Paper Group AWR 175
Improving Document Classification with Multi-Sense Embeddings. Cost-Sensitive Diagnosis and Learning Leveraging Public Health Data. Retinal Vessel Segmentation based on Fully Convolutional Networks. Quantization-Based Regularization for Autoencoders. Feature Selective Anchor-Free Module for Single-Shot Object Detection. Additive Noise Annealing and …
Improving Document Classification with Multi-Sense Embeddings
| Title | Improving Document Classification with Multi-Sense Embeddings |
| Authors | Vivek Gupta, Ankit Saw, Pegah Nokhiz, Harshit Gupta, Partha Talukdar |
| Abstract | Efficient representation of text documents is an important building block in many NLP tasks. Research on long text categorization has shown that simple weighted averaging of word vectors for sentence representation often outperforms more sophisticated neural models. Recently proposed Sparse Composite Document Vector (SCDV) (Mekala et. al, 2017) extends this approach from sentences to documents using soft clustering over word vectors. However, SCDV disregards the multi-sense nature of words, and it also suffers from the curse of higher dimensionality. In this work, we address these shortcomings and propose SCDV-MS. SCDV-MS utilizes multi-sense word embeddings and learns a lower dimensional manifold. Through extensive experiments on multiple real-world datasets, we show that SCDV-MS embeddings outperform previous state-of-the-art embeddings on multi-class and multi-label text categorization tasks. Furthermore, SCDV-MS embeddings are more efficient than SCDV in terms of time and space complexity on textual classification tasks. |
| Tasks | Document Classification, Text Categorization, Word Embeddings |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07918v1 |
| https://arxiv.org/pdf/1911.07918v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-document-classification-with-multi |
| Repo | https://github.com/vgupta123/SCDV-MS |
| Framework | none |
Cost-Sensitive Diagnosis and Learning Leveraging Public Health Data
| Title | Cost-Sensitive Diagnosis and Learning Leveraging Public Health Data |
| Authors | Mohammad Kachuee, Kimmo Karkkainen, Orpaz Goldstein, Davina Zamanzadeh, Majid Sarrafzadeh |
| Abstract | Traditionally, machine learning algorithms rely on the assumption that all features of a given dataset are available for free. However, there are many concerns such as monetary data collection costs, patient discomfort in medical procedures, and privacy impacts of data collection that require careful consideration in any real-world health analytics system. An efficient solution would only acquire a subset of features based on the value it provides while considering acquisition costs. Moreover, datasets that provide feature costs are very limited, especially in healthcare. In this paper, we provide a health dataset as well as a method for assigning feature costs based on the total level of inconvenience asking for each feature entails. Furthermore, based on the suggested dataset, we provide a comparison of recent and state-of-the-art approaches to cost-sensitive feature acquisition and learning. Specifically, we analyze the performance of major sensitivity-based and reinforcement learning based methods in the literature on three different problems in the health domain, including diabetes, heart disease, and hypertension classification. |
| Tasks | |
| Published | 2019-02-19 |
| URL | https://arxiv.org/abs/1902.07102v2 |
| https://arxiv.org/pdf/1902.07102v2.pdf | |
| PWC | https://paperswithcode.com/paper/nutrition-and-health-data-for-cost-sensitive |
| Repo | https://github.com/mkachuee/Opportunistic |
| Framework | pytorch |
Retinal Vessel Segmentation based on Fully Convolutional Networks
| Title | Retinal Vessel Segmentation based on Fully Convolutional Networks |
| Authors | Zhengyuan Liu |
| Abstract | The morphological attributes of retinal vessels, such as length, width, tortuosity and branching pattern and angles, play an important role in diagnosis, screening, treatment, and evaluation of various cardiovascular and ophthalmologic diseases such as diabetes, hypertension and arteriosclerosis. The crucial step before extracting these morphological characteristics of retinal vessels from retinal fundus images is vessel segmentation. In this work, we propose a method for retinal vessel segmentation based on fully convolutional networks. Thousands of patches are extracted from each retinal image and then fed into the network, and data argumentation is applied by rotating extracted patches. Two architectures of fully convolutional networks, U-Net and LadderNet, are used for vessel segmentation. The performance of our method is evaluated on three public datasets: DRIVE, STARE, and CHASE_DB1. Experimental results of our method show superior performance compared to recent state-of-the-art methods. |
| Tasks | Retinal Vessel Segmentation |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.09915v1 |
