Paper Group AWR 145
Enhancing Flood Impact Analysis using Interactive Retrieval of Social Media Images. What, Where and How to Transfer in SAR Target Recognition Based on Deep CNNs. Cumulo: A Dataset for Learning Cloud Classes. Characterizing SLAM Benchmarks and Methods for the Robust Perception Age. Deep Learning for Classification of Hyperspectral Data: A Comparativ …
Enhancing Flood Impact Analysis using Interactive Retrieval of Social Media Images
| Title | Enhancing Flood Impact Analysis using Interactive Retrieval of Social Media Images |
| Authors | Björn Barz, Kai Schröter, Moritz Münch, Bin Yang, Andrea Unger, Doris Dransch, Joachim Denzler |
| Abstract | The analysis of natural disasters such as floods in a timely manner often suffers from limited data due to a coarse distribution of sensors or sensor failures. This limitation could be alleviated by leveraging information contained in images of the event posted on social media platforms, so-called “Volunteered Geographic Information (VGI)". To save the analyst from the need to inspect all images posted online manually, we propose to use content-based image retrieval with the possibility of relevance feedback for retrieving only relevant images of the event to be analyzed. To evaluate this approach, we introduce a new dataset of 3,710 flood images, annotated by domain experts regarding their relevance with respect to three tasks (determining the flooded area, inundation depth, water pollution). We compare several image features and relevance feedback methods on that dataset, mixed with 97,085 distractor images, and are able to improve the precision among the top 100 retrieval results from 55% with the baseline retrieval to 87% after 5 rounds of feedback. |
| Tasks | Content-Based Image Retrieval, Image Retrieval |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.03361v1 |
| https://arxiv.org/pdf/1908.03361v1.pdf | |
| PWC | https://paperswithcode.com/paper/enhancing-flood-impact-analysis-using |
| Repo | https://github.com/cvjena/eu-flood-dataset |
| Framework | none |
What, Where and How to Transfer in SAR Target Recognition Based on Deep CNNs
| Title | What, Where and How to Transfer in SAR Target Recognition Based on Deep CNNs |
| Authors | Zhongling Huang, Zongxu Pan, Bin Lei |
| Abstract | Deep convolutional neural networks (DCNNs) have attracted much attention in remote sensing recently. Compared with the large-scale annotated dataset in natural images, the lack of labeled data in remote sensing becomes an obstacle to train a deep network very well, especially in SAR image interpretation. Transfer learning provides an effective way to solve this problem by borrowing the knowledge from the source task to the target task. In optical remote sensing application, a prevalent mechanism is to fine-tune on an existing model pre-trained with a large-scale natural image dataset, such as ImageNet. However, this scheme does not achieve satisfactory performance for SAR application because of the prominent discrepancy between SAR and optical images. In this paper, we attempt to discuss three issues that are seldom studied before in detail: (1) what network and source tasks are better to transfer to SAR targets, (2) in which layer are transferred features more generic to SAR targets and (3) how to transfer effectively to SAR targets recognition. Based on the analysis, a transitive transfer method via multi-source data with domain adaptation is proposed in this paper to decrease the discrepancy between the source data and SAR targets. Several experiments are conducted on OpenSARShip. The results indicate that the universal conclusions about transfer learning in natural images cannot be completely applied to SAR targets, and the analysis of what and where to transfer in SAR target recognition is helpful to decide how to transfer more effectively. |
| Tasks | Domain Adaptation, Transfer Learning |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01379v1 |
| https://arxiv.org/pdf/1906.01379v1.pdf | |
| PWC | https://paperswithcode.com/paper/what-where-and-how-to-transfer-in-sar-target |
| Repo | https://github.com/Alien9427/SAR_specific_models |
| Framework | pytorch |
Cumulo: A Dataset for Learning Cloud Classes
| Title | Cumulo: A Dataset for Learning Cloud Classes |
| Authors | Valentina Zantedeschi, Fabrizio Falasca, Alyson Douglas, Richard Strange, Matt J. Kusner, Duncan Watson-Parris |
