most citedDeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets

1 citations · 1 across the 2 of their papers we have counts for

collaborators

2 papers

cs.CV2024

Text2Place: Affordance-aware Text Guided Human Placement

Rishubh Parihar, Harsh Gupta, Sachidanand VS +1

For a given scene, humans can easily reason for the locations and pose to place objects. Designing a computational model to reason about these affordances poses a significant chall…

cs.CV2024★ 1 cited

DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets

Harsh Rangwani, Pradipto Mondal, Mayank Mishra +2

Vision Transformer (ViT) has emerged as a prominent architecture for various computer vision tasks. In ViT, we divide the input image into patch tokens and process them through a s…