January 27, 2020

3215 words 16 mins read

Paper Group ANR 1157

One-Way Prototypical Networks. A Weakly Supervised Method for Instance Segmentation of Biological Cells. Learning Radiative Transfer Models for Climate Change Applications in Imaging Spectroscopy. Simple, Fast, Accurate Intent Classification and Slot Labeling for Goal-Oriented Dialogue Systems. The Trustworthy Pal: Controlling the False Discovery R …

One-Way Prototypical Networks


Title	One-Way Prototypical Networks
Authors	Anna Kruspe
Abstract	Few-shot models have become a popular topic of research in the past years. They offer the possibility to determine class belongings for unseen examples using just a handful of examples for each class. Such models are trained on a wide range of classes and their respective examples, learning a decision metric in the process. Types of few-shot models include matching networks and prototypical networks. We show a new way of training prototypical few-shot models for just a single class. These models have the ability to predict the likelihood of an unseen query belonging to a group of examples without any given counterexamples. The difficulty here lies in the fact that no relative distance to other classes can be calculated via softmax. We solve this problem by introducing a “null class” centered around zero, and enforcing centering with batch normalization. Trained on the commonly used Omniglot data set, we obtain a classification accuracy of .98 on the matched test set, and of .8 on unmatched MNIST data. On the more complex MiniImageNet data set, test accuracy is .8. In addition, we propose a novel Gaussian layer for distance calculation in a prototypical network, which takes the support examples’ distribution rather than just their centroid into account. This extension shows promising results when a higher number of support examples is available.
Tasks	Omniglot
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00820v1
PDF	https://arxiv.org/pdf/1906.00820v1.pdf
PWC	https://paperswithcode.com/paper/190600820
Repo
Framework

A Weakly Supervised Method for Instance Segmentation of Biological Cells


Title	A Weakly Supervised Method for Instance Segmentation of Biological Cells
Authors	Fidel A. Guerrero-Peña, Pedro D. Marrero Fernandez, Tsang Ing Ren, Alexandre Cunha
Abstract	We present a weakly supervised deep learning method to perform instance segmentation of cells present in microscopy images. Annotation of biomedical images in the lab can be scarce, incomplete, and inaccurate. This is of concern when supervised learning is used for image analysis as the discriminative power of a learning model might be compromised in these situations. To overcome the curse of poor labeling, our method focuses on three aspects to improve learning: i) we propose a loss function operating in three classes to facilitate separating adjacent cells and to drive the optimizer to properly classify underrepresented regions; ii) a contour-aware weight map model is introduced to strengthen contour detection while improving the network generalization capacity; and iii) we augment data by carefully modulating local intensities on edges shared by adjoining regions and to account for possibly weak signals on these edges. Generated probability maps are segmented using different methods, with the watershed based one generally offering the best solutions, specially in those regions where the prevalence of a single class is not clear. The combination of these contributions allows segmenting individual cells on challenging images. We demonstrate our methods in sparse and crowded cell images, showing improvements in the learning process for a fixed network architecture.
Tasks	Contour Detection, Instance Segmentation, Semantic Segmentation
Published	2019-08-26
URL	https://arxiv.org/abs/1908.09891v1
PDF	https://arxiv.org/pdf/1908.09891v1.pdf
PWC	https://paperswithcode.com/paper/a-weakly-supervised-method-for-instance
Repo
Framework

Learning Radiative Transfer Models for Climate Change Applications in Imaging Spectroscopy


Title	Learning Radiative Transfer Models for Climate Change Applications in Imaging Spectroscopy
Authors	Shubhankar Deshpande, Brian D. Bue, David R. Thompson, Vijay Natraj, Mario Parente
Abstract	According to a recent investigation, an estimated 33-50% of the world’s coral reefs have undergone degradation, believed to be as a result of climate change. A strong driver of climate change and the subsequent environmental impact are greenhouse gases such as methane. However, the exact relation climate change has to the environmental condition cannot be easily established. Remote sensing methods are increasingly being used to quantify and draw connections between rapidly changing climatic conditions and environmental impact. A crucial part of this analysis is processing spectroscopy data using radiative transfer models (RTMs) which is a computationally expensive process and limits their use with high volume imaging spectrometers. This work presents an algorithm that can efficiently emulate RTMs using neural networks leading to a multifold speedup in processing time, and yielding multiple downstream benefits.
Tasks
Published	2019-06-08
URL	https://arxiv.org/abs/1906.03479v1
PDF	https://arxiv.org/pdf/1906.03479v1.pdf
PWC	https://paperswithcode.com/paper/learning-radiative-transfer-models-for
Repo
Framework

