Counterfactual Regret Minimization (CFR) has achieved many fascinating results in solving large scale Imperfect Information Games (IIGs). Neural CFR is one of the promising techniques that can effectively reduce the computation and memory consumption of CFR by generalizing decision information between similar states. However, current neural CFR algorithms have to approximate the cumulative variables in iterations with neural networks, which usually results in large estimation variance given the huge complexity of IIGs. Moreover, model-based sampling and inefficient training make current neural CFR algorithms still computationally expensive. In this paper, a new model-free neural CFR algorithm with bootstrap learning is proposed, in which, a Recursive Substitute Value (RSV) network is trained to replace the cumulative variables in CFR. The RSV is defined recursively and can be estimated independently in every iteration using bootstrapping. Then there is no need to track or approximate the cumulative variables any more. Based on the RSV, the new neural CFR algorithm is model-free and has higher training efficiency. Experimental results show that the new algorithm can match the state-of-the-art neural CFR algorithms and with less training cost.
Pre-trained models, e.g., from ImageNet, have proven to be effective in boosting the performance of many downstream applications. It is too demanding to acquire large-scale annotations to build such models for medical imaging. Meanwhile, there are numerous clinical data (in the form of images and text reports) stored in the hospital information systems. The paired image-text data from the same patient study could be utilized for the pre-training task in a weakly supervised manner. However, the integrity, accessibility, and amount of such raw data vary across different institutes, e.g., paired vs. unpaired (image-only or text-only). In this work, we introduce an image-text pre-training framework that can learn from these raw data with mixed data inputs, i.e., paired image-text data, a mixture of paired and unpaired data. The unpaired data can be sourced from one or multiple institutes (e.g., images from one institute coupled with texts from another). Specifically, we propose a transformer-based training framework for jointly learning the representation of both the image and text data. In addition to the existing masked language modeling, multi-scale masked vision modeling is introduced as a self-supervised training task for image patch regeneration. We not only demonstrate the feasibility of pre-training across mixed data inputs but also illustrate the benefits of adopting such pre-trained models in 3 chest X-ray applications, i.e., classification, retrieval, and image regeneration. Superior results are reported in comparison to prior art using MIMIC-CXR, NIH14-CXR, and OpenI-CXR datasets.
Lightweight super resolution networks have extremely importance for real-world applications. In recent years several SR deep learning approaches with outstanding achievement have been introduced by sacrificing memory and computational cost. To overcome this problem, a novel lightweight super resolution network is proposed, which improves the SOTA performance in lightweight SR and performs roughly similar to computationally expensive networks. Multi-Path Residual Network designs with a set of Residual concatenation Blocks stacked with Adaptive Residual Blocks: ($i$) to adaptively extract informative features and learn more expressive spatial context information; ($ii$) to better leverage multi-level representations before up-sampling stage; and ($iii$) to allow an efficient information and gradient flow within the network. The proposed architecture also contains a new attention mechanism, Two-Fold Attention Module, to maximize the representation ability of the model. Extensive experiments show the superiority of our model against other SOTA SR approaches.
Signal propagation in an optical fiber can be described by the nonlinear Schr\"odinger equation (NLSE). The NLSE has no known closed-form solution, mostly due to the interaction of dispersion and nonlinearities. In this paper, we present a novel closed-form approximate model for the nonlinear optical channel, with applications to passive optical networks. The proposed model is derived using logarithmic perturbation in the frequency domain on the group-velocity dispersion (GVD) parameter of the NLSE. The model can be seen as an improvement of the recently proposed regular perturbation (RP) on the GVD parameter. RP and logarithmic perturbation (LP) on the nonlinear coefficient have already been studied in the literature, and are hereby compared with RP on the GVD parameter and the proposed LP model. As an application of the model, we focus on passive optical networks. For a 20 km PON at 10 Gbaud, the proposed model improves upon LP on the nonlinear coefficient by 1.5 dB. For the same system, a detector based on the proposed LP model reduces the uncoded bit-error-rate by up to 5.4 times at the same input power or reduces the input power by 0.4 dB at the same information rate.
Electroanatomical maps are a key tool in the diagnosis and treatment of atrial fibrillation. Current approaches focus on the activation times recorded. However, more information can be extracted from the available data. The fibers in cardiac tissue conduct the electrical wave faster, and their direction could be inferred from activation times. In this work, we employ a recently developed approach, called physics informed neural networks, to learn the fiber orientations from electroanatomical maps, taking into account the physics of the electrical wave propagation. In particular, we train the neural network to weakly satisfy the anisotropic eikonal equation and to predict the measured activation times. We use a local basis for the anisotropic conductivity tensor, which encodes the fiber orientation. The methodology is tested both in a synthetic example and for patient data. Our approach shows good agreement in both cases and it outperforms a state of the art method in the patient data. The results show a first step towards learning the fiber orientations from electroanatomical maps with physics-informed neural networks.
