paper-with-me

홈 › Papers

Robustness to distribution shifts of compressed networks for edge devices

2024-01-22 · Lulan Shen, Ali Edalati, Brett Meyer, Warren Gross, James J. Clark

It is necessary to develop efficient DNNs deployed on edge devices with limited computation resources. However, the compressed networks often execute new tasks in the target domain, which is different from the source domain where the original network is trained. It is important to investigate the robustness of compressed networks in two types of data distribution shifts: domain shifts and adversarial perturbations. In this study, we discover that compressed models are less robust to distribution shifts than their original networks. Interestingly, larger networks are more vulnerable to losing robustness than smaller ones, even when they are compressed to a similar size as the smaller networks. Furthermore, compact networks obtained by knowledge distillation are much more robust to distribution shifts than pruned networks. Finally, post-training quantization is a reliable method for achieving significant robustness to distribution shifts, and it outperforms both pruned and distilled models in terms of robustness.

📄 PDF Abstract BibTeX arXiv:2401.12014

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationQuantization

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Distributed Monitoring for Data Distribution Shifts in Edge-ML Fraud Detection

2024-01-10 · Nader Karayanni, Robert J. Shahla, Chieh-Lien Hsiao

The digital era has seen a marked increase in financial fraud. edge ML emerged as a promising solution for smartphone payment services fraud detection, enabling the deployment of ML models directly on edge devices. This …

Fraud Detection

Attacking Compressed Vision Transformers

2022-09-28 · Swapnil Parekh, Devansh Shah, Pratyush Shukla

Vision Transformers are increasingly embedded in industrial systems due to their superior performance, but their memory and power requirements make deploying them to edge devices a challenging task. Hence, model compress…

Model Compression

Edge Radar Material Classification Under Geometry Shifts

2026-03-24 · Jannik Hohmann, Dong Wang, Andreas Nüchter arxiv

Material awareness can improve robotic navigation and interaction, particularly in conditions where cameras and LiDAR degrade. We present a lightweight mmWave radar material classification pipeline designed for ultra-low…

Non-adversarial Robustness of Deep Learning Methods for Computer Vision

2023-05-24 · Gorana Gojić, Vladimir Vincan, Ognjen Kundačina, Dragiša Mišković 외

Non-adversarial robustness, also known as natural robustness, is a property of deep learning models that enables them to maintain performance even when faced with distribution shifts caused by natural variations in data.…

Adversarial RobustnessDeep LearningNon-Adversarial Robustness

KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation

2021-09-13 · Marzieh S. Tahaei, Ella Charlaix, Vahid Partovi Nia, Ali Ghodsi 외

The development of over-parameterized pre-trained language models has made a significant contribution toward the success of natural language processing. While over-parameterization of these models is the key to their gen…

Knowledge DistillationLanguage ModelingLanguage ModellingModel Compression