ExPLoRe turns MoE dispatch weights into per-patch loss coefficients for multi-objective masked image modeling, reporting gains on ImageNet-1K and ADE20K transfer.
arXiv preprint arXiv:2210.10615 (2022)
2 Pith papers cite this work, alongside 14 external citations. Polarity classification is still indexing.
2
Pith papers citing it
14
external citations · external index
verdicts
UNVERDICTED 2representative citing papers
Frabjous applies deep learning to classify FRB morphologies into five classes at 55% accuracy by augmenting limited real data with simulations.
citing papers explorer
-
ExPLoRe: Expert Patch-Level Loss Routing for Multi-Objective Masked Image Modeling
ExPLoRe turns MoE dispatch weights into per-patch loss coefficients for multi-objective masked image modeling, reporting gains on ImageNet-1K and ADE20K transfer.
-
Frabjous: Deep Learning Fast Radio Burst Morphologies
Frabjous applies deep learning to classify FRB morphologies into five classes at 55% accuracy by augmenting limited real data with simulations.