# Interpretable CNNs for Object Classification

arXiv: https://arxiv.org/abs/1901.02413 · HTML: https://mlsanity.com/paper/1901.02413/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jan 2019.

## Built on by (most cited first, 17 of 17)

- [Causal Reasoning Meets Visual Representation Learning: A Prospective Study](https://mlsanity.com/paper/2204.12037/) (2022)
- [CX-ToM: Counterfactual Explanations with Theory-of-Mind for Enhancing Human Trust in Image Recognition Models](https://mlsanity.com/paper/2109.01401/) (2021)
- [Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification](https://mlsanity.com/paper/2208.08741/) (2022)
- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends](https://mlsanity.com/paper/2402.15490/) (2024)
- [Don't Forget Too Much: Towards Machine Unlearning on Feature Level](https://mlsanity.com/paper/2406.10951/) (2024)
- [Explainable Artificial Intelligence (XAI): An Engineering Perspective](https://mlsanity.com/paper/2101.03613/) (2021)
- [Explainable Diabetic Retinopathy Detection and Retinal Image Generation](https://mlsanity.com/paper/2107.00296/) (2021)
- [COIN: Counterfactual Image Generation for VQA Interpretation](https://mlsanity.com/paper/2201.03342/) (2022)
- [Layerwise Change of Knowledge in Neural Networks](https://mlsanity.com/paper/2409.08712/) (2024)
- [Learning Interpretable Concept Groups in CNNs](https://mlsanity.com/paper/2109.10078/) (2021)
- [Activation Template Matching Loss for Explainable Face Recognition](https://mlsanity.com/paper/2207.02179/) (2022)
- [Stylistic Multi-Task Analysis of Ukiyo-e Woodblock Prints](https://mlsanity.com/paper/2410.12379/) (2024)
- [A Survey on Interpretability in Visual Recognition](https://mlsanity.com/paper/2507.11099/) (2025)
- [Schema Inference for Interpretable Image Classification](https://mlsanity.com/paper/2303.06635/) (2023)
- [Semantic interpretation for convolutional neural networks: What makes a cat a cat?](https://mlsanity.com/paper/2204.07724/) (2022)
- [A matter of attitude: Focusing on positive and active gradients to boost saliency maps](https://mlsanity.com/paper/2309.12913/) (2023)

## Abstract (arXiv)

This paper proposes a generic method to learn interpretable convolutional filters in a deep convolutional neural network (CNN) for object classification, where each interpretable filter encodes features of a specific object part. Our method does not require additional annotations of object parts or textures for supervision. Instead, we use the same training data as traditional CNNs. Our method automatically assigns each interpretable filter in a high conv-layer with an object part of a certain category during the learning process. Such explicit knowledge representations in conv-layers of CNN help people clarify the logic encoded in the CNN, i.e., answering what patterns the CNN extracts from an input image and uses for prediction. We have tested our method using different benchmark CNNs with various structures to demonstrate the broad applicability of our method. Experiments have shown that our interpretable filters are much more semantically meaningful than traditional filters.