with meta-learning methods, little is known about why the resulting feature extractors perform so well. We develop a better understanding of the underlying mechanics of meta-learning and the difference between models trained using meta-learning and models which are trained classically. In doing so, we develop several hypotheses for why meta-learned models perform better. In addition to visualizations, we design several regularizers inspired by our hypotheses which improve performance on few-shot classification. |
| Tasks | Meta-Learning |
| Published | 2020-02-17 |
| URL | https://arxiv.org/abs/2002.06753v2 |
| https://arxiv.org/pdf/2002.06753v2.pdf | |
| PWC | https://paperswithcode.com/paper/unraveling-meta-learning-understanding |
| Repo | |
| Framework | |
Structural-Aware Sentence Similarity with Recursive Optimal Transport
| Title | Structural-Aware Sentence Similarity with Recursive Optimal Transport |
| Authors | Zihao Wang, Yong Zhang, Hao Wu |
| Abstract | Measuring sentence similarity is a classic topic in natural language processing. Light-weighted similarities are still of particular practical significance even when deep learning models have succeeded in many other tasks. Some light-weighted similarities with more theoretical insights have been demonstrated to be even stronger than supervised deep learning approaches. However, the successful light-weighted models such as Word Mover’s Distance [Kusner et al., 2015] or Smooth Inverse Frequency [Arora et al., 2017] failed to detect the difference from the structure of sentences, i.e. order of words. To address this issue, we present Recursive Optimal Transport (ROT) framework to incorporate the structural information with the classic OT. Moreover, we further develop Recursive Optimal Similarity (ROTS) for sentences with the valuable semantic insights from the connections between cosine similarity of weighted average of word vectors and optimal transport. ROTS is structural-aware and with low time complexity compared to optimal transport. Our experiments over 20 sentence textural similarity (STS) datasets show the clear advantage of ROTS over all weakly supervised approaches. Detailed ablation study demonstrate the effectiveness of ROT and the semantic insights. |
| Tasks | |
| Published | 2020-01-28 |
| URL | https://arxiv.org/abs/2002.00745v1 |
| https://arxiv.org/pdf/2002.00745v1.pdf | |
| PWC | https://paperswithcode.com/paper/structural-aware-sentence-similarity-with |
| Repo | |
| Framework | |
Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets
| Title | Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets |
| Authors | Dongxian Wu, Yisen Wang, Shu-Tao Xia, James Bailey, Xingjun Ma |
| Abstract | Skip connections are an essential component of current state-of-the-art deep neural networks (DNNs) such as ResNet, WideResNet, DenseNet, and ResNeXt. Despite their huge success in building deeper and more powerful DNNs, we identify a surprising security weakness of skip connections in this paper. Use of skip connections allows easier generation of highly transferable adversarial examples. Specifically, in ResNet-like (with skip connections) neural networks, gradients can backpropagate through either skip connections or residual modules. We find that using more gradients from the skip connections rather than the residual modules according to a decay factor, allows one to craft adversarial examples with high transferability. Our method is termed Skip Gradient Method(SGM). We conduct comprehensive transfer attacks against state-of-the-art DNNs including ResNets, DenseNets, Inceptions, Inception-ResNet, Squeeze-and-Excitation Network (SENet) and robustly trained DNNs. We show that employing SGM on the gradient flow can greatly improve the transferability of crafted attacks in almost all cases. Furthermore, SGM can be easily combined with existing black-box attack techniques, and obtain high improvements over state-of-the-art transferability methods. Our findings not only motivate new research into the architectural vulnerability of DNNs, but also open up further challenges for the design of secure DNN architectures. |
| Tasks | |
| Published | 2020-02-14 |
| URL | https://arxiv.org/abs/2002.05990v1 |
| https://arxiv.org/pdf/2002.05990v1.pdf | |
| PWC | https://paperswithcode.com/paper/skip-connections-matter-on-the |
| Repo | |
| Framework | |
A Visual Analytics Framework for Reviewing Streaming Performance Data
| Title | A Visual Analytics Framework for Reviewing Streaming Performance Data |
| Authors | Suraj P. Kesavan, Takanori Fujiwara, Jianping Kelvin Li, Caitlin Ross, Misbah Mubarak, Christopher D. Carothers, Robert B. Ross, Kwan-Liu Ma |
| Abstract | Understanding and tuning the performance of extreme-scale parallel computing systems demands a streaming approach due to the computational cost of applying offline algorithms to vast amounts of performance log data. Analyzing large streaming data is challenging because the rate of receiving data and limited time to comprehend data make it difficult for the analysts to sufficiently examine the data without missing important changes or patterns. To support streaming data analysis, we introduce a visual analytic framework comprising of three modules: data management, analysis, and interactive visualization. The data management module collects various computing and communication performance metrics from the monitored system using streaming data processing techniques and feeds the data to the other two modules. The analysis module automatically identifies important changes and patterns at the required latency. In particular, we introduce a set of online and progressive analysis methods for not only controlling the computational costs but also helping analysts better follow the critical aspects of the analysis results. Finally, the interactive visualization module provides the analysts with a coherent view of the changes and patterns in the continuously captured performance data. Through a multi-faceted case study on performance analysis of parallel discrete-event simulation, we demonstrate the effectiveness of our framework for identifying bottlenecks and locating outliers. |
