Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.10016 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913430380740608 |
|---|---|
| author | Wang, Zhenyu Nirjon, Shahriar |
| author_facet | Wang, Zhenyu Nirjon, Shahriar |
| contents | Edge devices, with their widely varying capabilities, support a diverse range of edge AI models. This raises the question: how does an edge model differ from a high-accuracy (base) model for the same task? We introduce XDELTA, a novel explainable AI tool that explains differences between a high-accuracy base model and a computationally efficient but lower-accuracy edge model. To achieve this, we propose a learning-based approach to characterize the model difference, named the DELTA network, which complements the feature representation capability of the edge network in a compact form. To construct DELTA, we propose a sparsity optimization framework that extracts the essence of the base model to ensure compactness and sufficient feature representation capability of DELTA, and implement a negative correlation learning approach to ensure it complements the edge model. We conduct a comprehensive evaluation to test XDELTA's ability to explain model discrepancies, using over 1.2 million images and 24 models, and assessing real-world deployments with six participants. XDELTA excels in explaining differences between base and edge models (arbitrary pairs as well as compressed base models) through geometric and concept-level analysis, proving effective in real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10016 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Characterizing Disparity Between Edge Models and High-Accuracy Base Models for Vision Tasks Wang, Zhenyu Nirjon, Shahriar Computer Vision and Pattern Recognition Artificial Intelligence Edge devices, with their widely varying capabilities, support a diverse range of edge AI models. This raises the question: how does an edge model differ from a high-accuracy (base) model for the same task? We introduce XDELTA, a novel explainable AI tool that explains differences between a high-accuracy base model and a computationally efficient but lower-accuracy edge model. To achieve this, we propose a learning-based approach to characterize the model difference, named the DELTA network, which complements the feature representation capability of the edge network in a compact form. To construct DELTA, we propose a sparsity optimization framework that extracts the essence of the base model to ensure compactness and sufficient feature representation capability of DELTA, and implement a negative correlation learning approach to ensure it complements the edge model. We conduct a comprehensive evaluation to test XDELTA's ability to explain model discrepancies, using over 1.2 million images and 24 models, and assessing real-world deployments with six participants. XDELTA excels in explaining differences between base and edge models (arbitrary pairs as well as compressed base models) through geometric and concept-level analysis, proving effective in real-world applications. |
| title | Characterizing Disparity Between Edge Models and High-Accuracy Base Models for Vision Tasks |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.10016 |