Search

We propose probabilistic task modelling -- a generative probabilistic model for collections of tasks used in meta-learning. The proposed model combines variational auto-encoding and latent Dirichlet allocation to model each task as a mixture of Gaussian distribution in an embedding space. Such modelling provides an explicit representation of a task through its task-theme mixture. We present an efficient approximation inference technique based on variational inference method for empirical Bayes parameter estimation. We perform empirical evaluations to validate the task uncertainty and task distance produced by the proposed method through correlation diagrams of the prediction accuracy on testing tasks. We also carry out experiments of task selection in meta-learning to demonstrate how the task relatedness inferred from the proposed model help to facilitate meta-learning algorithms., Comment: Correct typos, notations and update related work

Background modeling and subtraction is a promising research area with a variety of applications for video surveillance. Recent years have witnessed a proliferation of effective learning-based deep neural networks in this area. However, the techniques have only provided limited descriptions of scenes' properties while requiring heavy computations, as their single-valued mapping functions are learned to approximate the temporal conditional averages of observed target backgrounds and foregrounds. On the other hand, statistical learning in imagery domains has been a prevalent approach with high adaptation to dynamic context transformation, notably using Gaussian Mixture Models (GMM) with its generalization capabilities. By leveraging both, we propose a novel method called CDN-MEDAL-net for background modeling and subtraction with two convolutional neural networks. The first architecture, CDN-GM, is grounded on an unsupervised GMM statistical learning strategy to describe observed scenes' salient features. The second one, MEDAL-net, implements a light-weighted pipeline of online video background subtraction. Our two-stage architecture is small, but it is very effective with rapid convergence to representations of intricate motion patterns. Our experiments show that the proposed approach is not only capable of effectively extracting regions of moving objects in unseen cases, but it is also very efficient., Comment: 13 pages, 5 figures, to be submitted to IEEE TMM

Toward a computer-assisted marking for descriptive math questions,this paper presents clustering of online handwritten mathematical expressions (OnHMEs) to help human markers to mark them efficiently and reliably. We propose a generative sequence similarity function for computing a similarity score of two OnHMEs based on a sequence-to-sequence OnHME recognizer. Each OnHME is represented by a similarity-based representation (SbR) vector. The SbR matrix is inputted to the k-means algorithm for clustering OnHMEs. Experiments are conducted on an answer dataset (Dset_Mix) of 200 OnHMEs mixed of real patterns and synthesized patterns for each of 10 questions and a real online handwritten mathematical answer dataset of 122 student answers at most for each of 15 questions (NIER_CBT). The best clustering results achieved around 0.916 and 0.915 for purity, and around 0.556 and 0.702 for the marking cost on Dset_Mix and NIER_CBT, respectively. Our method currently outperforms the previous methods for clustering HMEs., Comment: 16 pages, ICDAR2021

This paper presents a temporal classification method for all three subtasks of symbol segmentation, symbol recognition and relation classification in online handwritten mathematical expressions (HMEs). The classification model is trained by multiple paths of symbols and spatial relations derived from the Symbol Relation Tree (SRT) representation of HMEs. The method benefits from global context of a deep bidirectional Long Short-term Memory network, which learns the temporal classification directly from online handwriting by the Connectionist Temporal Classification loss. To recognize an online HME, a symbol-level parse tree with Context-Free Grammar is constructed, where symbols and spatial relations are obtained from the temporal classification results. We show the effectiveness of the proposed method on the two latest CROHME datasets., Comment: 16 pages, ICDAR2021

This paper proposes a method for recognizing online handwritten mathematical expressions (OnHME) by building a symbol relation tree (SRT) directly from a sequence of strokes. A bidirectional recurrent neural network learns from multiple derived paths of SRT to predict both symbols and spatial relations between symbols using global context. The recognition system has two parts: a temporal classifier and a tree connector. The temporal classifier produces an SRT by recognizing an OnHME pattern. The tree connector splits the SRT into several sub-SRTs. The final SRT is formed by looking up the best combination among those sub-SRTs. Besides, we adopt a tree sorting method to deal with various stroke orders. Recognition experiments indicate that the proposed OnHME recognition system is competitive to other methods. The recognition system achieves 44.12% and 41.76% expression recognition rates on the Competition on Recognition of Online Handwritten Mathematical Expressions (CROHME) 2014 and 2016 testing sets., Comment: 13 pages, conference

