25 citations · 51 across the 21 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023★ 4 cited
Classes are not Clusters: Improving Label-based Evaluation of Dimensionality Reduction
Hyeon Jeon, Yun-Hsin Kuo, Michaël Aupetit +2
A common way to evaluate the reliability of dimensionality reduction (DR) embeddings is to quantify how well labeled classes form compact, mutually separated clusters in the embedd…
cs.LG2023★ 1 cited
How Does Attention Work in Vision Transformers? A Visual Analytics Attempt
Yiran Li, Junpeng Wang, Xin Dai +5
Vision transformer (ViT) expands the success of transformer models from sequential data to images. The model decomposes an image into many smaller patches and arranges them into a…