February 2, 2020

# Paper Group AWR 33

Active Learning for Decision-Making from Imbalanced Observational Data. BIRL: Benchmark on Image Registration methods with Landmark validation. ANETAC: Arabic Named Entity Transliteration and Classification Dataset. Selecting the independent coordinates of manifolds with large aspect ratios. Seeing Under the Cover: A Physics Guided Learning Approac …

#### Active Learning for Decision-Making from Imbalanced Observational Data

Title Active Learning for Decision-Making from Imbalanced Observational Data
Authors Iiris Sundin, Peter Schulam, Eero Siivola, Aki Vehtari, Suchi Saria, Samuel Kaski
Abstract Machine learning can help personalized decision support by learning models to predict individual treatment effects (ITE). This work studies the reliability of prediction-based decision-making in a task of deciding which action $a$ to take for a target unit after observing its covariates $\tilde{x}$ and predicted outcomes $\hat{p}(\tilde{y} \mid \tilde{x}, a)$. An example case is personalized medicine and the decision of which treatment to give to a patient. A common problem when learning these models from observational data is imbalance, that is, difference in treated/control covariate distributions, which is known to increase the upper bound of the expected ITE estimation error. We propose to assess the decision-making reliability by estimating the ITE model’s Type S error rate, which is the probability of the model inferring the sign of the treatment effect wrong. Furthermore, we use the estimated reliability as a criterion for active learning, in order to collect new (possibly expensive) observations, instead of making a forced choice based on unreliable predictions. We demonstrate the effectiveness of this decision-making aware active learning in two decision-making tasks: in simulated data with binary outcomes and in a medical dataset with synthetic and continuous treatment outcomes.
Published 2019-04-10
URL https://arxiv.org/abs/1904.05268v2
PDF https://arxiv.org/pdf/1904.05268v2.pdf
PWC https://paperswithcode.com/paper/active-learning-for-decision-making-from
Repo https://github.com/IirisSundin/active-learning-for-decision-making
Framework none

#### BIRL: Benchmark on Image Registration methods with Landmark validation

Title BIRL: Benchmark on Image Registration methods with Landmark validation
Authors Jiri Borovec
Abstract This report presents a generic image registration benchmark with automatic evaluation using landmark annotations. The key features of the BIRL framework are: easily extendable, performance evaluation, parallel experimentation, simple visualisations, experiment’s time-out limit, resuming unfinished experiments. From the research practice, we identified and focused on these two main use-cases: (a) comparison of user’s (newly developed) method with some State-of-the-Art (SOTA) methods on a common dataset and (b) experimenting SOTA methods on user’s custom dataset (which should contain landmark annotation). Moreover, we present an integration of several standard image registration methods aiming at biomedical imaging into the BIRL framework. This report also contains experimental results of these SOTA methods on the CIMA dataset, which is a dataset of Whole Slice Imaging (WSI) from histology/pathology containing several multi-stain tissue samples from three tissue kinds. Source and results: https://borda.github.io/BIRL
Tasks BIRL, Image Registration, Medical Image Registration
Published 2019-12-31
URL https://arxiv.org/abs/1912.13452v2
PDF https://arxiv.org/pdf/1912.13452v2.pdf
PWC https://paperswithcode.com/paper/birl-benchmark-on-image-registration-methods
Repo https://github.com/Borda/BIRL
Framework none

#### ANETAC: Arabic Named Entity Transliteration and Classification Dataset

Title ANETAC: Arabic Named Entity Transliteration and Classification Dataset
Authors Mohamed Seghir Hadj Ameur, Farid Meziane, Ahmed Guessoum
Abstract In this paper, we make freely accessible ANETAC our English-Arabic named entity transliteration and classification dataset that we built from freely available parallel translation corpora. The dataset contains 79,924 instances, each instance is a triplet (e, a, c), where e is the English named entity, a is its Arabic transliteration and c is its class that can be either a Person, a Location, or an Organization. The ANETAC dataset is mainly aimed for the researchers that are working on Arabic named entity transliteration, but it can also be used for named entity classification purposes.
Published 2019-07-06
URL https://arxiv.org/abs/1907.03110v1
PDF https://arxiv.org/pdf/1907.03110v1.pdf
PWC https://paperswithcode.com/paper/anetac-arabic-named-entity-transliteration
Framework none

