POEM: Pattern-Oriented Explanations of CNN Models
Summary: POEM outputs pattern-oriented explanations for CNNs by mapping image features to semantic concepts (e.g., 'if bed then bedroom'). Its modular design enables governance, model auditing, and detection of training-data errors within ML pipelines. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Vargha Dadvar (University of Waterloo)
- 2. Lukasz Golab (University of Waterloo)
- 3. Divesh Srivastava (AT&T)
BibTeX Citation
@article{dadvar_vldb22,
title = {{POEM: Pattern-Oriented Explanations of CNN Models}},
author = {Dadvar, Vargha and Golab, Lukasz and Srivastava, Divesh},
journal = {PVLDB},
series = {{VLDB} '22},
volume = {15},
number = {12},
pages = {3618--3621},
doi = {10.14778/3554821.3554858},
url = {https://doi.org/10.14778/3554821.3554858},
year = {2022}
}
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 7,508 | POEM: Pattern-Oriented Explanations of Convolutional Neural Networks | 2023 | VLDB | 5.6029996e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 0 of 0 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,376 | Unsupervised Hashing with Semantic Concept Mining | 2023 | SIGMOD |
| 2 | 13,367 | Demonstrating TabEE: Tabular Embedding Explanations | 2024 | VLDB |
| 3 | 6,354 | On Data-Aware Global Explainability of Graph Neural Networks | 2023 | VLDB |
| 4 | 10,557 | Database Views as Explanations for Relational Deep Learning | 2026 | VLDB |
| 5 | 6,427 | DeepBase: Deep Inspection of Neural Networks | 2019 | SIGMOD |
| 6 | 9,479 | dCAM: Dimension-wise Class Activation Map for Explaining Multivariate Data Series Classification | 2022 | SIGMOD |
| 7 | 13,514 | Demonstration of Krypton: Optimized CNN Inference for Occlusion-based Deep CNN Explanations | 2019 | VLDB |
| 8 | 2,987 | Incremental and Approximate Inference for Faster Occlusion-based Deep CNN Explanations | 2019 | SIGMOD |
| 9 | 9,922 | View-based Explanations for Graph Neural Networks | 2024 | SIGMOD |
| 10 | 7,508 | POEM: Pattern-Oriented Explanations of Convolutional Neural Networks | 2023 | VLDB |