28 citations · 37 across the 4 of their papers we have counts for
4 papers · 1 filter
Efficient Image Generation with Variadic Attention Heads
Steven Walton, Ali Hassani, Xingqian Xu +2
While the integration of transformers in vision models have yielded significant improvements on vision tasks they still require significant amounts of computation for both training…
Distilling Facial Knowledge With Teacher-Tasks: Semantic-Segmentation-Features For Pose-Invariant Face-Recognition
Ali Hassani, Zaid El Shair, Rafi Ud Duala Refat +1
This paper demonstrates a novel approach to improve face-recognition pose-invariance using semantic-segmentation features. The proposed Seg-Distilled-ID network jointly learns iden…
Dilated Neighborhood Attention Transformer
Ali Hassani, Humphrey Shi
Transformers are quickly becoming one of the most heavily applied deep learning architectures across modalities, domains, and tasks. In vision, on top of ongoing efforts into plain…
DiSparse: Disentangled Sparsification for Multitask Model Compression
Xinglong Sun, Ali Hassani, Zhangyang Wang +2
Despite the popularity of Model Compression and Multitask Learning, how to effectively compress a multitask model has been less thoroughly analyzed due to the challenging entanglem…