Conflating/stitching 2.5D raster digital surface models (DSM) into a large one has been a running practice in geoscience applications, however, conflating full-3D mesh models, such as those from oblique photogrammetry, is extremely challenging. In this letter, we propose a novel approach to address this challenge by conflating multiple full-3D oblique photogrammetric models into a single, and seamless mesh for high-resolution site modeling. Given two or more individually collected and created photogrammetric meshes, we first propose to create a virtual camera field (with a panoramic field of view) to incubate virtual spaces represented by Truncated Signed Distance Field (TSDF), an implicit volumetric field friendly for linear 3D fusion; then we adaptively leverage the truncated bound of meshes in TSDF to conflate them into a single and accurate full 3D site model. With drone-based 3D meshes, we show that our approach significantly improves upon traditional methods for model conflations, to drive new potentials to create excessively large and accurate full 3D mesh models in support of geoscience and environmental applications.
相關內容
Deep Neural Networks (DNNs) are widely used for computer vision tasks. However, it has been shown that deep models are vulnerable to adversarial attacks, i.e., their performances drop when imperceptible perturbations are made to the original inputs, which may further degrade the following visual tasks or introduce new problems such as data and privacy security. Hence, metrics for evaluating the robustness of deep models against adversarial attacks are desired. However, previous metrics are mainly proposed for evaluating the adversarial robustness of shallow networks on the small-scale datasets. Although the Cross Lipschitz Extreme Value for nEtwork Robustness (CLEVER) metric has been proposed for large-scale datasets (e.g., the ImageNet dataset), it is computationally expensive and its performance relies on a tractable number of samples. In this paper, we propose the Adversarial Converging Time Score (ACTS), an attack-dependent metric that quantifies the adversarial robustness of a DNN on a specific input. Our key observation is that local neighborhoods on a DNN's output surface would have different shapes given different inputs. Hence, given different inputs, it requires different time for converging to an adversarial sample. Based on this geometry meaning, ACTS measures the converging time as an adversarial robustness metric. We validate the effectiveness and generalization of the proposed ACTS metric against different adversarial attacks on the large-scale ImageNet dataset using state-of-the-art deep networks. Extensive experiments show that our ACTS metric is an efficient and effective adversarial metric over the previous CLEVER metric.
The use of Deep Neural Network (DNN) models in risk-based decision-making has attracted extensive attention with broad applications in medical, finance, manufacturing, and quality control. To mitigate prediction-related risks in decision making, prediction confidence or uncertainty should be assessed alongside the overall performance of algorithms. Recent studies on Bayesian deep learning helps quantify prediction uncertainty arises from input noises and model parameters. However, the normality assumption of input noise in these models limits their applicability to problems involving categorical and discrete feature variables in tabular datasets. In this paper, we propose a mathematical framework to quantify prediction uncertainty for DNN models. The prediction uncertainty arises from errors in predictors that follow some known finite discrete distribution. We then conducted a case study using the framework to predict treatment outcome for tuberculosis patients during their course of treatment. The results demonstrate under a certain level of risk, we can identify risk-sensitive cases, which are prone to be misclassified due to error in predictors. Comparing to the Monte Carlo dropout method, our proposed framework is more aware of misclassification cases. Our proposed framework for uncertainty quantification in deep learning can support risk-based decision making in applications when discrete errors in predictors are present.
We investigate a novel modeling approach for end-to-end neural network training using hidden Markov models (HMM) where the transition probabilities between hidden states are modeled and learned explicitly. Most contemporary sequence-to-sequence models allow for from-scratch training by summing over all possible label segmentations in a given topology. In our approach there are explicit, learnable probabilities for transitions between segments as opposed to a blank label that implicitly encodes duration statistics. We implement a GPU-based forward-backward algorithm that enables the simultaneous training of label and transition probabilities. We investigate recognition results and additionally Viterbi alignments of our models. We find that while the transition model training does not improve recognition performance, it has a positive impact on the alignment quality. The generated alignments are shown to be viable targets in state-of-the-art Viterbi trainings.
Training a high performance end-to-end speech (E2E) processing model requires an enormous amount of labeled speech data, especially in the era of data-centric artificial intelligence. However, labeled speech data are usually scarcer and more expensive for collection, compared to textual data. We propose Latent Synthesis (LaSyn), an efficient textual data utilization framework for E2E speech processing models. We train a latent synthesizer to convert textual data into an intermediate latent representation of a pre-trained speech model. These pseudo acoustic representations of textual data augment acoustic data for model training. We evaluate LaSyn on low-resource automatic speech recognition (ASR) and spoken language understanding (SLU) tasks. For ASR, LaSyn improves an E2E baseline trained on LibriSpeech train-clean-100, with relative word error rate reductions over 22.3% on different test sets. For SLU, LaSyn improves our E2E baseline by absolute 4.1% for intent classification accuracy and 3.8% for slot filling SLU-F1 on SLURP, and absolute 4.49% and 2.25% for exact match (EM) and EM-Tree accuracies on STOP respectively. With fewer parameters, the results of LaSyn are competitive to published state-of-the-art works. The results demonstrate the quality of the augmented training data. The source code will be available to the community.
