7 citations · 42 across the 10 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023★ 7 cited
Improving Visual Prompt Tuning for Self-supervised Vision Transformers
Seungryong Yoo, Eunji Kim, Dahuin Jung +2
Visual Prompt Tuning (VPT) is an effective tuning method for adapting pretrained Vision Transformers (ViTs) to downstream tasks. It leverages extra learnable tokens, known as promp…
cs.LG2023★ 6 cited
Probabilistic Concept Bottleneck Models
Eunji Kim, Dahuin Jung, Sangha Park +2
Interpretable models are designed to make decisions in a human-interpretable manner. Representatively, Concept Bottleneck Models (CBM) follow a two-step process of concept predicti…