We address the problem of modeling constrained hospital resources in the midst of the COVID-19 pandemic in order to inform decision-makers of future demand and assess the societal value of possible interventions. For broad applicability, we focus on the common yet challenging scenario where patient-level data for a region of interest are not available. Instead, given daily admissions counts, we model aggregated counts of observed resource use, such as the number of patients in the general ward, in the intensive care unit, or on a ventilator. In order to explain how individual patient trajectories produce these counts, we propose an aggregate count explicit-duration hidden Markov model, nicknamed the ACED-HMM, with an interpretable, compact parameterization. We develop an Approximate Bayesian Computation approach that draws samples from the posterior distribution over the model's transition and duration parameters given aggregate counts from a specific location, thus adapting the model to a region or individual hospital site of interest. Samples from this posterior can then be used to produce future forecasts of any counts of interest. Using data from the United States and the United Kingdom, we show our mechanistic approach provides competitive probabilistic forecasts for the future even as the dynamics of the pandemic shift. Furthermore, we show how our model provides insight about recovery probabilities or length of stay distributions, and we suggest its potential to answer challenging what-if questions about the societal value of possible interventions., Comment: To appear in the Proceedings of the Machine Learning for Healthcare (MLHC) conference, 2021. 20 pages, 7 figures and 1 table. 26 additional pages of supplementary material

Recent advances in meta-learning has led to remarkable performances on several few-shot learning benchmarks. However, such success often ignores the similarity between training and testing tasks, resulting in a potential bias evaluation. We, therefore, propose a generative approach based on a variant of Latent Dirichlet Allocation to analyse task similarity to optimise and better understand the performance of meta-learning. We demonstrate that the proposed method can provide an insightful evaluation for meta-learning algorithms on two few-shot classification benchmarks that matches common intuition: the more similar the higher performance. Based on this similarity measure, we propose a task-selection strategy for meta-learning and show that it can produce more accurate classification results than methods that randomly select training tasks., Comment: Accepted at Neurips Meta-learning Workshop 2020

Most of the existing chest X-ray datasets include labels from a list of findings without specifying their locations on the radiographs. This limits the development of machine learning algorithms for the detection and localization of chest abnormalities. In this work, we describe a dataset of more than 100,000 chest X-ray scans that were retrospectively collected from two major hospitals in Vietnam. Out of this raw data, we release 18,000 images that were manually annotated by a total of 17 experienced radiologists with 22 local labels of rectangles surrounding abnormalities and 6 global labels of suspected diseases. The released dataset is divided into a training set of 15,000 and a test set of 3,000. Each scan in the training set was independently labeled by 3 radiologists, while each scan in the test set was labeled by the consensus of 5 radiologists. We designed and built a labeling platform for DICOM images to facilitate these annotation procedures. All images are made publicly available (https://www.physionet.org/content/vindr-cxr/1.0.0/) in DICOM format along with the labels of both the training set and the test set., Comment: 11 pages, under review by Nature Scientific Data

The text-independent approach to writer identification does not require the writer to write some predetermined text. Previous research on text-independent writer identification has been based on identifying writer-specific features designed by experts. However, in the last decade, deep learning methods have been successfully applied to learn features from data automatically. We propose here an end-to-end deep-learning method for text-independent writer identification that does not require prior identification of features. A Convolutional Neural Network (CNN) is trained initially to extract local features, which represent characteristics of individual handwriting in the whole character images and their sub-regions. Randomly sampled tuples of images from the training set are used to train the CNN and aggregate the extracted local features of images from the tuples to form global features. For every training epoch, the process of randomly sampling tuples is repeated, which is equivalent to a large number of training patterns being prepared for training the CNN for text-independent writer identification. We conducted experiments on the JEITA-HP database of offline handwritten Japanese character patterns. With 200 characters, our method achieved an accuracy of 99.97% to classify 100 writers. Even when using 50 characters for 100 writers or 100 characters for 400 writers, our method achieved accuracy levels of 92.80% or 93.82%, respectively. We conducted further experiments on the Firemaker and IAM databases of offline handwritten English text. Using only one page per writer to train, our method achieved over 91.81% accuracy to classify 900 writers. Overall, we achieved a better performance than the previously published best result based on handcrafted features and clustering algorithms, which demonstrates the effectiveness of our method for handwritten English text also., Comment: 12 pages

