# Mid-level Deep Pattern Mining

arXiv: https://arxiv.org/abs/1411.6382 · HTML: https://mlsanity.com/paper/1411.6382/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2014.

## Built on by (most cited first, 3 of 3)

- [Prototype-based Dataset Comparison](https://mlsanity.com/paper/2309.02401/) (2023)
- [Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection](https://mlsanity.com/paper/2504.13938/) (2025)
- [Deciphering Personalization: Towards Fine-Grained Explainability in Natural Language for Personalized Image Generation Models](https://mlsanity.com/paper/2511.01932/) (2025)

## Abstract (arXiv)

Mid-level visual element discovery aims to find clusters of image patches that are both representative and discriminative. In this work, we study this problem from the prospective of pattern mining while relying on the recently popularized Convolutional Neural Networks (CNNs). Specifically, we find that for an image patch, activations extracted from the first fully-connected layer of CNNs have two appealing properties which enable its seamless integration with pattern mining. Patterns are then discovered from a large number of CNN activations of image patches through the well-known association rule mining. When we retrieve and visualize image patches with the same pattern, surprisingly, they are not only visually similar but also semantically consistent. We apply our approach to scene and object classification tasks, and demonstrate that our approach outperforms all previous works on mid-level visual element discovery by a sizeable margin with far fewer elements being used. Our approach also outperforms or matches recent works using CNN for these tasks. Source code of the complete system is available online.