Spectral Measurement Sparsification for Pose-Graph SLAM

Simultaneous localization and mapping (SLAM) is a critical capability in autonomous navigation, but in order to scale SLAM to the setting of "lifelong" SLAM, particularly under memory or computation constraints, a robot must be able to determine what information should be retained and what can safely be forgotten. In graph-based SLAM, the number of edges (measurements) in a pose graph determines both the memory requirements of storing a robot's observations and the computational expense of algorithms deployed for performing state estimation using those observations; both of which can grow unbounded during long-term navigation. To address this, we propose a spectral approach for pose graph sparsification which maximizes the algebraic connectivity of the sparsified measurement graphs, a key quantity which has been shown to control the estimation error of pose graph SLAM solutions. Our algorithm, MAC (for "maximizing algebraic connectivity"), which is based on convex relaxation, is simple and computationally inexpensive, and admits formal post hoc performance guarantees on the quality of the solutions it provides. In experiments on benchmark pose-graph SLAM datasets, we show that our approach quickly produces high-quality sparsification results which retain the connectivity of the graph and, in turn, the quality of corresponding SLAM solutions, as compared to a baseline approach which does not consider graph connectivity.

Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism

Interpretable graph learning is in need as many scientific applications depend on learning models to collect insights from graph-structured data. Previous works mostly focused on using post-hoc approaches to interpret a pre-trained model (graph neural network models in particular). They argue against inherently interpretable models because good interpretation of these models is often at the cost of their prediction accuracy. And, the widely used attention mechanism for inherent interpretation often fails to provide faithful interpretation in graph learning tasks. In this work, we address both issues by proposing Graph Stochastic Attention (GSAT), an attention mechanism derived from the information bottleneck principle. GSAT leverages stochastic attention to block the information from the task-irrelevant graph components while learning stochasticity-reduced attention to select the task-relevant subgraphs for interpretation. GSAT can also apply to fine-tuning and interpreting pre-trained models via stochastic attention mechanism. Extensive experiments on eight datasets show that GSAT outperforms the state-of-the-art methods by up to 20%$\uparrow$ in interpretation AUC and 5%$\uparrow$ in prediction accuracy.

Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention

We present a simple but effective attention named the unary-pairwise attention (UPA) for modeling the relationship between 3D point clouds. Our idea is motivated by the analysis that the standard self-attention (SA) that operates globally tends to produce almost the same attention maps for different query positions, revealing difficulties for learning query-independent and query-dependent information jointly. Therefore, we reformulate the SA and propose query-independent (Unary) and query-dependent (Pairwise) components to facilitate the learning of both terms. In contrast to the SA, the UPA ensures query dependence via operating locally. Extensive experiments show that the UPA outperforms the SA consistently on various point cloud understanding tasks including shape classification, part segmentation, and scene segmentation. Moreover, simply equipping the popular PointNet++ method with the UPA even outperforms or is on par with the state-of-the-art attention-based approaches. In addition, the UPA systematically boosts the performance of both standard and modern networks when it is integrated into them as a compositional module.

Computerization of Clinical Pathways: A Literature Review and Directions for Future Research

Clinical Pathways (CP) are medical management plans developed to standardize patient treatment activities, optimize resource usage, reduce expenses, and improve the quality of healthcare services. Most CPs currently in use are paper-based documents (i.e., not computerized). CP computerization has been an active research topic since the inception of CP use in hospitals. This literature review research aims to examine studies that focused on CP computerization and offers recommendations for future research in this important research area. Some critical research suggestions include centralizing computerized CPs in Healthcare Information Systems (HIS), CP term standardization using international medical terminology systems, developing a global CP-specific digital coding system, creating a unified CP meta-ontology, developing independent Clinical Pathway Management Systems (CPMS), and supporting CPMSs with machine learning sub-systems.

Multi-scale Sparse Representation-Based Shadow Inpainting for Retinal OCT Images

Inpainting shadowed regions cast by superficial blood vessels in retinal optical coherence tomography (OCT) images is critical for accurate and robust machine analysis and clinical diagnosis. Traditional sequence-based approaches such as propagating neighboring information to gradually fill in the missing regions are cost-effective. But they generate less satisfactory outcomes when dealing with larger missing regions and texture-rich structures. Emerging deep learning-based methods such as encoder-decoder networks have shown promising results in natural image inpainting tasks. However, they typically need a long computational time for network training in addition to the high demand on the size of datasets, which makes it difficult to be applied on often small medical datasets. To address these challenges, we propose a novel multi-scale shadow inpainting framework for OCT images by synergically applying sparse representation and deep learning: sparse representation is used to extract features from a small amount of training images for further inpainting and to regularize the image after the multi-scale image fusion, while convolutional neural network (CNN) is employed to enhance the image quality. During the image inpainting, we divide preprocessed input images into different branches based on the shadow width to harvest complementary information from different scales. Finally, a sparse representation-based regularizing module is designed to refine the generated contents after multi-scale feature aggregation. Experiments are conducted to compare our proposal versus both traditional and deep learning-based techniques on synthetic and real-world shadows. Results demonstrate that our proposed method achieves favorable image inpainting in terms of visual quality and quantitative metrics, especially when wide shadows are presented.

