Neural network compression techniques for out-of-distribution detection
One of the key challenges in deploying ML models on embedded systems are the numerous resource constraints, for instance, memory footprint, response time, and power consumption. Such real-time systems require resource-efficient models with low inference time while maintaining reasonable accuracy. In...
Saved in:
Main Author: | Bansal, Aditya |
---|---|
Other Authors: | Arvind Easwaran |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/159148 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Towards out-of-distribution detection for object detection networks
by: Kanodia, Ritwik
Published: (2022) -
Full-spectrum out-of-distribution detection
by: Yang, Jingkang, et al.
Published: (2023) -
Traffic sign detection system with efficient and low-bit neural network compression in computer vision
by: Thin Lat Han
Published: (2022) -
Evaluating & enhancing deep learning systems via out-of-distribution detection
by: Christopher, Berend David
Published: (2022) -
Evaluating variational autoencoder methods for out-of-distribution detection in autonomous vehicles
by: Dinh, Phuc Hung
Published: (2023)