Simple, Fast, Accurate Intent Classification and Slot Labeling for Goal-Oriented Dialogue Systems


Title	Simple, Fast, Accurate Intent Classification and Slot Labeling for Goal-Oriented Dialogue Systems
Authors	Arshit Gupta, John Hewitt, Katrin Kirchhoff
Abstract	With the advent of conversational assistants, like Amazon Alexa, Google Now, etc., dialogue systems are gaining a lot of traction, especially in industrial setting. These systems typically consist of Spoken Language understanding component which, in turn, consists of two tasks - Intent Classification (IC) and Slot Labeling (SL). Generally, these two tasks are modeled together jointly to achieve best performance. However, this joint modeling adds to model obfuscation. In this work, we first design framework for a modularization of joint IC-SL task to enhance architecture transparency. Then, we explore a number of self-attention, convolutional, and recurrent models, contributing a large-scale analysis of modeling paradigms for IC+SL across two datasets. Finally, using this framework, we propose a class of ‘label-recurrent’ models that otherwise non-recurrent, with a 10-dimensional representation of the label history, and show that our proposed systems are easy to interpret, highly accurate (achieving over 30% error reduction in SL over the state-of-the-art on the Snips dataset), as well as fast, at 2x the inference and 2/3 to 1/2 the training time of comparable recurrent models, thus giving an edge in critical real-world systems.
Tasks	Goal-Oriented Dialogue Systems, Intent Classification, Spoken Language Understanding
Published	2019-03-19
URL	https://arxiv.org/abs/1903.08268v2
PDF	https://arxiv.org/pdf/1903.08268v2.pdf
PWC	https://paperswithcode.com/paper/simple-fast-accurate-intent-classification
Repo
Framework

The Trustworthy Pal: Controlling the False Discovery Rate in Boolean Matrix Factorization


Title	The Trustworthy Pal: Controlling the False Discovery Rate in Boolean Matrix Factorization
Authors	Sibylle Hess, Nico Piatkowski, Katharina Morik
Abstract	Boolean matrix factorization (BMF) is a popular and powerful technique for inferring knowledge from data. The mining result is the Boolean product of two matrices, approximating the input dataset. The Boolean product is a disjunction of rank-1 binary matrices, each describing a feature-relation, called pattern, for a group of samples. Yet, there are no guarantees that any of the returned patterns do not actually arise from noise, i.e., are false discoveries. In this paper, we propose and discuss the usage of the false discovery rate in the unsupervised BMF setting. We prove two bounds on the probability that a found pattern is constituted of random Bernoulli-distributed noise. Each bound exploits a specific property of the factorization which minimizes the approximation error—yielding new insights on the minimizers of Boolean matrix factorization. This leads to improved BMF algorithms by replacing heuristic rank selection techniques with a theoretically well-based approach. Our empirical demonstration shows that both bounds deliver excellent results in various practical settings.
Tasks
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00697v1
PDF	https://arxiv.org/pdf/1907.00697v1.pdf
PWC	https://paperswithcode.com/paper/the-trustworthy-pal-controlling-the-false
Repo
Framework