| Abstract | One of the greatest sources of uncertainty in future climate projections comes from limitations in modelling clouds and in understanding how different cloud types interact with the climate system. A key first step in reducing this uncertainty is to accurately classify cloud types at high spatial and temporal resolution. In this paper, we introduce Cumulo, a benchmark dataset for training and evaluating global cloud classification models. It consists of one year of 1km resolution MODIS hyperspectral imagery merged with pixel-width ‘tracks’ of CloudSat cloud labels. Bringing these complementary datasets together is a crucial first step, enabling the Machine-Learning community to develop innovative new techniques which could greatly benefit the Climate community. To showcase Cumulo, we provide baseline performance analysis using an invertible flow generative model (IResNet), which further allows us to discover new sub-classes for a given cloud class by exploring the latent space. To compare methods, we introduce a set of evaluation criteria, to identify models that are not only accurate, but also physically-realistic. |
| Tasks | |
| Published | 2019-11-05 |
| URL | https://arxiv.org/abs/1911.04227v1 |
| https://arxiv.org/pdf/1911.04227v1.pdf | |
| PWC | https://paperswithcode.com/paper/cumulo-a-dataset-for-learning-cloud-classes |
| Repo | https://github.com/FrontierDevelopmentLab/CUMULO |
| Framework | none |
Characterizing SLAM Benchmarks and Methods for the Robust Perception Age
| Title | Characterizing SLAM Benchmarks and Methods for the Robust Perception Age |
| Authors | Wenkai Ye, Yipu Zhao, Patricio A. Vela |
| Abstract | The diversity of SLAM benchmarks affords extensive testing of SLAM algorithms to understand their performance, individually or in relative terms. The ad-hoc creation of these benchmarks does not necessarily illuminate the particular weak points of a SLAM algorithm when performance is evaluated. In this paper, we propose to use a decision tree to identify challenging benchmark properties for state-of-the-art SLAM algorithms and important components within the SLAM pipeline regarding their ability to handle these challenges. Establishing what factors of a particular sequence lead to track failure or degradation relative to these characteristics is important if we are to arrive at a strong understanding for the core computational needs of a robust SLAM algorithm. Likewise, we argue that it is important to profile the computational performance of the individual SLAM components for use when benchmarking. In particular, we advocate the use of time-dilation during ROS bag playback, or what we refer to as slo-mo playback. Using slo-mo to benchmark SLAM instantiations can provide clues to how SLAM implementations should be improved at the computational component level. Three prevalent VO/SLAM algorithms and two low-latency algorithms of our own are tested on selected typical sequences, which are generated from benchmark characterization, to further demonstrate the benefits achieved from computationally efficient components. |
| Tasks | |
| Published | 2019-05-19 |
| URL | https://arxiv.org/abs/1905.07808v1 |
| https://arxiv.org/pdf/1905.07808v1.pdf | |
| PWC | https://paperswithcode.com/paper/characterizing-slam-benchmarks-and-methods |
| Repo | https://github.com/ivalab/Benchmarking_SLAM |
| Framework | none |
Deep Learning for Classification of Hyperspectral Data: A Comparative Review
| Title | Deep Learning for Classification of Hyperspectral Data: A Comparative Review |
| Authors | Nicolas Audebert, Bertrand Saux, Sébastien Lefèvre |
| Abstract | In recent years, deep learning techniques revolutionized the way remote sensing data are processed. Classification of hyperspectral data is no exception to the rule, but has intrinsic specificities which make application of deep learning less straightforward than with other optical data. This article presents a state of the art of previous machine learning approaches, reviews the various deep learning approaches currently proposed for hyperspectral classification, and identifies the problems and difficulties which arise to implement deep neural networks for this task. In particular, the issues of spatial and spectral resolution, data volume, and transfer of models from multimedia images to hyperspectral data are addressed. Additionally, a comparative study of various families of network architectures is provided and a software toolbox is publicly released to allow experimenting with these methods. 1 This article is intended for both data scientists with interest in hyperspectral data and remote sensing experts eager to apply deep learning techniques to their own dataset. |
| Tasks | |
| Published | 2019-04-24 |
| URL | http://arxiv.org/abs/1904.10674v1 |
| http://arxiv.org/pdf/1904.10674v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-classification-of-1 |
| Repo | https://github.com/nshaud/DeepHyperX |
| Framework | pytorch |
Content-Consistent Generation of Realistic Eyes with Style
| Title | Content-Consistent Generation of Realistic Eyes with Style |
| Authors | Marcel Bühler, Seonwook Park, Shalini De Mello, Xucong Zhang, Otmar Hilliges |
