Paper Group ANR 1371
A Generalization Error Bound for Multi-class Domain Generalization. MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation. Fully Using Classifiers for Weakly Supervised Semantic Segmentation with Modified Cues. Tag Recommendation by Word-Level Tag Sequence Modeling. A Relation Extraction Approach for Clinical Decision Support. Modality to …
A Generalization Error Bound for Multi-class Domain Generalization
| Title | A Generalization Error Bound for Multi-class Domain Generalization |
| Authors | Aniket Anand Deshmukh, Yunwen Lei, Srinagesh Sharma, Urun Dogan, James W. Cutler, Clayton Scott |
| Abstract | Domain generalization is the problem of assigning labels to an unlabeled data set, given several similar data sets for which labels have been provided. Despite considerable interest in this problem over the last decade, there has been no theoretical analysis in the setting of multi-class classification. In this work, we study a kernel-based learning algorithm and establish a generalization error bound that scales logarithmically in the number of classes, matching state-of-the-art bounds for multi-class classification in the conventional learning setting. We also demonstrate empirically that the proposed algorithm achieves significant performance gains compared to a pooling strategy. |
| Tasks | Domain Generalization |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10392v1 |
| https://arxiv.org/pdf/1905.10392v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-generalization-error-bound-for-multi-class |
| Repo | |
| Framework | |
MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation
| Title | MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation |
| Authors | Abhay Kumar, Nishant Jain, Suraj Tripathi, Chirag Singh, Kamal Krishna |
| Abstract | We propose a Multi-Task Learning (MTL) paradigm based deep neural network architecture, called MTCNet (Multi-Task Crowd Network) for crowd density and count estimation. Crowd count estimation is challenging due to the non-uniform scale variations and the arbitrary perspective of an individual image. The proposed model has two related tasks, with Crowd Density Estimation as the main task and Crowd-Count Group Classification as the auxiliary task. The auxiliary task helps in capturing the relevant scale-related information to improve the performance of the main task. The main task model comprises two blocks: VGG-16 front-end for feature extraction and a dilated Convolutional Neural Network for density map generation. The auxiliary task model shares the same front-end as the main task, followed by a CNN classifier. Our proposed network achieves 5.8% and 14.9% lower Mean Absolute Error (MAE) than the state-of-the-art methods on ShanghaiTech dataset without using any data augmentation. Our model also outperforms with 10.5% lower MAE on UCF_CC_50 dataset. |
| Tasks | Data Augmentation, Density Estimation, Multi-Task Learning |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.08652v1 |
| https://arxiv.org/pdf/1908.08652v1.pdf | |
| PWC | https://paperswithcode.com/paper/mtcnet-multi-task-learning-paradigm-for-crowd |
| Repo | |
| Framework | |
Fully Using Classifiers for Weakly Supervised Semantic Segmentation with Modified Cues
| Title | Fully Using Classifiers for Weakly Supervised Semantic Segmentation with Modified Cues |
| Authors | Ting Sun, Lei Tai, Zhihan Gao, Ming Liu, Dit-Yan Yeung |
| Abstract | This paper proposes a novel weakly-supervised semantic segmentation method using image-level label only. The class-specific activation maps from the well-trained classifiers are used as cues to train a segmentation network. The well-known defects of these cues are coarseness and incompleteness. We use super-pixel to refine them, and fuse the cues extracted from both a color image trained classifier and a gray image trained classifier to compensate for their incompleteness. The conditional random field is adapted to regulate the training process and to refine the outputs further. Besides initializing the segmentation network, the previously trained classifier is also used in the testing phase to suppress the non-existing classes. Experimental results on the PASCAL VOC 2012 dataset illustrate the effectiveness of our method. |
| Tasks | Semantic Segmentation, Weakly-Supervised Semantic Segmentation |
| Published | 2019-04-03 |
| URL | https://arxiv.org/abs/1904.01749v2 |
| https://arxiv.org/pdf/1904.01749v2.pdf | |
| PWC | https://paperswithcode.com/paper/fully-using-classifiers-for-weakly-supervised |
| Repo | |
| Framework | |
Tag Recommendation by Word-Level Tag Sequence Modeling
| Title | Tag Recommendation by Word-Level Tag Sequence Modeling |
| Authors | Xuewen Shi, Heyan Huang, Shuyang Zhao, Ping Jian, Yi-Kun Tang |
| Abstract | In this paper, we transform tag recommendation into a word-based text generation problem and introduce a sequence-to-sequence model. The model inherits the advantages of LSTM-based encoder for sequential modeling and attention-based decoder with local positional encodings for learning relations globally. Experimental results on Zhihu datasets illustrate the proposed model outperforms other state-of-the-art text classification based methods. |
| Tasks | Text Classification, Text Generation |
| Published | 2019-11-30 |
| URL | https://arxiv.org/abs/1912.00113v1 |
| https://arxiv.org/pdf/1912.00113v1.pdf | |
| PWC | https://paperswithcode.com/paper/tag-recommendation-by-word-level-tag-sequence |
