Estimating label quality and errors in semantic segmentation data via any model

The soft-minimum of the model-estimated likelihoods of each pixel’s annotated class – that is particularly effective to identify images that are mislabeled, across multiple types of annotation error

<span title='2023-07-11 00:00:00 +0000 UTC'>July 2023</span>&nbsp;&middot;&nbsp;Vedang Lad, Jonas Mueller

GRUNet: A Novel Bi-directional RNN for VQA

We propose a new framework which we call GRUNet. GRUNet is a novel Bi-Directional RNN architecture that combines GRU + RNN + ResNet to effectively combine text and im- age input to answer VQA questions.

<span title='2021-05-11 00:00:00 +0000 UTC'>May 2021</span>&nbsp;&middot;&nbsp;Vedang Lad, Lowell Hensgen