| Abstract | Accurately labeled real-world training data can be scarce, and hence recent works adapt, modify or generate images to boost target datasets. However, retaining relevant details from input data in the generated images is challenging and failure could be critical to the performance on the final task. In this work, we synthesize person-specific eye images that satisfy a given semantic segmentation mask (content), while following the style of a specified person from only a few reference images. We introduce two approaches, (a) one used to win the OpenEDS Synthetic Eye Generation Challenge at ICCV 2019, and (b) a principled approach to solving the problem involving simultaneous injection of style and content information at multiple scales. Our implementation is available at https://github.com/mcbuehler/Seg2Eye. |
| Tasks | Semantic Segmentation |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03346v1 |
| https://arxiv.org/pdf/1911.03346v1.pdf | |
| PWC | https://paperswithcode.com/paper/content-consistent-generation-of-realistic |
| Repo | https://github.com/mcbuehler/Seg2Eye |
| Framework | pytorch |
AdaNet: A Scalable and Flexible Framework for Automatically Learning Ensembles
| Title | AdaNet: A Scalable and Flexible Framework for Automatically Learning Ensembles |
| Authors | Charles Weill, Javier Gonzalvo, Vitaly Kuznetsov, Scott Yang, Scott Yak, Hanna Mazzawi, Eugen Hotaj, Ghassen Jerfel, Vladimir Macko, Ben Adlam, Mehryar Mohri, Corinna Cortes |
| Abstract | AdaNet is a lightweight TensorFlow-based (Abadi et al., 2015) framework for automatically learning high-quality ensembles with minimal expert intervention. Our framework is inspired by the AdaNet algorithm (Cortes et al., 2017) which learns the structure of a neural network as an ensemble of subnetworks. We designed it to: (1) integrate with the existing TensorFlow ecosystem, (2) offer sensible default search spaces to perform well on novel datasets, (3) present a flexible API to utilize expert information when available, and (4) efficiently accelerate training with distributed CPU, GPU, and TPU hardware. The code is open-source and available at: https://github.com/tensorflow/adanet. |
| Tasks | Neural Architecture Search |
| Published | 2019-04-30 |
| URL | http://arxiv.org/abs/1905.00080v1 |
| http://arxiv.org/pdf/1905.00080v1.pdf | |
| PWC | https://paperswithcode.com/paper/adanet-a-scalable-and-flexible-framework-for |
| Repo | https://github.com/tensorflow/adanet |
| Framework | tf |
Working Hard or Hardly Working: Challenges of Integrating Typology into Neural Dependency Parsers
| Title | Working Hard or Hardly Working: Challenges of Integrating Typology into Neural Dependency Parsers |
| Authors | Adam Fisch, Jiang Guo, Regina Barzilay |
| Abstract | This paper explores the task of leveraging typology in the context of cross-lingual dependency parsing. While this linguistic information has shown great promise in pre-neural parsing, results for neural architectures have been mixed. The aim of our investigation is to better understand this state-of-the-art. Our main findings are as follows: 1) The benefit of typological information is derived from coarsely grouping languages into syntactically-homogeneous clusters rather than from learning to leverage variations along individual typological dimensions in a compositional manner; 2) Typology consistent with the actual corpus statistics yields better transfer performance; 3) Typological similarity is only a rough proxy of cross-lingual transferability with respect to parsing. |
| Tasks | Dependency Parsing |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09279v1 |
| https://arxiv.org/pdf/1909.09279v1.pdf | |
| PWC | https://paperswithcode.com/paper/working-hard-or-hardly-working-challenges-of |
| Repo | https://github.com/ajfisch/TypologyParser |
| Framework | pytorch |
Interpretable Counterfactual Explanations Guided by Prototypes
| Title | Interpretable Counterfactual Explanations Guided by Prototypes |
| Authors | Arnaud Van Looveren, Janis Klaise |
| Abstract | We propose a fast, model agnostic method for finding interpretable counterfactual explanations of classifier predictions by using class prototypes. We show that class prototypes, obtained using either an encoder or through class specific k-d trees, significantly speed up the the search for counterfactual instances and result in more interpretable explanations. We introduce two novel metrics to quantitatively evaluate local interpretability at the instance level. We use these metrics to illustrate the effectiveness of our method on an image and tabular dataset, respectively MNIST and Breast Cancer Wisconsin (Diagnostic). The method also eliminates the computational bottleneck that arises because of numerical gradient evaluation for $\textit{black box}$ models. |
| Tasks | |
| Published | 2019-07-03 |
| URL | https://arxiv.org/abs/1907.02584v2 |
| https://arxiv.org/pdf/1907.02584v2.pdf | |