| https://arxiv.org/pdf/1911.09915v1.pdf | |
| PWC | https://paperswithcode.com/paper/retinal-vessel-segmentation-based-on-fully-1 |
| Repo | https://github.com/americofmoliveira/VesselSegmentation_ESWA |
| Framework | none |
Quantization-Based Regularization for Autoencoders
| Title | Quantization-Based Regularization for Autoencoders |
| Authors | Hanwei Wu, Markus Flierl |
| Abstract | Autoencoders and their variations provide unsupervised models for learning low-dimensional representations for downstream tasks. Without proper regularization, autoencoder models are susceptible to the overfitting problem and the so-called posterior collapse phenomenon. In this paper, we introduce a quantization-based regularizer in the bottleneck stage of autoencoder models to learn meaningful latent representations. We combine both perspectives of Vector Quantized-Variational AutoEncoders (VQ-VAE) and classical denoising regularization methods of neural networks. We interpret quantizers as regularizers that constrain latent representations while fostering a similarity-preserving mapping at the encoder. Before quantization, we impose noise on the latent codes and use a Bayesian estimator to optimize the quantizer-based representation. The introduced bottleneck Bayesian estimator outputs the posterior mean of the centroids to the decoder, and thus, is performing soft quantization of the noisy latent codes. We show that our proposed regularization method results in improved latent representations for both supervised learning and clustering downstream tasks when compared to autoencoders using other bottleneck structures. |
| Tasks | Denoising, Quantization |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11062v2 |
| https://arxiv.org/pdf/1905.11062v2.pdf | |
| PWC | https://paperswithcode.com/paper/quantization-based-regularization-for |
| Repo | https://github.com/AlbertOh90/Soft-VQ-VAE |
| Framework | none |
Feature Selective Anchor-Free Module for Single-Shot Object Detection
| Title | Feature Selective Anchor-Free Module for Single-Shot Object Detection |
| Authors | Chenchen Zhu, Yihui He, Marios Savvides |
| Abstract | We motivate and present feature selective anchor-free (FSAF) module, a simple and effective building block for single-shot object detectors. It can be plugged into single-shot detectors with feature pyramid structure. The FSAF module addresses two limitations brought up by the conventional anchor-based detection: 1) heuristic-guided feature selection; 2) overlap-based anchor sampling. The general concept of the FSAF module is online feature selection applied to the training of multi-level anchor-free branches. Specifically, an anchor-free branch is attached to each level of the feature pyramid, allowing box encoding and decoding in the anchor-free manner at an arbitrary level. During training, we dynamically assign each instance to the most suitable feature level. At the time of inference, the FSAF module can work jointly with anchor-based branches by outputting predictions in parallel. We instantiate this concept with simple implementations of anchor-free branches and online feature selection strategy. Experimental results on the COCO detection track show that our FSAF module performs better than anchor-based counterparts while being faster. When working jointly with anchor-based branches, the FSAF module robustly improves the baseline RetinaNet by a large margin under various settings, while introducing nearly free inference overhead. And the resulting best model can achieve a state-of-the-art 44.6% mAP, outperforming all existing single-shot detectors on COCO. |
| Tasks | Feature Selection, Object Detection |
| Published | 2019-03-02 |
| URL | http://arxiv.org/abs/1903.00621v1 |
| http://arxiv.org/pdf/1903.00621v1.pdf | |
| PWC | https://paperswithcode.com/paper/feature-selective-anchor-free-module-for |
| Repo | https://github.com/xuannianz/FSAF |
| Framework | tf |
Additive Noise Annealing and Approximation Properties of Quantized Neural Networks
| Title | Additive Noise Annealing and Approximation Properties of Quantized Neural Networks |
| Authors | Matteo Spallanzani, Lukas Cavigelli, Gian Paolo Leonardi, Marko Bertogna, Luca Benini |
| Abstract | We present a theoretical and experimental investigation of the quantization problem for artificial neural networks. We provide a mathematical definition of quantized neural networks and analyze their approximation capabilities, showing in particular that any Lipschitz-continuous map defined on a hypercube can be uniformly approximated by a quantized neural network. We then focus on the regularization effect of additive noise on the arguments of multi-step functions inherent to the quantization of continuous variables. In particular, when the expectation operator is applied to a non-differentiable multi-step random function, and if the underlying probability density is differentiable (in either classical or weak sense), then a differentiable function is retrieved, with explicit bounds on its Lipschitz constant. Based on these results, we propose a novel gradient-based training algorithm for quantized neural networks that generalizes the straight-through estimator, acting on noise applied to the network’s parameters. We evaluate our algorithm on the CIFAR-10 and ImageNet image classification benchmarks, showing state-of-the-art performance on AlexNet and MobileNetV2 for ternary networks. |