| Repo | |
| Framework | |
A Relation Extraction Approach for Clinical Decision Support
| Title | A Relation Extraction Approach for Clinical Decision Support |
| Authors | Maristella Agosti, Giorgio Maria Di Nunzio, Stefano Marchesin, Gianmaria Silvello |
| Abstract | In this paper, we investigate how semantic relations between concepts extracted from medical documents can be employed to improve the retrieval of medical literature. Semantic relations explicitly represent relatedness between concepts and carry high informative power that can be leveraged to improve the effectiveness of retrieval functionalities of clinical decision support systems. We present preliminary results and show how relations are able to provide a sizable increase of the precision for several topics, albeit having no impact on others. We then discuss some future directions to minimize the impact of negative results while maximizing the impact of good results. |
| Tasks | Relation Extraction |
| Published | 2019-05-03 |
| URL | https://arxiv.org/abs/1905.01257v1 |
| https://arxiv.org/pdf/1905.01257v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-relation-extraction-approach-for-clinical |
| Repo | |
| Framework | |
Modality to Modality Translation: An Adversarial Representation Learning and Graph Fusion Network for Multimodal Fusion
| Title | Modality to Modality Translation: An Adversarial Representation Learning and Graph Fusion Network for Multimodal Fusion |
| Authors | Sijie Mai, Haifeng Hu, Songlong Xing |
| Abstract | Learning joint embedding space for various modalities is of vital importance for multimodal fusion. Mainstream modality fusion approaches fail to achieve this goal, leaving a modality gap which heavily affects cross-modal fusion. In this paper, we propose a novel adversarial encoder-decoder-classifier framework to learn a modality-invariant embedding space. Since the distributions of various modalities vary in nature, to reduce the modality gap, we translate the distributions of source modalities into that of target modality via their respective encoders using adversarial training. Furthermore, we exert additional constraints on embedding space by introducing reconstruction loss and classification loss. Then we fuse the encoded representations using hierarchical graph neural network which explicitly explores unimodal, bimodal and trimodal interactions in multi-stage. Our method achieves state-of-the-art performance on multiple datasets. Visualization of the learned embeddings suggests that the joint embedding space learned by our method is discriminative. |
| Tasks | Representation Learning |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07848v3 |
| https://arxiv.org/pdf/1911.07848v3.pdf | |
| PWC | https://paperswithcode.com/paper/modality-to-modality-translation-an |
| Repo | |
| Framework | |
Experiments with mmWave Automotive Radar Test-bed
| Title | Experiments with mmWave Automotive Radar Test-bed |
| Authors | Xiangyu Gao, Guanbin Xing, Sumit Roy, Hui Liu |
| Abstract | Millimeter-wave (mmW) radars are being increasingly integrated in commercial vehicles to support new Adaptive Driver Assisted Systems (ADAS) for its ability to provide high accuracy location, velocity, and angle estimates of objects, largely independent of environmental conditions. Such radar sensors not only perform basic functions such as detection and ranging/angular localization, but also provide critical inputs for environmental perception via object recognition and classification. To explore radar-based ADAS applications, we have assembled a lab-scale frequency modulated continuous wave (FMCW) radar test-bed (https://depts.washington.edu/funlab/research) based on Texas Instrument’s (TI) automotive chipset family. In this work, we describe the test-bed components and provide a summary of FMCW radar operational principles. To date, we have created a large raw radar dataset for various objects under controlled scenarios. Thereafter, we apply some radar imaging algorithms to the collected dataset, and present some preliminary results that validate its capabilities in terms of object recognition. |
| Tasks | Object Recognition |
| Published | 2019-12-29 |
| URL | https://arxiv.org/abs/1912.12566v1 |
| https://arxiv.org/pdf/1912.12566v1.pdf | |
| PWC | https://paperswithcode.com/paper/experiments-with-mmwave-automotive-radar-test |
| Repo | |
| Framework | |
The spectral dimension of simplicial complexes: a renormalization group theory
| Title | The spectral dimension of simplicial complexes: a renormalization group theory |
| Authors | Ginestra Bianconi, Sergey N. Dorogovtsev |
| Abstract | Simplicial complexes are increasingly used to study complex system structure and dynamics including diffusion, synchronization and epidemic spreading. The spectral dimension of the graph Laplacian is known to determine the diffusion properties at long time scales. Using the renormalization group here we calculate the spectral dimension of the graph Laplacian of two classes of non-amenable $d$ dimensional simplicial complexes: the Apollonian networks and the pseudo-fractal networks. We analyse the scaling of the spectral dimension with the topological dimension $d$ for $d\to \infty$ and we point out that randomness such as the one present in Network Geometry with Flavor can diminish the value of the spectral dimension of these structures. |
| Tasks | |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.12566v3 |
| https://arxiv.org/pdf/1910.12566v3.pdf | |