| Tasks | |
| Published | 2020-01-26 |
| URL | https://arxiv.org/abs/2001.09399v1 |
| https://arxiv.org/pdf/2001.09399v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-visual-analytics-framework-for-reviewing |
| Repo | |
| Framework | |
Accelerating Reinforcement Learning with a Directional-Gaussian-Smoothing Evolution Strategy
| Title | Accelerating Reinforcement Learning with a Directional-Gaussian-Smoothing Evolution Strategy |
| Authors | Jiaxing Zhang, Hoang Tran, Guannan Zhang |
| Abstract | Evolution strategy (ES) has been shown great promise in many challenging reinforcement learning (RL) tasks, rivaling other state-of-the-art deep RL methods. Yet, there are two limitations in the current ES practice that may hinder its otherwise further capabilities. First, most current methods rely on Monte Carlo type gradient estimators to suggest search direction, where the policy parameter is, in general, randomly sampled. Due to the low accuracy of such estimators, the RL training may suffer from slow convergence and require more iterations to reach optimal solution. Secondly, the landscape of reward functions can be deceptive and contains many local maxima, causing ES algorithms to prematurely converge and be unable to explore other parts of the parameter space with potentially greater rewards. In this work, we employ a Directional Gaussian Smoothing Evolutionary Strategy (DGS-ES) to accelerate RL training, which is well-suited to address these two challenges with its ability to i) provide gradient estimates with high accuracy, and ii) find nonlocal search direction which lays stress on large-scale variation of the reward function and disregards local fluctuation. Through several benchmark RL tasks demonstrated herein, we show that DGS-ES is highly scalable, possesses superior wall-clock time, and achieves competitive reward scores to other popular policy gradient and ES approaches. |
| Tasks | |
| Published | 2020-02-21 |
| URL | https://arxiv.org/abs/2002.09077v1 |
| https://arxiv.org/pdf/2002.09077v1.pdf | |
| PWC | https://paperswithcode.com/paper/accelerating-reinforcement-learning-with-a |
| Repo | |
| Framework | |
IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval
| Title | IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval |
| Authors | Hui Chen, Guiguang Ding, Xudong Liu, Zijia Lin, Ji Liu, Jungong Han |
| Abstract | Enabling bi-directional retrieval of images and texts is important for understanding the correspondence between vision and language. Existing methods leverage the attention mechanism to explore such correspondence in a fine-grained manner. However, most of them consider all semantics equally and thus align them uniformly, regardless of their diverse complexities. In fact, semantics are diverse (i.e. involving different kinds of semantic concepts), and humans usually follow a latent structure to combine them into understandable languages. It may be difficult to optimally capture such sophisticated correspondences in existing methods. In this paper, to address such a deficiency, we propose an Iterative Matching with Recurrent Attention Memory (IMRAM) method, in which correspondences between images and texts are captured with multiple steps of alignments. Specifically, we introduce an iterative matching scheme to explore such fine-grained correspondence progressively. A memory distillation unit is used to refine alignment knowledge from early steps to later ones. Experiment results on three benchmark datasets, i.e. Flickr8K, Flickr30K, and MS COCO, show that our IMRAM achieves state-of-the-art performance, well demonstrating its effectiveness. Experiments on a practical business advertisement dataset, named \Ads{}, further validates the applicability of our method in practical scenarios. |
| Tasks | |
| Published | 2020-03-08 |
| URL | https://arxiv.org/abs/2003.03772v1 |
| https://arxiv.org/pdf/2003.03772v1.pdf | |
| PWC | https://paperswithcode.com/paper/imram-iterative-matching-with-recurrent |
| Repo | |
| Framework | |
Weighted Meta-Learning
| Title | Weighted Meta-Learning |
| Authors | Diana Cai, Rishit Sheth, Lester Mackey, Nicolo Fusi |
| Abstract | Meta-learning leverages related source tasks to learn an initialization that can be quickly fine-tuned to a target task with limited labeled examples. However, many popular meta-learning algorithms, such as model-agnostic meta-learning (MAML), only assume access to the target samples for fine-tuning. In this work, we provide a general framework for meta-learning based on weighting the loss of different source tasks, where the weights are allowed to depend on the target samples. In this general setting, we provide upper bounds on the distance of the weighted empirical risk of the source tasks and expected target risk in terms of an integral probability metric (IPM) and Rademacher complexity, which apply to a number of meta-learning settings including MAML and a weighted MAML variant. We then develop a learning algorithm based on minimizing the error bound with respect to an empirical IPM, including a weighted MAML algorithm, $\alpha$-MAML. Finally, we demonstrate empirically on several regression problems that our weighted meta-learning algorithm is able to find better initializations than uniformly-weighted meta-learning algorithms, such as MAML. |
