All Publications


  • Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation Shen, K., Jones, R., Kumar, A., Xie, S., HaoChen, J. Z., Ma, T., Liang, P., Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2022: 19847-19878
  • WILDS: A Benchmark of in-the-Wild Distribution Shifts Koh, P., Sagawa, S., Marklund, H., Xie, S., Zhang, M., Balsubramani, A., Hu, W., Yasunaga, M., Phillips, R., Gao, I., Lee, T., David, E., Stavness, I., Guo, W., Earnshaw, B. A., Haque, I. S., Beery, S., Leskovec, J., Kundaje, A., Pierson, E., Levine, S., Finn, C., Liang, P., Meila, M., Zhang, T. JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2021
  • Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization Xie, S., Ma, T., Liang, P., Meila, M., Zhang, T. JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2021
  • Weakly Supervised Deep Learning for Segmentation of Remote Sensing Imagery REMOTE SENSING Wang, S., Chen, W., Xie, S., Azzari, G., Lobell, D. B. 2020; 12 (2)

    View details for DOI 10.3390/rs12020207

    View details for Web of Science ID 000515569800006

  • Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance Jean, N., Xie, S., Ermon, S., Bengio, S., Wallach, H., Larochelle, H., Grauman, K., CesaBianchi, N., Garnett, R. NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2018
  • Combining satellite imagery and machine learning to predict poverty. Science Jean, N., Burke, M., Xie, M., Davis, W. M., Lobell, D. B., Ermon, S. 2016; 353 (6301): 790-794

    Abstract

    Reliable data on economic livelihoods remain scarce in the developing world, hampering efforts to study these outcomes and to design policies that improve them. Here we demonstrate an accurate, inexpensive, and scalable method for estimating consumption expenditure and asset wealth from high-resolution satellite imagery. Using survey and satellite data from five African countries--Nigeria, Tanzania, Uganda, Malawi, and Rwanda--we show how a convolutional neural network can be trained to identify image features that can explain up to 75% of the variation in local-level economic outcomes. Our method, which requires only publicly available data, could transform efforts to track and target poverty in developing countries. It also demonstrates how powerful machine learning techniques can be applied in a setting with limited training data, suggesting broad potential application across many scientific domains.

    View details for DOI 10.1126/science.aaf7894

    View details for PubMedID 27540167

  • Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping Xie, M., Jean, N., Burke, M., Lobell, D., Ermon, S., AAAI ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2016: 3929–35