#### Selecting the independent coordinates of manifolds with large aspect ratios

Title Selecting the independent coordinates of manifolds with large aspect ratios
Authors Yu-Chia Chen, Marina Meilă
Abstract Many manifold embedding algorithms fail apparently when the data manifold has a large aspect ratio (such as a long, thin strip). Here, we formulate success and failure in terms of finding a smooth embedding, showing also that the problem is pervasive and more complex than previously recognized. Mathematically, success is possible under very broad conditions, provided that embedding is done by carefully selected eigenfunctions of the Laplace-Beltrami operator $\Delta$. Hence, we propose a bicriterial Independent Eigencoordinate Selection (IES) algorithm that selects smooth embeddings with few eigenvectors. The algorithm is grounded in theory, has low computational overhead, and is successful on synthetic and large real data.
Published 2019-07-02
URL https://arxiv.org/abs/1907.01651v2
PDF https://arxiv.org/pdf/1907.01651v2.pdf
PWC https://paperswithcode.com/paper/selecting-the-independent-coordinates-of
Repo https://github.com/alainchau/IES.jl
Framework none

#### Seeing Under the Cover: A Physics Guided Learning Approach for In-Bed Pose Estimation

Title Seeing Under the Cover: A Physics Guided Learning Approach for In-Bed Pose Estimation
Abstract Human in-bed pose estimation has huge practical values in medical and healthcare applications yet still mainly relies on expensive pressure mapping (PM) solutions. In this paper, we introduce our novel physics inspired vision-based approach that addresses the challenging issues associated with the in-bed pose estimation problem including monitoring a fully covered person in complete darkness. We reformulated this problem using our proposed Under the Cover Imaging via Thermal Diffusion (UCITD) method to capture the high resolution pose information of the body even when it is fully covered by using a long wavelength IR technique. We proposed a physical hyperparameter concept through which we achieved high quality groundtruth pose labels in different modalities. A fully annotated in-bed pose dataset called Simultaneously-collected multimodal Lying Pose (SLP) is also formed/released with the same order of magnitude as most existing large-scale human pose datasets to support complex models’ training and evaluation. A network trained from scratch on it and tested on two diverse settings, one in a living room and the other in a hospital room showed pose estimation performance of 99.5% and 95.7% in PCK0.2 standard, respectively. Moreover, in a multi-factor comparison with a state-of-the art in-bed pose monitoring solution based on PM, our solution showed significant superiority in all practical aspects by being 60 times cheaper, 300 times smaller, while having higher pose recognition granularity and accuracy.
Published 2019-07-03
URL https://arxiv.org/abs/1907.02161v3
PDF https://arxiv.org/pdf/1907.02161v3.pdf
PWC https://paperswithcode.com/paper/seeing-under-the-cover-a-physics-guided
Framework pytorch

