More Like this

1. EQAdap: Equipollent Domain Adaptation Approach to Image Deblurring

   https://doi.org/10.1109/access.2022.3203736  

   Jalata, Ibsa; Chappa, Naga Venkata; Truong, Thanh-Dat; Helton, Pierce; Rainwater, Chase; Luu, Khoa (January 2022, IEEE Access)
2. Statistical Guarantees for Unpaired Image-to-Image Cross-domain Analysis using GANs

   Chakraborty, Saptarshi; Bartlett, Peter L (May 2025, Proceedings of Machine Learning Research)
3. Transferring Indoor Corrosion Image Assessment Models to Outdoor Images via Domain Adaptation

   https://doi.org/10.1109/ICMLA55696.2022.00219  

   Josselyn, Nicholas; Yin, Biao; Considine, Thomas; Kelley, John; Rinderspacher, Berend; Jensen, Robert; Snyder, James; Zhang, Ziming; Rundensteiner, Elke (December 2022, 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA))

   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
4. Iterative Image Translation for Unsupervised Domain Adaptation

   https://doi.org/10.1145/3476098.3485050  

   Chhabra, Sachin; Venkateswara, Hemanth; Li, Baoxin (October 2021, MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021)

   In this paper, we propose an image-translation-based unsupervised domain adaptation approach that iteratively trains an image translation and a classification network using each other. In Phase A, a classification network is used to guide the image translation to preserve the content and generate images. In Phase B, the generated images are used to train the classification network. With each step, the classification network and generator improve each other to learn the target domain representation. Detailed analysis and the experiments are testimony of the strength of our approach. 

   more » « less
5. Few-shot Image Generation via Cross-domain Correspondence

   https://doi.org/10.1109/cvpr46437.2021.01060  

   Ojha, Utkarsh; Li, Yijun; Lu, Jingwan; Efros, Alexei A.; Lee, Yong Jae; Shechtman, Eli; Zhang, Richard (June 2021, Conference on Computer Vision and Pattern Recognition (CVPR))

   Training generative models, such as GANs, on a target domain containing limited examples (e.g., 10) can easily result in overfitting. In this work, we seek to utilize a large source domain for pretraining and transfer the diversity information from source to target. We propose to preserve the relative similarities and differences between instances in the source via a novel cross-domain distance consistency loss. To further reduce overfitting, we present an anchor-based strategy to encourage different levels of realism over different regions in the latent space. With extensive results in both photorealistic and non-photorealistic domains, we demonstrate qualitatively and quantitatively that our few-shot model automatically discovers correspondences between source and target domains and generates more diverse and realistic images than previous methods. 

   more » « less