Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks

Skeleton Ground Truth (GT) is critical to the success of supervised skeleton extraction methods, especially with the popularity of deep learning techniques. Furthermore, we see skeleton GTs used not only for training skeleton detectors with Convolutional Neural Networks (CNN) but also for evaluating skeleton-related pruning and matching algorithms. However, most existing shape and image datasets suffer from the lack of skeleton GT and inconsistency of GT standards. As a result, it is difficult to evaluate and reproduce CNN-based skeleton detectors and algorithms on a fair basis. In this paper, we present a heuristic strategy for object skeleton GT extraction in binary shapes and natural images. Our strategy is built on an extended theory of diagnosticity hypothesis, which enables encoding human-in-the-loop GT extraction based on clues from the target's context, simplicity, and completeness. Using this strategy, we developed a tool, SkeView, to generate skeleton GT of 17 existing shape and image datasets. The GTs are then structurally evaluated with representative methods to build viable baselines for fair comparisons. Experiments demonstrate that GTs generated by our strategy yield promising quality with respect to standard consistency, and also provide a balance between simplicity and completeness.

A Radiomics-Incorporated Deep Ensemble Learning Model for Multi-Parametric MRI-based Glioma Segmentation

We developed a deep ensemble learning model with a radiomics spatial encoding execution for improved glioma segmentation accuracy using multi-parametric MRI (mp-MRI). This model was developed using 369 glioma patients with a 4-modality mp-MRI protocol: T1, contrast-enhanced T1 (T1-Ce), T2, and FLAIR. In each modality volume, a 3D sliding kernel was implemented across the brain to capture image heterogeneity: fifty-six radiomic features were extracted within the kernel, resulting in a 4th order tensor. Each radiomic feature can then be encoded as a 3D image volume, namely a radiomic feature map (RFM). PCA was employed for data dimension reduction and the first 4 PCs were selected. Four deep neural networks as sub-models following the U-Net architecture were trained for the segmenting of a region-of-interest (ROI): each sub-model utilizes the mp-MRI and 1 of the 4 PCs as a 5-channel input for a 2D execution. The 4 softmax probability results given by the U-net ensemble were superimposed and binarized by Otsu method as the segmentation result. Three ensemble models were trained to segment enhancing tumor (ET), tumor core (TC), and whole tumor (WT). The adopted radiomics spatial encoding execution enriches the image heterogeneity information that leads to the successful demonstration of the proposed deep ensemble model, which offers a new tool for mp-MRI based medical image segmentation.

A Comprehensive Survey of Graph-level Learning

Graphs have a superior ability to represent relational data, like chemical compounds, proteins, and social networks. Hence, graph-level learning, which takes a set of graphs as input, has been applied to many tasks including comparison, regression, classification, and more. Traditional approaches to learning a set of graphs tend to rely on hand-crafted features, such as substructures. But while these methods benefit from good interpretability, they often suffer from computational bottlenecks as they cannot skirt the graph isomorphism problem. Conversely, deep learning has helped graph-level learning adapt to the growing scale of graphs by extracting features automatically and decoding graphs into low-dimensional representations. As a result, these deep graph learning methods have been responsible for many successes. Yet, there is no comprehensive survey that reviews graph-level learning starting with traditional learning and moving through to the deep learning approaches. This article fills this gap and frames the representative algorithms into a systematic taxonomy covering traditional learning, graph-level deep neural networks, graph-level graph neural networks, and graph pooling. To ensure a thoroughly comprehensive survey, the evolutions, interactions, and communications between methods from four different branches of development are also examined. This is followed by a brief review of the benchmark data sets, evaluation metrics, and common downstream applications. The survey concludes with 13 future directions of necessary research that will help to overcome the challenges facing this booming field.

Shadow-Oriented Tracking Method for Multi-Target Tracking in Video-SAR

This work focuses on multi-target tracking in Video synthetic aperture radar. Specifically, we refer to tracking based on targets' shadows. Current methods have limited accuracy as they fail to consider shadows' characteristics and surroundings fully. Shades are low-scattering and varied, resulting in missed tracking. Surroundings can cause interferences, resulting in false tracking. To solve these, we propose a shadow-oriented multi-target tracking method (SOTrack). To avoid false tracking, a pre-processing module is proposed to enhance shadows from surroundings, thus reducing their interferences. To avoid missed tracking, a detection method based on deep learning is designed to thoroughly learn shadows' features, thus increasing the accurate estimation. And further, a recall module is designed to recall missed shadows. We conduct experiments on measured data. Results demonstrate that, compared with other methods, SOTrack achieves much higher performance in tracking accuracy-18.4%. And ablation study confirms the effectiveness of the proposed modules.