#### Robustness properties of Facebook’s ResNeXt WSL models

Title Robustness properties of Facebook’s ResNeXt WSL models
Authors A. Emin Orhan
Abstract We investigate the robustness properties of ResNeXt class image recognition models trained with billion scale weakly supervised data (ResNeXt WSL models). These models, recently made public by Facebook AI, were trained with ~1B images from Instagram and fine-tuned on ImageNet. We show that these models display an unprecedented degree of robustness against common image corruptions and perturbations, as measured by the ImageNet-C and ImageNet-P benchmarks. They also achieve substantially improved accuracies on the recently introduced “natural adversarial examples” benchmark (ImageNet-A). The largest of the released models, in particular, achieves state-of-the-art results on ImageNet-C, ImageNet-P, and ImageNet-A by a large margin. The gains on ImageNet-C, ImageNet-P, and ImageNet-A far outpace the gains on ImageNet validation accuracy, suggesting the former as more useful benchmarks to measure further progress in image recognition. Remarkably, the ResNeXt WSL models even achieve a limited degree of adversarial robustness against state-of-the-art white-box attacks (10-step PGD attacks). However, in contrast to adversarially trained models, the robustness of the ResNeXt WSL models rapidly declines with the number of PGD steps, suggesting that these models do not achieve genuine adversarial robustness. Visualization of the learned features also confirms this conclusion. Finally, we show that although the ResNeXt WSL models are more shape-biased than comparable ImageNet-trained models in a shape-texture cue conflict experiment, they still remain much more texture-biased than humans, suggesting that they share some of the underlying characteristics of ImageNet-trained models that make this benchmark challenging.
Published 2019-07-17
URL https://arxiv.org/abs/1907.07640v5
PDF https://arxiv.org/pdf/1907.07640v5.pdf
Repo https://github.com/eminorhan/ood-benchmarks
Framework pytorch

#### ImageNet-trained deep neural network exhibits illusion-like response to the Scintillating Grid

Title ImageNet-trained deep neural network exhibits illusion-like response to the Scintillating Grid
Authors Eric D. Sun, Ron Dekel
Abstract Deep neural network (DNN) models for computer vision are now capable of human-level object recognition. Consequently, similarities in the performance and vulnerabilities of DNN and human vision are of great interest. Here we characterize the response of the VGG-19 DNN to images of the Scintillating Grid visual illusion, in which white dots are perceived to be partially black. We observed a significant deviation from the expected monotonic relation between VGG-19 representational dissimilarity and dot whiteness in the Scintillating Grid. That is, a linear increase in dot whiteness leads to a non-linear increase and then, remarkably, a decrease (non-monotonicity) in representational dissimilarity. In control images, mostly monotonic relations between representational dissimilarity and dot whiteness were observed. Furthermore, the dot whiteness level corresponding to the maximal representational dissimilarity (i.e. onset of non-monotonic dissimilarity) matched closely with that corresponding to the onset of illusion perception in human observers. As such, the non-monotonic response in the DNN is a potential model correlate for human illusion perception.
Published 2019-07-21
URL https://arxiv.org/abs/1907.09019v2
PDF https://arxiv.org/pdf/1907.09019v2.pdf
PWC https://paperswithcode.com/paper/imagenet-trained-deep-neural-network-exhibits
Repo https://github.com/sunericd/dnn-illusion
Framework none

#### Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition

Title Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition
Authors Genta Indra Winata, Zhaojiang Lin, Jamin Shin, Zihan Liu, Pascale Fung
Abstract In countries that speak multiple main languages, mixing up different languages within a conversation is commonly called code-switching. Previous works addressing this challenge mainly focused on word-level aspects such as word embeddings. However, in many cases, languages share common subwords, especially for closely related languages, but also for languages that are seemingly irrelevant. Therefore, we propose Hierarchical Meta-Embeddings (HME) that learn to combine multiple monolingual word-level and subword-level embeddings to create language-agnostic lexical representations. On the task of Named Entity Recognition for English-Spanish code-switching data, our model achieves the state-of-the-art performance in the multilingual settings. We also show that, in cross-lingual settings, our model not only leverages closely related languages, but also learns from languages with different roots. Finally, we show that combining different subunits are crucial for capturing code-switching entities.
Tasks Named Entity Recognition, Word Embeddings
Published 2019-09-18
URL https://arxiv.org/abs/1909.08504v1
PDF https://arxiv.org/pdf/1909.08504v1.pdf
PWC https://paperswithcode.com/paper/hierarchical-meta-embeddings-for-code
Repo https://github.com/gentaiscool/meta-emb
Framework pytorch