Laplace Landmark Localization


Title	Laplace Landmark Localization
Authors	Joseph P Robinson, Yuncheng Li, Ning Zhang, Yun Fu, and Sergey Tulyakov
Abstract	Landmark localization in images and videos is a classic problem solved in various ways. Nowadays, with deep networks prevailing throughout machine learning, there are revamped interests in pushing facial landmark detection technologies to handle more challenging data. Most efforts use network objectives based on L1 or L2 norms, which have several disadvantages. First of all, the locations of landmarks are determined from generated heatmaps (i.e., confidence maps) from which predicted landmark locations (i.e., the means) get penalized without accounting for the spread: a high scatter corresponds to low confidence and vice-versa. For this, we introduce a LaplaceKL objective that penalizes for a low confidence. Another issue is a dependency on labeled data, which are expensive to obtain and susceptible to error. To address both issues we propose an adversarial training framework that leverages unlabeled data to improve model performance. Our method claims state-of-the-art on all of the 300W benchmarks and ranks second-to-best on the Annotated Facial Landmarks in the Wild (AFLW) dataset. Furthermore, our model is robust with a reduced size: 1/8 the number of channels (i.e., 0.0398MB) is comparable to state-of-that-art in real-time on CPU. Thus, we show that our method is of high practical value to real-life application.
Tasks	Facial Landmark Detection
Published	2019-03-27
URL	https://arxiv.org/abs/1903.11633v2
PDF	https://arxiv.org/pdf/1903.11633v2.pdf
PWC	https://paperswithcode.com/paper/laplace-landmark-localization
Repo
Framework

Differentiable Grammars for Videos


Title	Differentiable Grammars for Videos
Authors	AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo
Abstract	This paper proposes a novel algorithm which learns a formal regular grammar from real-world continuous data, such as videos. Learning latent terminals, non-terminals, and production rules directly from continuous data allows the construction of a generative model capturing sequential structures with multiple possibilities. Our model is fully differentiable, and provides easily interpretable results which are important in order to understand the learned structures. It outperforms the state-of-the-art on several challenging datasets and is more accurate for forecasting future activities in videos. We plan to open-source the code. https://sites.google.com/view/differentiable-grammars
Tasks
Published	2019-02-01
URL	https://arxiv.org/abs/1902.00505v2
PDF	https://arxiv.org/pdf/1902.00505v2.pdf
PWC	https://paperswithcode.com/paper/learning-differentiable-grammars-for
Repo
Framework

Learning Latent State Spaces for Planning through Reward Prediction


Title	Learning Latent State Spaces for Planning through Reward Prediction
Authors	Aaron Havens, Yi Ouyang, Prabhat Nagarajan, Yasuhiro Fujita
Abstract	Model-based reinforcement learning methods typically learn models for high-dimensional state spaces by aiming to reconstruct and predict the original observations. However, drawing inspiration from model-free reinforcement learning, we propose learning a latent dynamics model directly from rewards. In this work, we introduce a model-based planning framework which learns a latent reward prediction model and then plans in the latent state-space. The latent representation is learned exclusively from multi-step reward prediction which we show to be the only necessary information for successful planning. With this framework, we are able to benefit from the concise model-free representation, while still enjoying the data-efficiency of model-based algorithms. We demonstrate our framework in multi-pendulum and multi-cheetah environments where several pendulums or cheetahs are shown to the agent but only one of which produces rewards. In these environments, it is important for the agent to construct a concise latent representation to filter out irrelevant observations. We find that our method can successfully learn an accurate latent reward prediction model in the presence of the irrelevant information while existing model-based methods fail. Planning in the learned latent state-space shows strong performance and high sample efficiency over model-free and model-based baselines.
Tasks
Published	2019-12-09
URL	https://arxiv.org/abs/1912.04201v1
PDF	https://arxiv.org/pdf/1912.04201v1.pdf
PWC	https://paperswithcode.com/paper/learning-latent-state-spaces-for-planning-1
Repo
Framework

Augmenting C. elegans Microscopic Dataset for Accelerated Pattern Recognition


Title	Augmenting C. elegans Microscopic Dataset for Accelerated Pattern Recognition
Authors	Dali Wang, Zheng Lu, Zhirong Bao
Abstract	The detection of cell shape changes in 3D time-lapse images of complex tissues is an important task. However, it is a challenging and tedious task to establish a comprehensive dataset to improve the performance of deep learning models. In the paper, we present a deep learning approach to augment 3D live images of the Caenorhabditis elegans embryo, so that we can further speed up the specific structural pattern recognition. We use an unsupervised training over unlabeled images to generate supplementary datasets for further pattern recognition. Technically, we used Alex-style neural networks in a generative adversarial network framework to generate new datasets that have common features of the C. elegans membrane structure. We also made the dataset available for a broad scientific community.
Tasks
Published	2019-05-31
URL	https://arxiv.org/abs/1906.00078v1
PDF	https://arxiv.org/pdf/1906.00078v1.pdf
PWC	https://paperswithcode.com/paper/190600078
Repo
Framework