| PWC | https://paperswithcode.com/paper/interpretable-counterfactual-explanations |
| Repo | https://github.com/SeldonIO/alibi |
| Framework | tf |
Employing Genetic Algorithm as an Efficient Alternative to Parameter Sweep Based Multi-Layer Thickness Optimization in Solar Cells
| Title | Employing Genetic Algorithm as an Efficient Alternative to Parameter Sweep Based Multi-Layer Thickness Optimization in Solar Cells |
| Authors | Premkumar Vincent, Gwenaelle Cunha Sergio, Jaewon Jang, In Man Kang, Philippe Lang, Hyeok Kim, Jaehoon Park, Muhan Choi, Minho Lee, Jin-Hyuk Bae |
| Abstract | Conventional solar cells are predominately designed similar to a stacked structure. Optimizing the layer thicknesses in this stack structure is crucial to extract the best efficiency of the solar cell. The commonplace method used in optimization simulations, such as for optimizing the optical spacer layers’ thicknesses, is the parameter sweep. Our experiments show that the introduction of genetic algorithm based method results in a significantly faster and accurate search method when compared to brute-force parameter sweep method in both single and multi-layer optimization. While other sweep methods can also outperform the brute-force method, they do not consistently exhibit $100%$ accuracy in the optimized results like our genetic algorithm. Our best case scenario was observed to utilize 57.9% less simulations than brute-force method. |
| Tasks | |
| Published | 2019-09-14 |
| URL | https://arxiv.org/abs/1909.06447v2 |
| https://arxiv.org/pdf/1909.06447v2.pdf | |
| PWC | https://paperswithcode.com/paper/genetic-algorithm-for-more-efficient-multi |
| Repo | https://github.com/gcunhase/GeneticAlgorithm-SolarCells |
| Framework | none |
Safe Augmentation: Learning Task-Specific Transformations from Data
| Title | Safe Augmentation: Learning Task-Specific Transformations from Data |
| Authors | Irynei Baran, Orest Kupyn, Arseny Kravchenko |
| Abstract | Data augmentation is widely used as a part of the training process applied to deep learning models, especially in the computer vision domain. Currently, common data augmentation techniques are designed manually. Therefore they require expert knowledge and time. Moreover, augmentations are dataset-specific, and the optimal augmentations set on a specific dataset has limited transferability to others. We present a simple and explainable method called $\textbf{Safe Augmentation}$ that can learn task-specific data augmentation techniques that do not change the data distribution and improve the generalization of the model. We propose to use safe augmentation in two ways: for model fine-tuning and along with other augmentation techniques. Our method is model-agnostic, easy to implement, and achieves better accuracy on CIFAR-10, CIFAR-100, SVHN, Tiny ImageNet, and Cityscapes datasets comparing to baseline augmentation techniques. The code is available at $\href{https://github.com/Irynei/SafeAugmentation}{https://github.com/Irynei/SafeAugmentation}$. |
| Tasks | Data Augmentation |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.12896v1 |
| https://arxiv.org/pdf/1907.12896v1.pdf | |
| PWC | https://paperswithcode.com/paper/safe-augmentation-learning-task-specific |
| Repo | https://github.com/Irynei/SafeAugmentation |
| Framework | pytorch |
Needles in Haystacks: On Classifying Tiny Objects in Large Images
| Title | Needles in Haystacks: On Classifying Tiny Objects in Large Images |
| Authors | Nick Pawlowski, Suvrat Bhooshan, Nicolas Ballas, Francesco Ciompi, Ben Glocker, Michal Drozdzal |
| Abstract | In some important computer vision domains, such as medical or hyperspectral imaging, we care about the classification of tiny objects in large images. However, most Convolutional Neural Networks (CNNs) for image classification were developed using biased datasets that contain large objects, in mostly central image positions. To assess whether classical CNN architectures work well for tiny object classification we build a comprehensive testbed containing two datasets: one derived from MNIST digits and one from histopathology images. This testbed allows controlled experiments to stress-test CNN architectures with a broad spectrum of signal-to-noise ratios. Our observations indicate that: (1) There exists a limit to signal-to-noise below which CNNs fail to generalize and that this limit is affected by dataset size - more data leading to better performances; however, the amount of training data required for the model to generalize scales rapidly with the inverse of the object-to-image ratio (2) in general, higher capacity models exhibit better generalization; (3) when knowing the approximate object sizes, adapting receptive field is beneficial; and (4) for very small signal-to-noise ratio the choice of global pooling operation affects optimization, whereas for relatively large signal-to-noise values, all tested global pooling operations exhibit similar performance. |
