27 citations · 46 across the 17 of their papers we have counts for
4 papers · 1 filter
Learning from Limited and Imperfect Data
Harsh Rangwani
The datasets used for Deep Neural Network training (e.g., ImageNet, MSCOCO, etc.) are often manually balanced across categories (classes) to facilitate learning of all the categori…
Composing Parts for Expressive Object Generation
Harsh Rangwani, Aishwarya Agarwal, Kuldeep Kulkarni +2
Image composition and generation are processes where the artists need control over various parts of the generated images. However, the current state-of-the-art generation models, l…
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…
Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives
Shrinivas Ramasubramanian, Harsh Rangwani, Sho Takemori +3
The rise in internet usage has led to the generation of massive amounts of data, resulting in the adoption of various supervised and semi-supervised machine learning algorithms, wh…