Optimising Communication Overhead in Federated Learning Using NSGA-II

Federated learning is a training paradigm according to which a server-based model is cooperatively trained using local models running on edge devices and ensuring data privacy. These devices exchange information that induces a substantial communication load, which jeopardises the functioning efficiency. The difficulty of reducing this overhead stands in achieving this without decreasing the model's efficiency (contradictory relation). To do so, many works investigated the compression of the pre/mid/post-trained models and the communication rounds, separately, although they jointly contribute to the communication overload. Our work aims at optimising communication overhead in federated learning by (I) modelling it as a multi-objective problem and (II) applying a multi-objective optimization algorithm (NSGA-II) to solve it. To the best of the author's knowledge, this is the first work that \texttt{(I)} explores the add-in that evolutionary computation could bring for solving such a problem, and \texttt{(II)} considers both the neuron and devices features together. We perform the experimentation by simulating a server/client architecture with 4 slaves. We investigate both convolutional and fully-connected neural networks with 12 and 3 layers, 887,530 and 33,400 weights, respectively. We conducted the validation on the \texttt{MNIST} dataset containing 70,000 images. The experiments have shown that our proposal could reduce communication by 99% and maintain an accuracy equal to the one obtained by the FedAvg Algorithm that uses 100% of communications.

Decontextualized I3D ConvNet for ultra-distance runners performance analysis at a glance

In May 2021, the site runnersworld.com published that participation in ultra-distance races has increased by 1,676% in the last 23 years. Moreover, nearly 41% of those runners participate in more than one race per year. The development of wearable devices has undoubtedly contributed to motivating participants by providing performance measures in real-time. However, we believe there is room for improvement, particularly from the organizers point of view. This work aims to determine how the runners performance can be quantified and predicted by considering a non-invasive technique focusing on the ultra-running scenario. In this sense, participants are captured when they pass through a set of locations placed along the race track. Each footage is considered an input to an I3D ConvNet to extract the participant's running gait in our work. Furthermore, weather and illumination capture conditions or occlusions may affect these footages due to the race staff and other runners. To address this challenging task, we have tracked and codified the participant's running gait at some RPs and removed the context intending to ensure a runner-of-interest proper evaluation. The evaluation suggests that the features extracted by an I3D ConvNet provide enough information to estimate the participant's performance along the different race tracks.

OCR quality affects perceived usefulness of historical newspaper clippings -- a user study

Effects of Optical Character Recognition (OCR) quality on historical information retrieval have so far been studied in data-oriented scenarios regarding the effectiveness of retrieval results. Such studies have either focused on the effects of artificially degraded OCR quality (see, e.g., [1-2]) or utilized test collections containing texts based on authentic low quality OCR data (see, e.g., [3]). In this paper the effects of OCR quality are studied in a user-oriented information retrieval setting. Thirty-two users evaluated subjectively query results of six topics each (out of 30 topics) based on pre-formulated queries using a simulated work task setting. To the best of our knowledge our simulated work task experiment is the first one showing empirically that users' subjective relevance assessments of retrieved documents are affected by a change in the quality of optically read text. Users of historical newspaper collections have so far commented effects of OCR'ed data quality mainly in impressionistic ways, and controlled user environments for studying effects of OCR quality on users' relevance assessments of the retrieval results have so far been missing. To remedy this The National Library of Finland (NLF) set up an experimental query environment for the contents of one Finnish historical newspaper, Uusi Suometar 1869-1918, to be able to compare users' evaluation of search results of two different OCR qualities for digitized newspaper articles. The query interface was able to present the same underlying document for the user based on two alternatives: either based on the lower OCR quality, or based on the higher OCR quality, and the choice was randomized. The users did not know about quality differences in the article texts they evaluated. The main result of the study is that improved optical character recognition quality affects perceived usefulness of historical newspaper articles significantly. The mean average evaluation score for the improved OCR results was 7.94% higher than the mean average evaluation score of the old OCR results.

High-fidelity GAN Inversion with Padding Space

Inverting a Generative Adversarial Network (GAN) facilitates a wide range of image editing tasks using pre-trained generators. Existing methods typically employ the latent space of GANs as the inversion space yet observe the insufficient recovery of spatial details. In this work, we propose to involve the padding space of the generator to complement the latent space with spatial information. Concretely, we replace the constant padding (e.g., usually zeros) used in convolution layers with some instance-aware coefficients. In this way, the inductive bias assumed in the pre-trained model can be appropriately adapted to fit each individual image. Through learning a carefully designed encoder, we manage to improve the inversion quality both qualitatively and quantitatively, outperforming existing alternatives. We then demonstrate that such a space extension barely affects the native GAN manifold, hence we can still reuse the prior knowledge learned by GANs for various downstream applications. Beyond the editing tasks explored in prior arts, our approach allows a more flexible image manipulation, such as the separate control of face contour and facial details, and enables a novel editing manner where users can customize their own manipulations highly efficiently.

Speech-enhanced and Noise-aware Networks for Robust Speech Recognition

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability. In this paper, a noise-aware training framework based on two cascaded neural structures is proposed to jointly optimize speech enhancement and speech recognition. The feature enhancement module is composed of a multi-task autoencoder, where noisy speech is decomposed into clean speech and noise. By concatenating its enhanced, noise-aware, and noisy features for each frame, the acoustic-modeling module maps each feature-augmented frame into a triphone state by optimizing the lattice-free maximum mutual information and cross entropy between the predicted and actual state sequences. On top of the factorized time delay neural network (TDNN-F) and its convolutional variant (CNN-TDNNF), both with SpecAug, the two proposed systems achieve word error rate (WER) of 3.90% and 3.55%, respectively, on the Aurora-4 task. Compared with the best existing systems that use bigram and trigram language models for decoding, the proposed CNN-TDNNF-based system achieves a relative WER reduction of 15.20% and 33.53%, respectively. In addition, the proposed CNN-TDNNF-based system also outperforms the baseline CNN-TDNNF system on the AMI task.