Time dependent data is a main source of information in today's data driven world. Generating this type of data though has shown its challenges and made it an interesting research area in the field of generative machine learning. One such approach was that by Smith et al. who developed Time Series Generative Adversarial Network (TSGAN) which showed promising performance in generating time dependent data and the ability of few shot generation though being flawed in certain aspects of training and learning. This paper looks to improve on the results from TSGAN and address those flaws by unifying the training of the independent networks in TSGAN and creating a dependency both in training and learning. This improvement, called unified TSGAN (uTSGAN) was tested and comapred both quantitatively and qualitatively to its predecessor on 70 benchmark time series data sets used in the community. uTSGAN showed to outperform TSGAN in 80\% of the data sets by the same number of training epochs and 60\% of the data sets in 3/4th the amount of training time or less while maintaining the few shot generation ability with better FID scores across those data sets.
The accurate prognosis of Glioblastoma Multiforme (GBM) plays an essential role in planning correlated surgeries and treatments. The conventional models of survival prediction rely on radiomic features using magnetic resonance imaging (MRI). In this paper, we propose a radiogenomic overall survival (OS) prediction approach by incorporating gene expression data with radiomic features such as shape, geometry, and clinical information. We exploit TCGA (The Cancer Genomic Atlas) dataset and synthesize the missing MRI modalities using a fully convolutional network (FCN) in a conditional Generative Adversarial Network (cGAN). Meanwhile, the same FCN architecture enables the tumor segmentation from the available and the synthesized MRI modalities. The proposed FCN architecture comprises octave convolution (OctConv) and a novel decoder, with skip connections in spatial and channel squeeze & excitation (skip-scSE) block. The OctConv can process low and high-frequency features individually and improve model efficiency by reducing channel-wise redundancy. Skip-scSE applies spatial and channel-wise excitation to signify the essential features and reduces the sparsity in deeper layers learning parameters using skip connections. The proposed approaches are evaluated by comparative experiments with state-of-the-art models in synthesis, segmentation, and overall survival (OS) prediction. We observe that adding missing MRI modality improves the segmentation prediction, and expression levels of gene markers have a high contribution in the GBM prognosis prediction, and fused radiogenomic features boost the OS estimation.
Prediction of human actions in social interactions has important applications in the design of social robots or artificial avatars. In this paper, we model human interaction generation as a discrete multi-sequence generation problem and present SocialInteractionGAN, a novel adversarial architecture for conditional interaction generation. Our model builds on a recurrent encoder-decoder generator network and a dual-stream discriminator. This architecture allows the discriminator to jointly assess the realism of interactions and that of individual action sequences. Within each stream a recurrent network operating on short subsequences endows the output signal with local assessments, better guiding the forthcoming generation. Crucially, contextual information on interacting participants is shared among agents and reinjected in both the generation and the discriminator evaluation processes. We show that the proposed SocialInteractionGAN succeeds in producing high realism action sequences of interacting people, comparing favorably to a diversity of recurrent and convolutional discriminator baselines. Evaluations are conducted using modified Inception Score and Fr{\'e}chet Inception Distance metrics, that we specifically design for discrete sequential generated data. The distribution of generated sequences is shown to approach closely that of real data. In particular our model properly learns the dynamics of interaction sequences, while exploiting the full range of actions.
We present a protocol to construct your own depth validation dataset for navigation. This protocol, called RDC for Rigid Depth Constructor, aims at being more accessible and cheaper than already existing techniques, requiring only a camera and a Lidar sensor to get started. We also develop a test suite to get insightful information from the evaluated algorithm. Finally, we take the example of UAV videos, on which we test two depth algorithms that were initially tested on KITTI and show that the drone context is dramatically different from in-car videos. This shows that a single context benchmark should not be considered reliable, and when developing a depth estimation algorithm, one should benchmark it on a dataset that best fits one's particular needs, which often means creating a brand new one. Along with this paper we provide the tool with an open source implementation and plan to make it as user-friendly as possible, to make depth dataset creation possible even for small teams. Our key contributions are the following: We propose a complete, open-source and almost fully automatic software application for creating validation datasets with densely annotated depth, adaptable to a wide variety of image, video and range data. It includes selection tools to adapt the dataset to specific validation needs, and conversion tools to other dataset formats. Using this application, we propose two new real datasets, outdoor and indoor, readily usable in UAV navigation context. Finally as examples, we show an evaluation of two depth prediction algorithms, using a collection of comprehensive (e.g. distribution based) metrics.
Text classification, as the task consisting in assigning categories to textual instances, is a very common task in information science. Methods learning distributed representations of words, such as word embeddings, have become popular in recent years as the features to use for text classification tasks. Despite the increasing use of word embeddings for text classification, these are generally used in an unsupervised manner, i.e. information derived from class labels in the training data are not exploited. While word embeddings inherently capture the distributional characteristics of words, and contexts observed around them in a large dataset, they aren't optimised to consider the distributions of words across categories in the classification dataset at hand. To optimise text representations based on word embeddings by incorporating class distributions in the training data, we propose the use of weighting schemes that assign a weight to embeddings of each word based on its saliency in each class. To achieve this, we introduce a novel weighting scheme, Term Frequency-Category Ratio (TF-CR), which can weight high-frequency, category-exclusive words higher when computing word embeddings. Our experiments on 16 classification datasets show the effectiveness of TF-CR, leading to improved performance scores over existing weighting schemes, with a performance gap that increases as the size of the training data grows.