| PWC | https://paperswithcode.com/paper/the-spectral-dimension-of-simplicial |
| Repo | |
| Framework | |
On Applying Machine Learning/Object Detection Models for Analysing Digitally Captured Physical Prototypes from Engineering Design Projects
| Title | On Applying Machine Learning/Object Detection Models for Analysing Digitally Captured Physical Prototypes from Engineering Design Projects |
| Authors | Jorgen F. Erichsen, Sampsa Kohtala, Martin Steinert, Torgeir Welo |
| Abstract | While computer vision has received increasing attention in computer science over the last decade, there are few efforts in applying this to leverage engineering design research. Existing datasets and technologies allow researchers to capture and access more observations and video files, hence analysis is becoming a limiting factor. Therefore, this paper is investigating the application of machine learning, namely object detection methods to aid in the analysis of physical porotypes. With access to a large dataset of digitally captured physical prototypes from early-stage development projects (5950 images from 850 prototypes), the authors investigate applications that can be used for analysing this dataset. The authors retrained two pre-trained object detection models from two known frameworks, the TensorFlow Object Detection API and Darknet, using custom image sets of images of physical prototypes. As a result, a proof-of-concept of four trained models are presented; two models for detecting samples of wood-based sheet materials and two models for detecting samples containing microcontrollers. All models are evaluated using standard metrics for object detection model performance and the applicability of using object detection models in engineering design research is discussed. Results indicate that the models can successfully classify the type of material and type of pre-made component, respectively. However, more work is needed to fully integrate object detection models in the engineering design analysis workflow. The authors also extrapolate that the use of object detection for analysing images of physical prototypes will substantially reduce the effort required for analysing large datasets in engineering design research. |
| Tasks | Object Detection |
| Published | 2019-05-07 |
| URL | https://arxiv.org/abs/1905.03697v1 |
| https://arxiv.org/pdf/1905.03697v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503697 |
| Repo | |
| Framework | |
Predicting Time-to-Failure of Plasma Etching Equipment using Machine Learning
| Title | Predicting Time-to-Failure of Plasma Etching Equipment using Machine Learning |
| Authors | Anahid Jalali, Clemens Heistracher, Alexander Schindler, Bernhard Haslhofer, Tanja Nemeth, Robert Glawar, Wilfried Sihn, Peter De Boer |
| Abstract | Predicting unscheduled breakdowns of plasma etching equipment can reduce maintenance costs and production losses in the semiconductor industry. However, plasma etching is a complex procedure and it is hard to capture all relevant equipment properties and behaviors in a single physical model. Machine learning offers an alternative for predicting upcoming machine failures based on relevant data points. In this paper, we describe three different machine learning tasks that can be used for that purpose: (i) predicting Time-To-Failure (TTF), (ii) predicting health state, and (iii) predicting TTF intervals of an equipment. Our results show that trained machine learning models can outperform benchmarks resembling human judgments in all three tasks. This suggests that machine learning offers a viable alternative to currently deployed plasma etching equipment maintenance strategies and decision making processes. |
| Tasks | Decision Making |
| Published | 2019-04-16 |
| URL | http://arxiv.org/abs/1904.07686v1 |
| http://arxiv.org/pdf/1904.07686v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-time-to-failure-of-plasma-etching |
| Repo | |
| Framework | |
Multi-stakeholder Recommendation and its Connection to Multi-sided Fairness
| Title | Multi-stakeholder Recommendation and its Connection to Multi-sided Fairness |
| Authors | Himan Abdollahpouri, Robin Burke |
| Abstract | There is growing research interest in recommendation as a multi-stakeholder problem, one where the interests of multiple parties should be taken into account. This category subsumes some existing well-established areas of recommendation research including reciprocal and group recommendation, but a detailed taxonomy of different classes of multi-stakeholder recommender systems is still lacking. Fairness-aware recommendation has also grown as a research area, but its close connection with multi-stakeholder recommendation is not always recognized. In this paper, we define the most commonly observed classes of multi-stakeholder recommender systems and discuss how different fairness concerns may come into play in such systems. |
| Tasks | Recommendation Systems |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.13158v1 |
| https://arxiv.org/pdf/1907.13158v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-stakeholder-recommendation-and-its |
| Repo | |
| Framework | |
Attention Guided Metal Artifact Correction in MRI using Deep Neural Networks
| Title | Attention Guided Metal Artifact Correction in MRI using Deep Neural Networks |
| Authors | Jee Won Kim, Kinam Kwon, Byungjai Kim, HyunWook Park |