| Tasks | Image Classification, Object Classification |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.06037v2 |
| https://arxiv.org/pdf/1908.06037v2.pdf | |
| PWC | https://paperswithcode.com/paper/needles-in-haystacks-on-classifying-tiny |
| Repo | https://github.com/facebookresearch/Needles-in-Haystacks |
| Framework | pytorch |
Linear Support Vector Regression with Linear Constraints
| Title | Linear Support Vector Regression with Linear Constraints |
| Authors | Quentin Klopfenstein, Samuel Vaiter |
| Abstract | This paper studies the addition of linear constraints to the Support Vector Regression (SVR) when the kernel is linear. Adding those constraints into the problem allows to add prior knowledge on the estimator obtained, such as finding probability vector or monotone data. We propose a generalization of the Sequential Minimal Optimization (SMO) algorithm for solving the optimization problem with linear constraints and prove its convergence. Then, practical performances of this estimator are shown on simulated and real datasets with different settings: non negative regression, regression onto the simplex for biomedical data and isotonic regression for weather forecast. |
| Tasks | |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02306v1 |
| https://arxiv.org/pdf/1911.02306v1.pdf | |
| PWC | https://paperswithcode.com/paper/linear-support-vector-regression-with-linear |
| Repo | https://github.com/Klopfe/LSVR |
| Framework | none |
SMURFF: a High-Performance Framework for Matrix Factorization
| Title | SMURFF: a High-Performance Framework for Matrix Factorization |
| Authors | Tom Vander Aa, Imen Chakroun, Thomas J. Ashby, Jaak Simm, Adam Arany, Yves Moreau, Thanh Le Van, José Felipe Golib Dzib, Jörg Wegner, Vladimir Chupakhin, Hugo Ceulemans, Roel Wuyts, Wilfried Verachtert |
| Abstract | Bayesian Matrix Factorization (BMF) is a powerful technique for recommender systems because it produces good results and is relatively robust against overfitting. Yet BMF is more computationally intensive and thus more challenging to implement for large datasets. In this work we present SMURFF a high-performance feature-rich framework to compose and construct different Bayesian matrix-factorization methods. The framework has been successfully used in to do large scale runs of compound-activity prediction. SMURFF is available as open-source and can be used both on a supercomputer and on a desktop or laptop machine. Documentation and several examples are provided as Jupyter notebooks using SMURFF’s high-level Python API. |
| Tasks | Activity Prediction, Recommendation Systems |
| Published | 2019-04-04 |
| URL | https://arxiv.org/abs/1904.02514v3 |
| https://arxiv.org/pdf/1904.02514v3.pdf | |
| PWC | https://paperswithcode.com/paper/smurff-a-high-performance-framework-for |
| Repo | https://github.com/ExaScience/smurff |
| Framework | none |
MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks
| Title | MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks |
| Authors | Chen Ma, Chenxu Zhao, Hailin Shi, Li Chen, Junhai Yong, Dan Zeng |
| Abstract | Deep neural networks (DNNs) are vulnerable to adversarial attack which is maliciously implemented by adding human-imperceptible perturbation to images and thus leads to incorrect prediction. Existing studies have proposed various methods to detect the new adversarial attacks. However, new attack methods keep evolving constantly and yield new adversarial examples to bypass the existing detectors. It needs to collect tens of thousands samples to train detectors, while the new attacks evolve much more frequently than the high-cost data collection. Thus, this situation leads the newly evolved attack samples to remain in small scales. To solve such few-shot problem with the evolving attack, we propose a meta-learning based robust detection method to detect new adversarial attacks with limited examples. Specifically, the learning consists of a double-network framework: a task-dedicated network and a master network which alternatively learn the detection capability for either seen attack or a new attack. To validate the effectiveness of our approach, we construct the benchmarks with few-shot-fashion protocols based on three conventional datasets, i.e. CIFAR-10, MNIST and Fashion-MNIST. Comprehensive experiments are conducted on them to verify the superiority of our approach with respect to the traditional adversarial attack detection methods. |
| Tasks | Adversarial Attack, Meta-Learning |
| Published | 2019-08-06 |
| URL | https://arxiv.org/abs/1908.02199v1 |
| https://arxiv.org/pdf/1908.02199v1.pdf | |
| PWC | https://paperswithcode.com/paper/metaadvdet-towards-robust-detection-of |
| Repo | https://github.com/sharpstill/MetaAdvDet |
| Framework | pytorch |
