279 citations · 952 across the 35 of their papers we have counts for
4 papers · 1 filter
Token Pooling in Vision Transformers
Dmitrii Marin, Jen-Hao Rick Chang, Anurag Ranjan +3
Despite the recent success in many applications, the high computational requirements of vision transformers limit their use in resource-constrained settings. While many existing me…
LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time
Elvis Nunez, Maxwell Horton, Anish Prabhu +3
When deploying deep learning models to a device, it is traditionally assumed that available computational resources (compute, memory, and power) remain static. However, real-world…
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Sachin Mehta, Mohammad Rastegari
Light-weight convolutional neural networks (CNNs) are the de-facto for mobile vision tasks. Their spatial inductive biases allow them to learn representations with fewer parameters…
DKM: Differentiable K-Means Clustering Layer for Neural Network Compression
Minsik Cho, Keivan A. Vahid, Saurabh Adya +1
Deep neural network (DNN) model compression for efficient on-device inference is becoming increasingly important to reduce memory requirements and keep user data on-device. To this…