skip to main content


Search for: All records

Creators/Authors contains: "Zhang, Ziming"

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. Free, publicly-accessible full text available April 27, 2024
  2. Free, publicly-accessible full text available April 27, 2024
  3. Deep learning often relies on the availability of a large amount of high-quality labeled data, which can be very limited in novel domains. To address such data scarcity, domain adaptation is one promising approach that allows for deep networks to leverage large amounts of available data from a source domain to enhance the model’s efficacy on the target domain of interest. However, while there is a plethora of alternate models for domain adaptation proposed over many years in the literature, there is a dearth of studies that objectively compare the relative effectiveness of these models in a rigorous, empirical study. To fill this gap, we provide a thorough, unbiased, empirical study of five state-of-the-art (SOTA) deep domain adaptation models proposed over the past 6 years whose codes are publicly available. Models are evaluated on the complex and diverse domain adaptation tasks featured in the DomainNet benchmark dataset as well as the popular Office-31 dataset. Our results suggest that (1) all 5 models perform similarly, on average, and do not even significantly beat the oldest model, and (2) counter to their intended purpose, the transfer loss functions in the literature do not contribute significantly to learning transferable representations. Our observations suggest that domain adaptation research needs to more thoroughly compare newly proposed models against existing works, along with assessing their loss functions’ utility thoroughly. Our code and data splits are made public for reproducibility of results by the community. 
    more » « less
  4. Lightweight neural networks refer to deep networks with small numbers of parameters, which can be deployed in resource-limited hardware such as embedded systems. To learn such lightweight networks effectively and efficiently, in this paper we propose a novel convolutional layer, namely Channel-Split Recurrent Convolution (CSR-Conv), where we split the output channels to generate data sequences with length T as the input to the recurrent layers with shared weights. As a consequence, we can construct lightweight convolutional networks by simply replacing (some) linear convolutional layers with CSR-Conv layers. We prove that under mild conditions the model size decreases with the rate of O( 1 ). Empirically we demonstrate the state-of-the-art T2 performance using VGG-16, ResNet-50, ResNet-56, ResNet- 110, DenseNet-40, MobileNet, and EfficientNet as backbone networks on CIFAR-10 and ImageNet. Codes can be found on https://github.com/tuaxon/CSR Conv. 
    more » « less
  5. Corrosion of materials impacts critical economic sectors from infrastructure, transportation, defense, health, to the environment. The development of safe anti-corrosive materials is thus an important area of study in materials science. Corrosion science of preparing materials and then monitoring their corrosion under adverse conditions is labor intensive, time consuming, and extremely costly. While deep learning has become popular in automating various engineering tasks, the development of deep models for corrosion assessment is lacking. We are the first to study deep domain adaptation (DA) models for the automated assessment of the corrosion status of anti-corrosive materials. Corrosion data, i.e., photographic images of treated corroding materials, is abundant when produced in artificially controlled laboratory settings, while corrosion image data sets from rich natural outdoor environments are more challenging to produce and thus much smaller. We leverage the more readily available indoor corrosion data to train a classifier and then transfer it via deep domain adaptation to also perform well on the small yet more realistic outdoor corrosion image data set – without requiring target labels. We empirically compare 5 popular domain adaptation models on real-world corrosion image data sets. Our study finds that DA achieves 27% improvement in test accuracy compared to the performance of the no-DA baseline for classifying real-world outdoor corrosion data. 
    more » « less
  6. Cross-modal vehicle localization is an important task for automated driving systems. This research proposes a novel approach based on LiDAR point clouds and OpenStreetMaps (OSM) via a constrained particle filter, which significantly improves the vehicle localization accuracy. The OSM modality provides not only a platform to generate simulated point cloud images, but also geometrical constraints (e.g., roads) to improve the particle filter’s final result. The proposed approach is deterministic without any learning component or need for labelled data. Evaluated by using the KITTI dataset, it achieves accurate vehicle pose tracking with a position error of less than 3 m when considering the mean error across all the sequences. This method shows state-of-the-art accuracy when compared with the existing methods based on OSM or satellite maps. 
    more » « less