44 citations · 52 across the 5 of their papers we have counts for
5 papers
Prior-Enhanced Few-Shot Segmentation with Meta-Prototypes
Jian-Wei Zhang, Lei Lv, Yawei Luo +3
Few-shot segmentation~(FSS) performance has been extensively promoted by introducing episodic training and class-wise prototypes. However, the FSS problem remains challenging due t…
SHOT-VAE: Semi-supervised Deep Generative Models With Label-aware ELBO Approximations
Hao-Zhe Feng, Kezhi Kong, Minghao Chen +3
Semi-supervised variational autoencoders (VAEs) have obtained strong results, but have also encountered the challenge that good ELBO values do not always imply accurate inference r…
Multitask machine learning of collective variables for enhanced sampling of rare events
Lixin Sun, Jonathan Vandermause, Simon Batzner +4
Computing accurate reaction rates is a central challenge in computational chemistry and biology because of the high cost of free energy estimation with unbiased molecular dynamics.…
KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
Hao-Zhe Feng, Zhaoyang You, Minghao Chen +5
Conventional unsupervised multi-source domain adaptation (UMDA) methods assume all source domains can be accessed directly. This neglects the privacy-preserving policy, that is, al…
An Interactive Insight Identification and Annotation Framework for Power Grid Pixel Maps using DenseU-Hierarchical VAE
Tianye Zhang, Haozhe Feng, Zexian Chen +4
Insights in power grid pixel maps (PGPMs) refer to important facility operating states and unexpected changes in the power grid. Identifying insights helps analysts understand the…