#### Learning Generalisable Omni-Scale Representations for Person Re-Identification

Title Learning Generalisable Omni-Scale Representations for Person Re-Identification
Authors Kaiyang Zhou, Yongxin Yang, Andrea Cavallaro, Tao Xiang
Abstract An effective person re-identification (re-ID) model should learn feature representations that are both discriminative, for distinguishing similar-looking people, and generalisable, for deployment across datasets without any adaptation. In this paper, we develop novel CNN architectures to address both challenges. First, we present a re-ID CNN termed omni-scale network (OSNet) to learn features that not only capture different spatial scales but also encapsulate a synergistic combination of multiple scales, namely omni-scale features. The basic building block consists of multiple convolutional streams, each detecting features at a certain scale. For omni-scale feature learning, a unified aggregation gate is introduced to dynamically fuse multi-scale features with channel-wise weights. OSNet is lightweight as its building blocks comprise factorised convolutions. Second, to improve generalisable feature learning, we introduce instance normalisation (IN) layers into OSNet to cope with cross-dataset discrepancies. Further, to determine the optimal placements of these IN layers in the architecture, we formulate an efficient differentiable architecture search algorithm. Extensive experiments show that, in the conventional same-dataset setting, OSNet achieves state-of-the-art performance, despite being much smaller than existing re-ID models. In the more challenging yet practical cross-dataset setting, OSNet beats most recent unsupervised domain adaptation methods without requiring any target data for model adaptation. Our code and models are released at \texttt{https://github.com/KaiyangZhou/deep-person-reid}.
Published 2019-10-15
URL https://arxiv.org/abs/1910.06827v3
PDF https://arxiv.org/pdf/1910.06827v3.pdf
PWC https://paperswithcode.com/paper/learning-generalisable-omni-scale
Repo https://github.com/KaiyangZhou/deep-person-reid
Framework pytorch

#### Manifold Embedded Knowledge Transfer for Brain-Computer Interfaces

Title Manifold Embedded Knowledge Transfer for Brain-Computer Interfaces
Authors Wen Zhang, Dongrui Wu
Abstract Transfer learning makes use of data or knowledge in one problem to help solve a different, yet related, problem. It is particularly useful in brain-computer interfaces (BCIs), for coping with variations among different subjects and/or tasks. This paper considers offline unsupervised cross-subject electroencephalogram (EEG) classification, i.e., we have labeled EEG trials from one or more source subjects, but only unlabeled EEG trials from the target subject. We propose a novel manifold embedded knowledge transfer (MEKT) approach, which first aligns the covariance matrices of the EEG trials in the Riemannian manifold, extracts features in the tangent space, and then performs domain adaptation by minimizing the joint probability distribution shift between the source and the target domains, while preserving their geometric structures. MEKT can cope with one or multiple source domains, and can be computed efficiently. We also propose a domain transferability estimation (DTE) approach to identify the most beneficial source domains, in case there are a large number of source domains. Experiments on four EEG datasets from two different BCI paradigms demonstrated that MEKT outperformed several state-of-the-art transfer learning approaches, and DTE can reduce more than half of the computational cost when the number of source subjects is large, with little sacrifice of classification accuracy.
Published 2019-10-14
URL https://arxiv.org/abs/1910.05878v2
PDF https://arxiv.org/pdf/1910.05878v2.pdf
PWC https://paperswithcode.com/paper/manifold-embedded-knowledge-transfer-for
Repo https://github.com/chamwen/MEKT
Framework none

#### MixMatch Domain Adaptaion: Prize-winning solution for both tracks of VisDA 2019 challenge

Title MixMatch Domain Adaptaion: Prize-winning solution for both tracks of VisDA 2019 challenge
Authors Danila Rukhovich, Danil Galeev
Abstract We present a domain adaptation (DA) system that can be used in multi-source and semi-supervised settings. Using the proposed method we achieved 2nd place on multi-source track and 3rd place on semi-supervised track of the VisDA 2019 challenge (http://ai.bu.edu/visda-2019/). The source code of the method is available at https://github.com/filaPro/visda2019.
Published 2019-10-09
URL https://arxiv.org/abs/1910.03903v1
PDF https://arxiv.org/pdf/1910.03903v1.pdf
Repo https://github.com/filaPro/visda2019
Framework tf