Why bigger is not always better: on finite and infinite neural networks


Title	Why bigger is not always better: on finite and infinite neural networks
Authors	Laurence Aitchison
Abstract	Recent work has shown that the outputs of convolutional neural networks become Gaussian process (GP) distributed when we take the number of channels to infinity. In principle, these infinite networks should perform very well, both because they allow for exact Bayesian inference, and because widening networks is generally thought to improve (or at least not diminish) performance. However, Bayesian infinite networks perform poorly in comparison to finite networks, and our goal here is to explain this discrepancy. We note that the high-level representation induced by an infinite network has very little flexibility; it depends only on network hyperparameters such as depth, and as such cannot learn a good high-level representation of data. In contrast, finite networks correspond to a rich prior over high-level representations, corresponding to kernel hyperparameters. We analyse this flexibility from the perspective of the prior (looking at the structured prior covariance of the top-level kernel), and from the perspective of the posterior, showing that the representation in a learned, finite deep linear network slowly transitions from the kernel induced by the inputs towards the kernel induced by the outputs, both for gradient descent, and for Langevin sampling. Finally, we explore representation learning in deep, convolutional, nonlinear networks, showing that learned representations differ dramatically from the corresponding infinite network.
Tasks	Bayesian Inference, Representation Learning
Published	2019-10-17
URL	https://arxiv.org/abs/1910.08013v2
PDF	https://arxiv.org/pdf/1910.08013v2.pdf
PWC	https://paperswithcode.com/paper/why-bigger-is-not-always-better-on-finite-and
Repo
Framework

Ethical Dilemmas of Strategic Coalitions


Title	Ethical Dilemmas of Strategic Coalitions
Authors	Pavel Naumov, Rui-Jie Yew
Abstract	A coalition of agents, or a single agent, has an ethical dilemma between several statements if each joint action of the coalition forces at least one specific statement among them to be true. For example, any action in the trolley dilemma forces one specific group of people to die. In many cases, agents face ethical dilemmas because they are restricted in the amount of the resources they are ready to sacrifice to overcome the dilemma. The paper presents a sound and complete modal logical system that describes properties of dilemmas for a given limit on a sacrifice.
Tasks
Published	2019-11-02
URL	https://arxiv.org/abs/1911.00786v1
PDF	https://arxiv.org/pdf/1911.00786v1.pdf
PWC	https://paperswithcode.com/paper/ethical-dilemmas-of-strategic-coalitions
Repo
Framework


Title	Evidence of distrust and disorientation towards immunization on online social media after contrasting political communication on vaccines. Results from an analysis of Twitter data in Italy
Authors	Samantha Ajovalasit, Veronica Dorgali, Angelo Mazza, Alberto d’ Onofrio, Piero Manfredi
Abstract	Background. Recently, In Italy the vaccination coverage for key immunizations, as MMR, has been declining, with measles outbreaks. In 2017, the Italian Government expanded the number of mandatory immunizations establishing penalties for families of unvaccinated children. During the 2018 elections campaign, immunization policy entered the political debate, with the government accusing oppositions of fuelling vaccine scepticism. A new government established in 2018 temporarily relaxed penalties and announced the introduction of flexibility. Objectives and Methods. By a sentiment analysis on tweets posted in Italian during 2018, we aimed at (i) characterising the temporal flow of communication on vaccines, (ii) evaluating the usefulness of Twitter data for estimating vaccination parameters, and (iii) investigating whether the ambiguous political communication might have originated disorientation among the public. Results. The population appeared to be mostly composed by “serial twitterers” tweeting about everything including vaccines. Tweets favourable to vaccination accounted for 75% of retained tweets, undecided for 14% and unfavourable for 11%. Twitter activity of the Italian public health institutions was negligible. After smoothing the temporal pattern, an up-and-down trend in the favourable proportion emerged, synchronized with the switch between governments, providing clear evidence of disorientation. Conclusion. The reported evidence of disorientation documents that critical health topics, as immunization, should never be used for political consensus. This is especially true given the increasing role of online social media as information source, which might yield to social pressures eventually harmful for vaccine uptake, and is worsened by the lack of institutional presence on Twitter. This calls for efforts to contrast misinformation and the ensuing spread of hesitancy.
Tasks	Sentiment Analysis
Published	2019-12-31
URL	https://arxiv.org/abs/2002.00846v3
PDF	https://arxiv.org/pdf/2002.00846v3.pdf
PWC	https://paperswithcode.com/paper/evidence-of-distrust-and-disorientation
Repo
Framework