| Tasks | Image Classification, Quantization |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10452v1 |
| https://arxiv.org/pdf/1905.10452v1.pdf | |
| PWC | https://paperswithcode.com/paper/additive-noise-annealing-and-approximation |
| Repo | https://github.com/spallanzanimatteo/QuantLab |
| Framework | pytorch |
Cross-Lingual Dependency Parsing Using Code-Mixed TreeBank
| Title | Cross-Lingual Dependency Parsing Using Code-Mixed TreeBank |
| Authors | Zhang Meishan, Zhang Yue, Fu Guohong |
| Abstract | Treebank translation is a promising method for cross-lingual transfer of syntactic dependency knowledge. The basic idea is to map dependency arcs from a source treebank to its target translation according to word alignments. This method, however, can suffer from imperfect alignment between source and target words. To address this problem, we investigate syntactic transfer by code mixing, translating only confident words in a source treebank. Cross-lingual word embeddings are leveraged for transferring syntactic knowledge to the target from the resulting code-mixed treebank. Experiments on University Dependency Treebanks show that code-mixed treebanks are more effective than translated treebanks, giving highly competitive performances among cross-lingual parsing methods. |
| Tasks | Cross-Lingual Transfer, Dependency Parsing, Word Embeddings |
| Published | 2019-09-05 |
| URL | https://arxiv.org/abs/1909.02235v1 |
| https://arxiv.org/pdf/1909.02235v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-lingual-dependency-parsing-using-code |
| Repo | https://github.com/zhangmeishan/CodeMixedTreebank |
| Framework | none |
Adversarially Robust Few-Shot Learning: A Meta-Learning Approach
| Title | Adversarially Robust Few-Shot Learning: A Meta-Learning Approach |
| Authors | Micah Goldblum, Liam Fowl, Tom Goldstein |
| Abstract | Previous work on adversarially robust neural networks for image classification requires large training sets and computationally expensive training procedures. On the other hand, few-shot learning methods are highly vulnerable to adversarial examples. The goal of our work is to produce networks which both perform well at few-shot classification tasks and are simultaneously robust to adversarial examples. We develop an algorithm for producing adversarially robust meta-learners, and we thoroughly investigate factors which contribute to adversarial vulnerability. Moreover, our method achieves far superior robust performance on few-shot image classification tasks, such as Mini-ImageNet and CIFAR-FS, than robust transfer learning. |
| Tasks | Few-Shot Image Classification, Few-Shot Learning, Image Classification, Meta-Learning, Transfer Learning |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.00982v2 |
| https://arxiv.org/pdf/1910.00982v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-few-shot-learning-with-adversarially-1 |
| Repo | https://github.com/goldblum/AdversarialQuerying |
| Framework | pytorch |
The Art of Food: Meal Image Synthesis from Ingredients
| Title | The Art of Food: Meal Image Synthesis from Ingredients |
| Authors | Fangda Han, Ricardo Guerrero, Vladimir Pavlovic |
| Abstract | In this work we propose a new computational framework, based on generative deep models, for synthesis of photo-realistic food meal images from textual descriptions of its ingredients. Previous works on synthesis of images from text typically rely on pre-trained text models to extract text features, followed by a generative neural networks (GANs) aimed to generate realistic images conditioned on the text features. These works mainly focus on generating spatially compact and well-defined categories of objects, such as birds or flowers. In contrast, meal images are significantly more complex, consisting of multiple ingredients whose appearance and spatial qualities are further modified by cooking methods. We propose a method that first builds an attention-based ingredients-image association model, which is then used to condition a generative neural network tasked with synthesizing meal images. Furthermore, a cycle-consistent constraint is added to further improve image quality and control appearance. Extensive experiments show our model is able to generate meal image corresponding to the ingredients, which could be used to augment existing dataset for solving other computational food analysis problems. |
| Tasks | Image Generation |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.13149v1 |
| https://arxiv.org/pdf/1905.13149v1.pdf | |