Quantifying U-Net Uncertainty in Multi-Parametric MRI-based Glioma Segmentation by Spherical Image Projection

Purpose: To develop a U-Net segmentation uncertainty quantification method based on spherical image projection of multi-parametric MRI (MP-MRI) in glioma segmentation. Methods: The projection of planar MRI onto a spherical surface retains global anatomical information. By incorporating such image transformation in our proposed spherical projection-based U-Net (SPU-Net) segmentation model design, multiple segmentation predictions can be obtained for a single MRI. The final segmentation is the average of all predictions, and the variation can be shown as an uncertainty map. An uncertainty score was introduced to compare the uncertainty measurements' performance. The SPU-Net model was implemented on 369 glioma patients with MP-MRI scans. Three SPU-Nets were trained to segment enhancing tumor (ET), tumor core (TC), and whole tumor (WT), respectively. The SPU-Net was compared with (1) classic U-Net with test-time augmentation (TTA) and (2) linear scaling-based U-Net (LSU-Net) in both segmentation accuracy (Dice coefficient) and uncertainty (uncertainty map and uncertainty score). Results: The SPU-Net achieved low uncertainty for correct segmentation predictions (e.g., tumor interior or healthy tissue interior) and high uncertainty for incorrect results (e.g., tumor boundaries). This model could allow the identification of missed tumor targets or segmentation errors in U-Net. The SPU-Net achieved the highest uncertainty scores for 3 targets (ET/TC/WT): 0.826/0.848/0.936, compared to 0.784/0.643/0.872 for the U-Net with TTA and 0.743/0.702/0.876 for the LSU-Net. The SPU-Net also achieved statistically significantly higher Dice coefficients. Conclusion: The SPU-Net offers a powerful tool to quantify glioma segmentation uncertainty while improving segmentation accuracy. The proposed method can be generalized to other medical image-related deep-learning applications for uncertainty evaluation.

Complicated Background Suppression of ViSAR Image For Moving Target Shadow Detection

The existing Video Synthetic Aperture Radar (ViSAR) moving target shadow detection methods based on deep neural networks mostly generate numerous false alarms and missing detections, because of the foreground-background indistinguishability. To solve this problem, we propose a method to suppress complicated background of ViSAR for moving target detection. In this work, the proposed method is used to suppress background; then, we use several target detection networks to detect the moving target shadows. The experimental result shows that the proposed method can effectively suppress the interference of complicated back-ground information and improve the accuracy of moving target shadow detection in ViSAR. The existing Video Synthetic Aperture Radar (ViSAR) moving target shadow detection methods based on deep neural networks mostly generate numerous false alarms and missing detections, because of the foreground-background indistinguishability. To solve this problem, we propose a method to suppress complicated background of ViSAR for moving target detection. In this work, the proposed method is used to suppress background; then, we use several target detection networks to detect the moving target shadows. The experimental result shows that the proposed method can effectively suppress the interference of complicated back-ground information and improve the accuracy of moving target shadow detection in ViSAR.

Generating Coherent Narratives by Learning Dynamic and Discrete Entity States with a Contrastive Framework

Despite advances in generating fluent texts, existing pretraining models tend to attach incoherent event sequences to involved entities when generating narratives such as stories and news. We conjecture that such issues result from representing entities as static embeddings of superficial words, while neglecting to model their ever-changing states, i.e., the information they carry, as the text unfolds. Therefore, we extend the Transformer model to dynamically conduct entity state updates and sentence realization for narrative generation. We propose a contrastive framework to learn the state representations in a discrete space, and insert additional attention layers into the decoder to better exploit these states. Experiments on two narrative datasets show that our model can generate more coherent and diverse narratives than strong baselines with the guidance of meaningful entity states.

Shadow-Background-Noise 3D Spatial Decomposition Using Sparse Low-Rank Gaussian Properties for Video-SAR Moving Target Shadow Enhancement

Moving target shadows among video synthetic aperture radar (Video-SAR) images are always interfered by low scattering backgrounds and cluttered noises, causing poor moving target shadow detection-tracking performance. To solve this problem, this letter proposes a shadow-background-noise 3D spatial de-composition method named SBN-3D-SD to boost shadow saliency for better Video-SAR moving target shadow detection-tracking performance.

Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text Generation

Despite the success of text-to-text pre-trained models in various natural language generation (NLG) tasks, the generation performance is largely restricted by the number of labeled data in downstream tasks, particularly in data-to-text generation tasks. Existing works mostly utilize abundant unlabeled structured data to conduct unsupervised pre-training for task adaption, which fail to model the complex relationship between source structured data and target texts. Thus, we introduce self-training as a better few-shot learner than task-adaptive pre-training, which explicitly captures this relationship via pseudo-labeled data generated by the pre-trained model. To alleviate the side-effect of low-quality pseudo-labeled data during self-training, we propose a novel method called Curriculum-Based Self-Training (CBST) to effectively leverage unlabeled data in a rearranged order determined by the difficulty of text generation. Experimental results show that our method can outperform fine-tuning and task-adaptive pre-training methods, and achieve state-of-the-art performance in the few-shot setting of data-to-text generation.

LaMemo: Language Modeling with Look-Ahead Memory

Although Transformers with fully connected self-attentions are powerful to model long-term dependencies, they are struggling to scale to long texts with thousands of words in language modeling. One of the solutions is to equip the model with a recurrence memory. However, existing approaches directly reuse hidden states from the previous segment that encodes contexts in a uni-directional way. As a result, this prohibits the memory to dynamically interact with the current context that provides up-to-date information for token prediction. To remedy this issue, we propose Look-Ahead Memory (LaMemo) that enhances the recurrence memory by incrementally attending to the right-side tokens, and interpolating with the old memory states to maintain long-term information in the history. LaMemo embraces bi-directional attention and segment recurrence with an additional computation overhead only linearly proportional to the memory length. Experiments on widely used language modeling benchmarks demonstrate its superiority over the baselines equipped with different types of memory.