In general, it is straightforward to render an offline handwriting image from an online handwriting pattern. However, it is challenging to reconstruct an online handwriting pattern given an offline handwriting image, especially for multiple-stroke character as Japanese kanji. The multiple-stroke character requires not only point coordinates but also stroke orders whose difficulty is exponential growth by the number of strokes. Besides, several crossed and touch points might increase the difficulty of the recovered task. We propose a deep neural network-based method to solve the recovered task using a large online handwriting database. Our proposed model has two main components: Convolutional Neural Network-based encoder and Long Short-Term Memory Network-based decoder with an attention layer. The encoder focuses on feature extraction while the decoder refers to the extracted features and generates the time-sequences of coordinates. We also demonstrate the effect of the attention layer to guide the decoder during the reconstruction. We evaluate the performance of the proposed method by both visual verification and handwritten character recognition. Although the visual verification reveals some problems, the recognition experiments demonstrate the effect of trajectory recovery in improving the accuracy of offline handwritten character recognition when online recognition for the recovered trajectories are combined., Comment: 9 pages, ICPR2020 (reviewing)

Building in silico models to predict chemical properties and activities is a crucial step in drug discovery. However, limited labeled data often hinders the application of deep learning in this setting. Meanwhile advances in meta-learning have enabled state-of-the-art performances in few-shot learning benchmarks, naturally prompting the question: Can meta-learning improve deep learning performance in low-resource drug discovery projects? In this work, we assess the transferability of graph neural networks initializations learned by the Model-Agnostic Meta-Learning (MAML) algorithm - and its variants FO-MAML and ANIL - for chemical properties and activities tasks. Using the ChEMBL20 dataset to emulate low-resource settings, our benchmark shows that meta-initializations perform comparably to or outperform multi-task pre-training baselines on 16 out of 20 in-distribution tasks and on all out-of-distribution tasks, providing an average improvement in AUPRC of 11.2% and 26.9% respectively. Finally, we observe that meta-initializations consistently result in the best performing models across fine-tuning sets with $k \in \{16, 32, 64, 128, 256\}$ instances., Comment: ICML 2020 Workshop on Graph Representation Learning and Beyond (GRL+)

We introduce a new and rigorously-formulated PAC-Bayes meta-learning algorithm that solves few-shot learning. Our proposed method extends the PAC-Bayes framework from a single task setting to the meta-learning multiple task setting to upper-bound the error evaluated on any, even unseen, tasks and samples. We also propose a generative-based approach to estimate the posterior of task-specific model parameters more expressively compared to the usual assumption based on a multivariate normal distribution with a diagonal covariance matrix. We show that the models trained with our proposed meta-learning algorithm are well calibrated and accurate, with state-of-the-art calibration and classification results on few-shot classification (mini-ImageNet and tiered-ImageNet) and regression (multi-modal task-distribution regression) benchmarks., Comment: Add background and directly specify meta-learning as a bi-level optimisation

We introduce a new measure to evaluate the transferability of representations learned by classifiers. Our measure, the Log Expected Empirical Prediction (LEEP), is simple and easy to compute: when given a classifier trained on a source data set, it only requires running the target data set through this classifier once. We analyze the properties of LEEP theoretically and demonstrate its effectiveness empirically. Our analysis shows that LEEP can predict the performance and convergence speed of both transfer and meta-transfer learning methods, even for small or imbalanced data. Moreover, LEEP outperforms recently proposed transferability measures such as negative conditional entropy and H scores. Notably, when transferring from ImageNet to CIFAR100, LEEP can achieve up to 30% improvement compared to the best competing method in terms of the correlations with actual transfer accuracy., Comment: Published at the International Conference on Machine Learning (ICML) 2020