| PWC | https://paperswithcode.com/paper/190513149 |
| Repo | https://github.com/CorneliusHsiao/FoodMethodGAN |
| Framework | pytorch |
Synthetic-Neuroscore: Using A Neuro-AI Interface for Evaluating Generative Adversarial Networks
| Title | Synthetic-Neuroscore: Using A Neuro-AI Interface for Evaluating Generative Adversarial Networks |
| Authors | Zhengwei Wang, Qi She, Alan F. Smeaton, Tomas E. Ward, Graham Healy |
| Abstract | Generative adversarial networks (GANs) are increasingly attracting attention in the computer vision, natural language processing, speech synthesis and similar domains. Arguably the most striking results have been in the area of image synthesis. However, evaluating the performance of GANs is still an open and challenging problem. Existing evaluation metrics primarily measure the dissimilarity between real and generated images using automated statistical methods. They often require large sample sizes for evaluation and do not directly reflect human perception of image quality. In this work, we describe an evaluation metric we call Neuroscore, for evaluating the performance of GANs, that more directly reflects psychoperceptual image quality through the utilization of brain signals. Our results show that Neuroscore has superior performance to the current evaluation metrics in that: (1) It is more consistent with human judgment; (2) The evaluation process needs much smaller numbers of samples; and (3) It is able to rank the quality of images on a per GAN basis. A convolutional neural network (CNN) based neuro-AI interface is proposed to predict Neuroscore from GAN-generated images directly without the need for neural responses. Importantly, we show that including neural responses during the training phase of the network can significantly improve the prediction capability of the proposed model. Materials related to this work are provided at https://github.com/villawang/Neuro-AI-Interface. |
| Tasks | Image Generation, Speech Synthesis |
| Published | 2019-05-10 |
| URL | https://arxiv.org/abs/1905.04243v2 |
| https://arxiv.org/pdf/1905.04243v2.pdf | |
| PWC | https://paperswithcode.com/paper/neuroscore-a-brain-inspired-evaluation-metric |
| Repo | https://github.com/villawang/Neuro-AI-Interface |
| Framework | tf |
On the Accuracy of Influence Functions for Measuring Group Effects
| Title | On the Accuracy of Influence Functions for Measuring Group Effects |
| Authors | Pang Wei Koh, Kai-Siang Ang, Hubert H. K. Teo, Percy Liang |
| Abstract | Influence functions estimate the effect of removing a training point on a model without the need to retrain. They are based on a first-order Taylor approximation that is guaranteed to be accurate for sufficiently small changes to the model, and so are commonly used to study the effect of individual points in large datasets. However, we often want to study the effects of large groups of training points, e.g., to diagnose batch effects or apportion credit between different data sources. Removing such large groups can result in significant changes to the model. Are influence functions still accurate in this setting? In this paper, we find that across many different types of groups and for a range of real-world datasets, the predicted effect (using influence functions) of a group correlates surprisingly well with its actual effect, even if the absolute and relative errors are large. Our theoretical analysis shows that such strong correlation arises only under certain settings and need not hold in general, indicating that real-world datasets have particular properties that allow the influence approximation to be accurate. |
| Tasks | |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.13289v2 |
| https://arxiv.org/pdf/1905.13289v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-accuracy-of-influence-functions-for |
| Repo | https://github.com/kohpangwei/group-influence-release |
| Framework | tf |
Extrapolating paths with graph neural networks
| Title | Extrapolating paths with graph neural networks |
| Authors | Jean-Baptiste Cordonnier, Andreas Loukas |
| Abstract | We consider the problem of path inference: given a path prefix, i.e., a partially observed sequence of nodes in a graph, we want to predict which nodes are in the missing suffix. In particular, we focus on natural paths occurring as a by-product of the interaction of an agent with a network—a driver on the transportation network, an information seeker in Wikipedia, or a client in an online shop. Our interest is sparked by the realization that, in contrast to shortest-path problems, natural paths are usually not optimal in any graph-theoretic sense, but might still follow predictable patterns. Our main contribution is a graph neural network called Gretel. Conditioned on a path prefix, this network can efficiently extrapolate path suffixes, evaluate path likelihood, and sample from the future path distribution. Our experiments with GPS traces on a road network and user-navigation paths in Wikipedia confirm that Gretel is able to adapt to graphs with very different properties, while also comparing favorably to previous solutions. |