L2AE-D: Learning to Aggregate Embeddings for Few-shot Learning with Meta-level Dropout


Title	L2AE-D: Learning to Aggregate Embeddings for Few-shot Learning with Meta-level Dropout
Authors	Heda Song, Mercedes Torres Torres, Ender Özcan, Isaac Triguero
Abstract	Few-shot learning focuses on learning a new visual concept with very limited labelled examples. A successful approach to tackle this problem is to compare the similarity between examples in a learned metric space based on convolutional neural networks. However, existing methods typically suffer from meta-level overfitting due to the limited amount of training tasks and do not normally consider the importance of the convolutional features of different examples within the same channel. To address these limitations, we make the following two contributions: (a) We propose a novel meta-learning approach for aggregating useful convolutional features and suppressing noisy ones based on a channel-wise attention mechanism to improve class representations. The proposed model does not require fine-tuning and can be trained in an end-to-end manner. The main novelty lies in incorporating a shared weight generation module that learns to assign different weights to the feature maps of different examples within the same channel. (b) We also introduce a simple meta-level dropout technique that reduces meta-level overfitting in several few-shot learning approaches. In our experiments, we find that this simple technique significantly improves the performance of the proposed method as well as various state-of-the-art meta-learning algorithms. Applying our method to few-shot image recognition using Omniglot and miniImageNet datasets shows that it is capable of delivering a state-of-the-art classification performance.
Tasks	Few-Shot Learning, Meta-Learning, Omniglot
Published	2019-04-08
URL	http://arxiv.org/abs/1904.04339v1
PDF	http://arxiv.org/pdf/1904.04339v1.pdf
PWC	https://paperswithcode.com/paper/l2ae-d-learning-to-aggregate-embeddings-for
Repo
Framework

Deep Tree Transductions - A Short Survey


Title	Deep Tree Transductions - A Short Survey
Authors	Davide Bacciu, Antonio Bruno
Abstract	The paper surveys recent extensions of the Long-Short Term Memory networks to handle tree structures from the perspective of learning non-trivial forms of isomorph structured transductions. It provides a discussion of modern TreeLSTM models, showing the effect of the bias induced by the direction of tree processing. An empirical analysis is performed on real-world benchmarks, highlighting how there is no single model adequate to effectively approach all transduction problems.
Tasks
Published	2019-02-05
URL	http://arxiv.org/abs/1902.01737v1
PDF	http://arxiv.org/pdf/1902.01737v1.pdf
PWC	https://paperswithcode.com/paper/deep-tree-transductions-a-short-survey
Repo
Framework

Spatio-temporal Video Re-localization by Warp LSTM


Title	Spatio-temporal Video Re-localization by Warp LSTM
Authors	Yang Feng, Lin Ma, Wei Liu, Jiebo Luo
Abstract	The need for efficiently finding the video content a user wants is increasing because of the erupting of user-generated videos on the Web. Existing keyword-based or content-based video retrieval methods usually determine what occurs in a video but not when and where. In this paper, we make an answer to the question of when and where by formulating a new task, namely spatio-temporal video re-localization. Specifically, given a query video and a reference video, spatio-temporal video re-localization aims to localize tubelets in the reference video such that the tubelets semantically correspond to the query. To accurately localize the desired tubelets in the reference video, we propose a novel warp LSTM network, which propagates the spatio-temporal information for a long period and thereby captures the corresponding long-term dependencies. Another issue for spatio-temporal video re-localization is the lack of properly labeled video datasets. Therefore, we reorganize the videos in the AVA dataset to form a new dataset for spatio-temporal video re-localization research. Extensive experimental results show that the proposed model achieves superior performances over the designed baselines on the spatio-temporal video re-localization task.
Tasks	Video Retrieval
Published	2019-05-10
URL	https://arxiv.org/abs/1905.03922v1
PDF	https://arxiv.org/pdf/1905.03922v1.pdf
PWC	https://paperswithcode.com/paper/spatio-temporal-video-re-localization-by-warp
Repo
Framework