Minyoung Kim

Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach

2019 · arXiv (Cornell University)

In unsupervised domain adaptation, it is widely known that the target domain error can be provably reduced by having a shared input representation that makes the source and target domains indistinguishable from each other. Very …

Gaussian Process Modeling of Approximate Inference Errors for Variational Autoencoders

2022 · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Variational autoencoder (VAE) is a very successful generative model whose key element is the so-called amortized inference network, which can perform test time inference using a single feed forward pass. Unfortunately, this comes at the …

Model Diffusion for Certifiable Few-shot Transfer Learning

2025 · arXiv (Cornell University)

In contemporary deep learning, a prevalent and effective workflow for solving low-data problems is adapting powerful pre-trained foundation models (FMs) to new tasks via parameter-efficient fine-tuning (PEFT). However, while empirically effective, the resulting solutions lack …