| Tasks | |
| Published | 2019-03-18 |
| URL | http://arxiv.org/abs/1903.07518v1 |
| http://arxiv.org/pdf/1903.07518v1.pdf | |
| PWC | https://paperswithcode.com/paper/extrapolating-paths-with-graph-neural |
| Repo | https://github.com/jbcdnr/gretel-path-extrapolation |
| Framework | pytorch |
Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning
| Title | Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning |
| Authors | Majed El Helou, Sabine Süsstrunk |
| Abstract | Blind and universal image denoising consists of using a unique model that denoises images with any level of noise. It is especially practical as noise levels do not need to be known when the model is developed or at test time. We propose a theoretically-grounded blind and universal deep learning image denoiser for additive Gaussian noise removal. Our network is based on an optimal denoising solution, which we call fusion denoising. It is derived theoretically with a Gaussian image prior assumption. Synthetic experiments show our network’s generalization strength to unseen additive noise levels. We also adapt the fusion denoising network architecture for image denoising on real images. Our approach improves real-world grayscale additive image denoising PSNR results for training noise levels and further on noise levels not seen during training. It also improves state-of-the-art color image denoising performance on every single noise level, by an average of 0.1dB, whether trained on or not. |
| Tasks | Denoising, Image Denoising |
| Published | 2019-07-05 |
| URL | https://arxiv.org/abs/1907.03029v2 |
| https://arxiv.org/pdf/1907.03029v2.pdf | |
| PWC | https://paperswithcode.com/paper/blind-universal-bayesian-image-denoising-with |
| Repo | https://github.com/IVRL/BUIFD |
| Framework | pytorch |
Check-It: A Plugin for Detecting and Reducing the Spread of Fake News and Misinformation on the Web
| Title | Check-It: A Plugin for Detecting and Reducing the Spread of Fake News and Misinformation on the Web |
| Authors | Demetris Paschalides, Alexandros Kornilakis, Chrysovalantis Christodoulou, Rafael Andreou, George Pallis, Marios D. Dikaiakos, Evangelos Markatos |
| Abstract | Over the past few years, we have been witnessing the rise of misinformation on the Web. People fall victims of fake news during their daily lives and assist their further propagation knowingly and inadvertently. There have been many initiatives that are trying to mitigate the damage caused by fake news, focusing on signals from either domain flag-lists, online social networks or artificial intelligence. In this work, we present Check-It, a system that combines, in an intelligent way, a variety of signals into a pipeline for fake news identification. Check-It is developed as a web browser plugin with the objective of efficient and timely fake news detection, respecting the user’s privacy. Experimental results show that Check-It is able to outperform the state-of-the-art methods. On a dataset, consisting of 9 millions of articles labeled as fake and real, Check-It obtains classification accuracies that exceed 99%. |
| Tasks | Fake News Detection |
| Published | 2019-05-10 |
| URL | https://arxiv.org/abs/1905.04260v1 |
| https://arxiv.org/pdf/1905.04260v1.pdf | |
| PWC | https://paperswithcode.com/paper/check-it-a-plugin-for-detecting-and-reducing |
| Repo | https://github.com/anguyen120/fake-news-in-time |
| Framework | none |
OmniFold: A Method to Simultaneously Unfold All Observables
| Title | OmniFold: A Method to Simultaneously Unfold All Observables |
| Authors | Anders Andreassen, Patrick T. Komiske, Eric M. Metodiev, Benjamin Nachman, Jesse Thaler |
| Abstract | Collider data must be corrected for detector effects (“unfolded”) to be compared with theoretical calculations and measurements from other experiments. Unfolding is traditionally done for individual, binned observables without including all information relevant for characterizing the detector response. We introduce OmniFold, an unfolding method that iteratively reweights a simulated dataset, using machine learning to capitalize on all available information. Our approach is unbinned, works for arbitrarily high-dimensional data, and naturally incorporates information from the full phase space. We illustrate this technique on a realistic jet substructure example from the Large Hadron Collider and compare it to standard binned unfolding methods. This new paradigm enables the simultaneous measurement of all observables, including those not yet invented at the time of the analysis. |
| Tasks | |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.09107v1 |
| https://arxiv.org/pdf/1911.09107v1.pdf | |
| PWC | https://paperswithcode.com/paper/omnifold-a-method-to-simultaneously-unfold |
| Repo | https://github.com/ericmetodiev/OmniFold |
| Framework | none |
