skip to main content

Search for: All records

Creators/Authors contains: "Wu, T."

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Deformable image registration (DIR), aiming to find spatial correspondence between images, is one of the most critical problems in the domain of medical image analysis. In this paper, we present a novel, generic, and accurate diffeomorphic image registration framework that utilizes neural ordinary differential equations (NODEs). We model each voxel as a moving particle and consider the set of all voxels in a 3D image as a high-dimensional dynamical system whose trajectory determines the targeted deformation field. Our method leverages deep neural networks for their expressive power in modeling dynamical systems, and simultaneously optimizes for a dynamical system between the image pairs and the corresponding transformation. Our formulation allows various constraints to be imposed along the transformation to maintain desired regularities. Our experiment results show that our method outperforms the benchmarks under various metrics. Additionally, we demonstrate the feasibility to expand our framework to register multiple image sets using a unified form of transformation, which could possibly serve a wider range of applications.
    Free, publicly-accessible full text available June 1, 2023
  2. Free, publicly-accessible full text available May 20, 2023
  3. Acoustic scattering is strongly influenced by the boundary geometry of objects over which sound scatters. The present work proposes a method to infer object geometry from scattering features by training convolutional neural networks. The training data is generated from a fast numerical solver developed on CUDA. The complete set of simulations is sampled to generate multiple datasets containing different amounts of channels and diverse image resolutions. The robustness of our approach in response to data degradation is evaluated by comparing the performance of networks trained using the datasets with varying levels of data degradation. The present work has found that the predictions made from our models match ground truth with high accuracy. In addition, accuracy does not degrade when fewer data channels or lower resolutions are used.
  4. Vedaldi, A. (Ed.)
    In state-of-the-art deep neural networks, both feature normalization and feature attention have become ubiquitous. They are usually studied as separate modules, however. In this paper, we propose a light-weight integration between the two schema and present Attentive Normalization (AN). Instead of learning a single affine transformation, AN learns a mixture of affine transformations and utilizes their weighted-sum as the final affine transformation applied to re-calibrate features in an instance-specific way. The weights are learned by leveraging channel-wise feature attention. In experiments, we test the proposed AN using four representative neural architectures. In the ImageNet-1000 classification benchmark and the MS-COCO 2017 object detection and instance segmentation benchmark. AN obtains consistent performance improvement for different neural architectures in both benchmarks with absolute increase of top-1 accuracy in ImageNet-1000 between 0.5\% and 2.7\%, and absolute increase up to 1.8\% and 2.2\% for bounding box and mask AP in MS-COCO respectively. We observe that the proposed AN provides a strong alternative to the widely used Squeeze-and-Excitation (SE) module. The source codes are publicly available at \href{https://github.com/iVMCL/AOGNet-v2}{the ImageNet Classification Repo} and \href{https://github.com/iVMCL/AttentiveNorm\_Detection}{the MS-COCO Detection and Segmentation Repo}.
  5. Free, publicly-accessible full text available December 11, 2022
  6. Isotopic measurements of organic carbon (δ13Corg), carbonate carbon (δ13Ccarb), and oxygen (δ18Ocarb) were made at low stratigraphic resolution on samples from International Ocean Discovery Program (IODP) Expedition 369, Hole U1515A (southeast Indian Ocean). The δ13Corg values ranged from −30.2‰ to −21.0‰, with an average of −24‰ ± 2‰, whereas δ13Ccarb values ranged from 0.5‰ to 1.4‰ with an average of 1.1‰ ± 0.3‰. Carbonate δ18Ocarb values averaged 1.1‰ ± 0.8‰ and ranged from −0.3‰ to 2.4‰. Initial plans were to use the δ13Ccarb and δ13Corg profiles to identify changes in the carbon cycle at the site and to compare local patterns to global records; however, poor core recovery and lack of solid age control limited the number of suitable samples and precluded meaningful interpretation of stratigraphic patterns.