Expressive human speech generally abounds with rich and flexible speech prosody variations. The speech prosody predictors in existing expressive speech synthesis methods mostly produce deterministic predictions, which are learned by directly minimizing the norm of prosody prediction error. Its unimodal nature leads to a mismatch with ground truth distribution and harms the model's ability in making diverse predictions. Thus, we propose a novel prosody predictor based on the denoising diffusion probabilistic model to take advantage of its high-quality generative modeling and training stability. Experiment results confirm that the proposed prosody predictor outperforms the deterministic baseline on both the expressiveness and diversity of prediction results with even fewer network parameters.
Robotic grasping refers to making a robotic system pick an object by applying forces and torques on its surface. Many recent studies use data-driven approaches to address grasping, but the sparse reward nature of this task made the learning process challenging to bootstrap. To avoid constraining the operational space, an increasing number of works propose grasping datasets to learn from. But most of them are limited to simulations. The present paper investigates how automatically generated grasps can be exploited in the real world. More than 7000 reach-and-grasp trajectories have been generated with Quality-Diversity (QD) methods on 3 different arms and grippers, including parallel fingers and a dexterous hand, and tested in the real world. Conducted analysis on the collected measure shows correlations between several Domain Randomization-based quality criteria and sim-to-real transferability. Key challenges regarding the reality gap for grasping have been identified, stressing matters on which researchers on grasping should focus in the future. A QD approach has finally been proposed for making grasps more robust to domain randomization, resulting in a transfer ratio of 84% on the Franka Research 3 arm.
Diffusion MRI is a non-invasive, in-vivo biomedical imaging method for mapping tissue microstructure. Applications include structural connectivity imaging of the human brain and detecting microstructural neural changes. However, acquiring high signal-to-noise ratio dMRI datasets with high angular and spatial resolution requires prohibitively long scan times, limiting usage in many important clinical settings, especially for children, the elderly, and in acute neurological disorders that may require conscious sedation or general anesthesia. We employ a Swin UNEt Transformers model, trained on augmented Human Connectome Project data and conditioned on registered T1 scans, to perform generalized denoising of dMRI. We also qualitatively demonstrate super-resolution with artificially downsampled HCP data in normal adult volunteers. Remarkably, Swin UNETR can be fine-tuned for an out-of-domain dataset with a single example scan, as we demonstrate on dMRI of children with neurodevelopmental disorders and of adults with acute evolving traumatic brain injury, each cohort scanned on different models of scanners with different imaging protocols at different sites. We exceed current state-of-the-art denoising methods in accuracy and test-retest reliability of rapid diffusion tensor imaging requiring only 90 seconds of scan time. Applied to tissue microstructural modeling of dMRI, Swin UNETR denoising achieves dramatic improvements over the state-of-the-art for test-retest reliability of intracellular volume fraction and free water fraction measurements and can remove heavy-tail noise, improving biophysical modeling fidelity. Swin UNeTR enables rapid diffusion MRI with unprecedented accuracy and reliability, especially for probing biological tissues for scientific and clinical applications. The code and model are publicly available at //github.com/ucsfncl/dmri-swin.
Concurrent estimation and control of robotic systems remains an ongoing challenge, where controllers rely on data extracted from states/parameters riddled with uncertainties and noises. Framework suitability hinges on task complexity and computational constraints, demanding a balance between computational efficiency and mission-critical accuracy. This study leverages recent advancements in neuromorphic computing, particularly spiking neural networks (SNNs), for estimation and control applications. Our presented framework employs a recurrent network of leaky integrate-and-fire (LIF) neurons, mimicking a linear quadratic regulator (LQR) through a robust filtering strategy, a modified sliding innovation filter (MSIF). Benefiting from both the robustness of MSIF and the computational efficiency of SNN, our framework customizes SNN weight matrices to match the desired system model without requiring training. Additionally, the network employs a biologically plausible firing rule similar to predictive coding. In the presence of uncertainties, we compare the SNN-LQR-MSIF with non-spiking LQR-MSIF and the optimal linear quadratic Gaussian (LQG) strategy. Evaluation across a workbench linear problem and a satellite rendezvous maneuver, implementing the Clohessy-Wiltshire (CW) model in space robotics, demonstrates that the SNN-LQR-MSIF achieves acceptable performance in computational efficiency, robustness, and accuracy. This positions it as a promising solution for addressing dynamic systems' concurrent estimation and control challenges in dynamic systems.
Answering questions that require reading texts in an image is challenging for current models. One key difficulty of this task is that rare, polysemous, and ambiguous words frequently appear in images, e.g., names of places, products, and sports teams. To overcome this difficulty, only resorting to pre-trained word embedding models is far from enough. A desired model should utilize the rich information in multiple modalities of the image to help understand the meaning of scene texts, e.g., the prominent text on a bottle is most likely to be the brand. Following this idea, we propose a novel VQA approach, Multi-Modal Graph Neural Network (MM-GNN). It first represents an image as a graph consisting of three sub-graphs, depicting visual, semantic, and numeric modalities respectively. Then, we introduce three aggregators which guide the message passing from one graph to another to utilize the contexts in various modalities, so as to refine the features of nodes. The updated nodes have better features for the downstream question answering module. Experimental evaluations show that our MM-GNN represents the scene texts better and obviously facilitates the performances on two VQA tasks that require reading scene texts.
Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191