| Tasks | Meta-Learning |
| Published | 2020-03-20 |
| URL | https://arxiv.org/abs/2003.09465v1 |
| https://arxiv.org/pdf/2003.09465v1.pdf | |
| PWC | https://paperswithcode.com/paper/weighted-meta-learning |
| Repo | |
| Framework | |
Generalization and Representational Limits of Graph Neural Networks
| Title | Generalization and Representational Limits of Graph Neural Networks |
| Authors | Vikas K. Garg, Stefanie Jegelka, Tommi Jaakkola |
| Abstract | We address two fundamental questions about graph neural networks (GNNs). First, we prove that several important graph properties cannot be computed by GNNs that rely entirely on local information. Such GNNs include the standard message passing models, and more powerful spatial variants that exploit local graph structure (e.g., via relative orientation of messages, or local port ordering) to distinguish neighbors of each node. Our treatment includes a novel graph-theoretic formalism. Second, we provide the first data dependent generalization bounds for message passing GNNs. This analysis explicitly accounts for the local permutation invariance of GNNs. Our bounds are much tighter than existing VC-dimension based guarantees for GNNs, and are comparable to Rademacher bounds for recurrent neural networks. |
| Tasks | |
| Published | 2020-02-14 |
| URL | https://arxiv.org/abs/2002.06157v1 |
| https://arxiv.org/pdf/2002.06157v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalization-and-representational-limits-of |
| Repo | |
| Framework | |
HAM: Hybrid Associations Model with Pooling for Sequential Recommendation
| Title | HAM: Hybrid Associations Model with Pooling for Sequential Recommendation |
| Authors | Bo Peng, Zhiyun Ren, Srinivasan Parthasarathy, Xia Ning |
| Abstract | We developed a hybrid associations model (HAM) to generate sequential recommendations using two factors: 1) users’ long-term preferences and 2) sequential, both high-order and low-order association patterns in the users’ most recent purchases/ratings. HAM uses simplistic pooling to represent a set of items in the associations. We compare HAM with three the most recent, state-of-the-art methods on six public benchmark datasets in three different experimental settings. Our experimental results demonstrate that HAM significantly outperforms the state of the art in all the experimental settings, with an improvement as high as 27.90%. |
| Tasks | |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.11890v1 |
| https://arxiv.org/pdf/2002.11890v1.pdf | |
| PWC | https://paperswithcode.com/paper/ham-hybrid-associations-model-with-pooling |
| Repo | |
| Framework | |
Electrocardiogram Generation and Feature Extraction Using a Variational Autoencoder
| Title | Electrocardiogram Generation and Feature Extraction Using a Variational Autoencoder |
| Authors | V. V. Kuznetsov, V. A. Moskalenko, N. Yu. Zolotykh |
| Abstract | We propose a method for generating an electrocardiogram (ECG) signal for one cardiac cycle using a variational autoencoder. Using this method we extracted a vector of new 25 features, which in many cases can be interpreted. The generated ECG has quite natural appearance. The low value of the Maximum Mean Discrepancy metric, 0.00383, indicates good quality of ECG generation too. The extracted new features will help to improve the quality of automatic diagnostics of cardiovascular diseases. Also, generating new synthetic ECGs will allow us to solve the issue of the lack of labeled ECG for use them in supervised learning. |
| Tasks | |
| Published | 2020-02-01 |
| URL | https://arxiv.org/abs/2002.00254v1 |
| https://arxiv.org/pdf/2002.00254v1.pdf | |
| PWC | https://paperswithcode.com/paper/electrocardiogram-generation-and-feature |
| Repo | |
| Framework | |
Markov Chain Monte-Carlo Phylogenetic Inference Construction in Computational Historical Linguistics
| Title | Markov Chain Monte-Carlo Phylogenetic Inference Construction in Computational Historical Linguistics |
| Authors | Tianyi Ni |
| Abstract | More and more languages in the world are under study nowadays, as a result, the traditional way of historical linguistics study is facing some challenges. For example, the linguistic comparative research among languages needs manual annotation, which becomes more and more impossible with the increasing amount of language data coming out all around the world. Although it could hardly replace linguists work, the automatic computational methods have been taken into consideration and it can help people reduce their workload. One of the most important work in historical linguistics is word comparison from different languages and find the cognate words for them, which means people try to figure out if the two languages are related to each other or not. In this paper, I am going to use computational method to cluster the languages and use Markov Chain Monte Carlo (MCMC) method to build the language typology relationship tree based on the clusters. |
| Tasks | |
| Published | 2020-02-22 |
| URL | https://arxiv.org/abs/2002.09637v2 |
| https://arxiv.org/pdf/2002.09637v2.pdf | |
| PWC | https://paperswithcode.com/paper/markov-chain-monte-carlo-phylogenetic |
| Repo | |
| Framework | |
