-
[pdf]
[supp]
[bibtex]@InProceedings{Jeon_2024_WACV, author = {Jeon, Ji-Ye and Nguyen, Xuan Truong and Ryu, Soojung and Lee, Hyuk-Jae}, title = {USDN: A Unified Sample-Wise Dynamic Network With Mixed-Precision and Early-Exit}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {646-654} }
USDN: A Unified Sample-Wise Dynamic Network With Mixed-Precision and Early-Exit
Abstract
To reduce computation in deep neural network inference, a promising approach is to design a network with multiple internal classifiers (ICs) and adaptively select an execution path based on the complexity of a given input. However, quantizing an input-adaptive network, a must-do task for network deployment on edge devices, is a non-trivial task due to jointly allocating its computation budget along with network layers and IC locations. In this paper, we propose Unified Sample-wise Dynamic Network (USDN) with a mixed-precision and early-exit framework that obtains both the optimal location of ICs and layer-wise bit configurations under a given computation budget. The proposed USDN comprises multiple groups of layers, with each group representing a varying degree of complexity for input samples. Experimental results demonstrate that our approach reduces computational cost of the previous work by 12.78% while achieving higher accuracy on ImageNet dataset.
Related Material