# Pruning for Feature-Preserving Circuits in CNNs

arXiv: https://arxiv.org/abs/2206.01627 · HTML: https://mlsanity.com/paper/2206.01627/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 72 references that are in the map.
- First posted on arXiv 3 Jun 2022.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [Picking Winning Tickets Before Training by Preserving Gradient Flow](https://mlsanity.com/paper/2002.07376/) (2020)
- [Neural Module Networks](https://mlsanity.com/paper/1511.02799/) (2015)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks](https://mlsanity.com/paper/1808.06866/) (2018)
- [Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts](https://mlsanity.com/paper/1406.2031/) (2014)
- [How Well Do Self-Supervised Models Transfer?](https://mlsanity.com/paper/2011.13377/) (2020)
- [Compositional Explanations of Neurons](https://mlsanity.com/paper/2006.14032/) (2020)
- [Conditional Computation in Neural Networks for faster models](https://mlsanity.com/paper/1511.06297/) (2015)
- [Towards Optimal Structured CNN Pruning via Generative Adversarial Learning](https://mlsanity.com/paper/1903.09291/) (2019)
- [Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks](https://mlsanity.com/paper/1801.03454/) (2018)
- [Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning](https://mlsanity.com/paper/1711.01239/) (2017)
- [Grounding of Textual Phrases in Images by Reconstruction](https://mlsanity.com/paper/1511.03745/) (2015)
- [Interpreting Deep Visual Representations via Network Dissection](https://mlsanity.com/paper/1711.05611/) (2017)
- [Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks](https://mlsanity.com/paper/2010.02066/) (2020)
- [AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference](https://mlsanity.com/paper/1805.08941/) (2018)
- [Progressive Skeletonization: Trimming more fat from a network at initialization](https://mlsanity.com/paper/2006.09081/) (2020)
- [Modular Networks: Learning to Decompose Neural Computation](https://mlsanity.com/paper/1811.05249/) (2018)
- [Explainable Neural Computation via Stack Neural Module Networks](https://mlsanity.com/paper/1807.08556/) (2018)
- [Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression](https://mlsanity.com/paper/1812.04368/) (2018)

## Built on by (most cited first, 4 of 4)

- [Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient](https://mlsanity.com/paper/2410.02984/) (2024)
- [Certified Circuits: Stability Guarantees for Mechanistic Circuits](https://mlsanity.com/paper/2602.22968/) (2026)
- [Engineering Resource-constrained Software Systems with DNN Components: a Concept-based Pruning Approach](https://mlsanity.com/paper/2604.09988/) (2026)
- [From Interpretability Methods to Interpretable Models](https://mlsanity.com/paper/2609.05399/) (2026)

## Abstract (arXiv)

Deep convolutional neural networks are a powerful model class for a range of computer vision problems, but it is difficult to interpret the image filtering process they implement, given their sheer size. In this work, we introduce a method for extracting 'feature-preserving circuits' from deep CNNs, leveraging methods from saliency-based neural network pruning. These circuits are modular sub-functions, embedded within the network, containing only a subset of convolutional kernels relevant to a target feature. We compare the efficacy of 3 saliency-criteria for extracting these sparse circuits. Further, we show how 'sub-feature' circuits can be extracted, that preserve a feature's responses to particular images, dividing the feature into even sparser filtering processes. We also develop a tool for visualizing 'circuit diagrams', which render the entire image filtering process implemented by circuits in a parsable format.