POEM: Pattern-Oriented Explanations of Convolutional Neural Networks
Summary: POEM: modular framework extracting semantic-concept patterns (shapes, colors) to explain CNN image classifiers. Yields interpretable rules like "if sofa then living room" linking concept presence + model attention to labels, with quantitative and qualitative advantages over prior explainers. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Vargha Dadvar (University of Waterloo)
- 2. Lukasz Golab (University of Waterloo)
- 3. Divesh Srivastava (AT&T)
BibTeX Citation
@article{dadvar_vldb23,
title = {{POEM: Pattern-Oriented Explanations of Convolutional Neural Networks}},
author = {Dadvar, Vargha and Golab, Lukasz and Srivastava, Divesh},
journal = {PVLDB},
series = {{VLDB} '23},
volume = {16},
number = {11},
pages = {3192--3200},
doi = {10.14778/3611479.3611518},
url = {https://doi.org/10.14778/3611479.3611518},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 11,327 | Demonstration of VCR: A Tabular Data Slicing Approach to Understanding Object Detection Model Performance | 2024 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 2,987 | Incremental and Approximate Inference for Faster Occlusion-based Deep CNN Explanations | 2019 | SIGMOD | 7.8907997e-05 |
| 5,054 | Explainable AI: Foundations, Applications, Opportunities for Data Management Research | 2022 | SIGMOD | 6.3843089e-05 |
| 13,424 | POEM: Pattern-Oriented Explanations of CNN Models | 2022 | VLDB | - |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 3,253 | Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics | 2021 | VLDB |
| 2 | 11,680 | Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural Networks | 2021 | SIGMOD |
| 3 | 2,702 | Panorama: A Data System for Unbounded Vocabulary Querying over Video | 2020 | VLDB |
| 4 | 3,573 | VISTA: Optimized System for Declarative Feature Transfer from Deep CNNs at Scale | 2020 | SIGMOD |
| 5 | 13,514 | Demonstration of Krypton: Optimized CNN Inference for Occlusion-based Deep CNN Explanations | 2019 | VLDB |
| 6 | 9,479 | dCAM: Dimension-wise Class Activation Map for Explaining Multivariate Data Series Classification | 2022 | SIGMOD |
| 7 | 9,922 | View-based Explanations for Graph Neural Networks | 2024 | SIGMOD |
| 8 | 11,376 | Unsupervised Hashing with Semantic Concept Mining | 2023 | SIGMOD |
| 9 | 2,987 | Incremental and Approximate Inference for Faster Occlusion-based Deep CNN Explanations | 2019 | SIGMOD |
| 10 | 13,424 | POEM: Pattern-Oriented Explanations of CNN Models | 2022 | VLDB |