| Abstract | An attention guided scheme for metal artifact correction in MRI using deep neural network is proposed in this paper. The inputs of the networks are two distorted images obtained with dual-polarity readout gradients. With MR image generation module and the additional data consistency loss to the previous work [1], the network is trained to estimate the frequency-shift map, off-resonance map, and attention map. The attention map helps to produce better distortion-corrected images by weighting on more relevant distortion-corrected images where two distortion-corrected images are produced with half of the frequency-shift maps. In this paper, we observed that in a real MRI environment, two distorted images obtained with opposite polarities of readout gradient showed artifacts in a different region. Therefore, we proved that using the attention map was important in that it reduced the residual ripple and pile-up artifacts near metallic implants. |
| Tasks | Image Generation |
| Published | 2019-10-19 |
| URL | https://arxiv.org/abs/1910.08705v1 |
| https://arxiv.org/pdf/1910.08705v1.pdf | |
| PWC | https://paperswithcode.com/paper/attention-guided-metal-artifact-correction-in |
| Repo | |
| Framework | |
Further advantages of data augmentation on convolutional neural networks
| Title | Further advantages of data augmentation on convolutional neural networks |
| Authors | Alex Hernández-García, Peter König |
| Abstract | Data augmentation is a popular technique largely used to enhance the training of convolutional neural networks. Although many of its benefits are well known by deep learning researchers and practitioners, its implicit regularization effects, as compared to popular explicit regularization techniques, such as weight decay and dropout, remain largely unstudied. As a matter of fact, convolutional neural networks for image object classification are typically trained with both data augmentation and explicit regularization, assuming the benefits of all techniques are complementary. In this paper, we systematically analyze these techniques through ablation studies of different network architectures trained with different amounts of training data. Our results unveil a largely ignored advantage of data augmentation: networks trained with just data augmentation more easily adapt to different architectures and amount of training data, as opposed to weight decay and dropout, which require specific fine-tuning of their hyperparameters. |
| Tasks | Data Augmentation, Object Classification |
| Published | 2019-06-26 |
| URL | https://arxiv.org/abs/1906.11052v1 |
| https://arxiv.org/pdf/1906.11052v1.pdf | |
| PWC | https://paperswithcode.com/paper/further-advantages-of-data-augmentation-on |
| Repo | |
| Framework | |
Structural plasticity on an accelerated analog neuromorphic hardware system
| Title | Structural plasticity on an accelerated analog neuromorphic hardware system |
| Authors | Sebastian Billaudelle, Benjamin Cramer, Mihai A. Petrovici, Korbinian Schreiber, David Kappel, Johannes Schemmel, Karlheinz Meier |
| Abstract | In computational neuroscience, as well as in machine learning, neuromorphic devices promise an accelerated and scalable alternative to neural network simulations. Their neural connectivity and synaptic capacity depends on their specific design choices, but is always intrinsically limited. Here, we present a strategy to achieve structural plasticity that optimizes resource allocation under these constraints by constantly rewiring the pre- and postsynaptic partners while keeping the neuronal fan-in constant and the connectome sparse. In our implementation, the algorithm is executed on a custom embedded digital processor that accompanies a mixed-signal substrate consisting of spiking neurons and synapse circuits. We evaluated our proposed algorithm in a simple supervised learning scenario, showing its ability to optimize the network topology with respect to the nature of its training data, as well as its overall computational efficiency. |
| Tasks | |
| Published | 2019-12-27 |
| URL | https://arxiv.org/abs/1912.12047v1 |
| https://arxiv.org/pdf/1912.12047v1.pdf | |
| PWC | https://paperswithcode.com/paper/structural-plasticity-on-an-accelerated |
| Repo | |
| Framework | |
Organization of ML-based product development as per ISO 26262
| Title | Organization of ML-based product development as per ISO 26262 |
| Authors | Krystian Radlak, Piotr Serwa, Michał Szczepankiewicz, Tim Jones |
| Abstract | Machine learning (ML) applications generate a continuous stream of success stories from various domains. ML enables many novel applications, also in a safety-related context. With the advent of Autonomous Driving, ML gets used in automotive domain. In such a context, ML-based systems are safety-related. In the automotive industry, the applicable functional safety standard is ISO 26262, which it does not cover specific aspects of ML. In a safety-related ML project, all ISO 26262 work products are typically necessary and have to be delivered. However, specific aspects of ML (like data set requirements, special analyses for ML) must be addressed within some work products. In this paper, we propose how the organization of a ML project could be done according to ISO 26262 phases, sub-phases and work-products. |
| Tasks | Autonomous Driving |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.05112v1 |
| https://arxiv.org/pdf/1910.05112v1.pdf | |
| PWC | https://paperswithcode.com/paper/organization-of-ml-based-product-development |
| Repo | |
| Framework | |