Authors Yingwei Pan, Yehao Li, Qi Cai, Yang Chen, Ting Yao
Published 2019-10-08
URL https://arxiv.org/abs/1910.03548v2
PDF https://arxiv.org/pdf/1910.03548v2.pdf
Repo https://github.com/Panda-Peter/visda2019-semisupervised
Framework pytorch

#### ATL: Autonomous Knowledge Transfer from Many Streaming Processes

Title ATL: Autonomous Knowledge Transfer from Many Streaming Processes
Authors Mahardhika Pratama, Marcus de Carvalho, Renchunzi Xie, Edwin Lughofer, Jie Lu
Abstract Transferring knowledge across many streaming processes remains an uncharted territory in the existing literature and features unique characteristics: no labelled instance of the target domain, covariate shift of source and target domain, different period of drifts in the source and target domains. Autonomous transfer learning (ATL) is proposed in this paper as a flexible deep learning approach for the online unsupervised transfer learning problem across many streaming processes. ATL offers an online domain adaptation strategy via the generative and discriminative phases coupled with the KL divergence based optimization strategy to produce a domain invariant network while putting forward an elastic network structure. It automatically evolves its network structure from scratch with/without the presence of ground truth to overcome independent concept drifts in the source and target domain. The rigorous numerical evaluation has been conducted along with a comparison against recently published works. ATL demonstrates improved performance while showing significantly faster training speed than its counterparts.
Published 2019-10-08
URL https://arxiv.org/abs/1910.03434v2
PDF https://arxiv.org/pdf/1910.03434v2.pdf
PWC https://paperswithcode.com/paper/atl-autonomous-knowledge-transfer-from-many
Repo https://github.com/Ivsucram/ATL_Python
Framework pytorch

#### Sequential Recommendation with Dual Side Neighbor-based Collaborative Relation Modeling

Title Sequential Recommendation with Dual Side Neighbor-based Collaborative Relation Modeling
Authors Jiarui Qin, Kan Ren, Yuchen Fang, Weinan Zhang, Yong Yu
Abstract Sequential recommendation task aims to predict user preference over items in the future given user historical behaviors. The order of user behaviors implies that there are resourceful sequential patterns embedded in the behavior history which reveal the underlying dynamics of user interests. Various sequential recommendation methods are proposed to model the dynamic user behaviors. However, most of the models only consider the user’s own behaviors and dynamics, while ignoring the collaborative relations among users and items, i.e., similar tastes of users or analogous properties of items. Without modeling collaborative relations, those methods suffer from the lack of recommendation diversity and thus may have worse performance. Worse still, most existing methods only consider the user-side sequence and ignore the temporal dynamics on the item side. To tackle the problems of the current sequential recommendation models, we propose Sequential Collaborative Recommender (SCoRe) which effectively mines high-order collaborative information using cross-neighbor relation modeling and, additionally utilizes both user-side and item-side historical sequences to better capture user and item dynamics. Experiments on three real-world yet large-scale datasets demonstrate the superiority of the proposed model over strong baselines.
Published 2019-11-10
URL https://arxiv.org/abs/1911.03883v1
PDF https://arxiv.org/pdf/1911.03883v1.pdf
PWC https://paperswithcode.com/paper/sequential-recommendation-with-dual-side
Repo https://github.com/qinjr/SCoRe
Framework tf

#### Semi-Supervised Variational Autoencoder for Survival Prediction

Title Semi-Supervised Variational Autoencoder for Survival Prediction
Authors Sveinn Pálsson, Stefano Cerri, Andrea Dittadi, Koen Van Leemput
Abstract In this paper we propose a semi-supervised variational autoencoder for classification of overall survival groups from tumor segmentation masks. The model can use the output of any tumor segmentation algorithm, removing all assumptions on the scanning platform and the specific type of pulse sequences used, thereby increasing its generalization properties. Due to its semi-supervised nature, the method can learn to classify survival time by using a relatively small number of labeled subjects. We validate our model on the publicly available dataset from the Multimodal Brain Tumor Segmentation Challenge (BraTS) 2019.