# A Disentangling Invertible Interpretation Network for Explaining Latent Representations

arXiv: https://arxiv.org/abs/2004.13166 · HTML: https://mlsanity.com/paper/2004.13166/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2020.

## Built on by (most cited first, 30 of 57)

- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Explaining in Style: Training a GAN to explain a classifier in StyleSpace](https://mlsanity.com/paper/2104.13369/) (2021)
- [ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis](https://mlsanity.com/paper/2108.08827/) (2021)
- [Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations](https://mlsanity.com/paper/2410.02762/) (2024)
- [Geometry-Free View Synthesis: Transformers and no 3D Priors](https://mlsanity.com/paper/2104.07652/) (2021)
- [A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts](https://mlsanity.com/paper/2105.07190/) (2021)
- [High Fidelity Visualization of What Your Self-Supervised Representation Knows About](https://mlsanity.com/paper/2112.09164/) (2021)
- [Shape or Texture: Understanding Discriminative Features in CNNs](https://mlsanity.com/paper/2101.11604/) (2021)
- [Stochastic Image-to-Video Synthesis using cINNs](https://mlsanity.com/paper/2105.04551/) (2021)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [Rosetta Neurons: Mining the Common Units in a Model Zoo](https://mlsanity.com/paper/2306.09346/) (2023)
- [iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis](https://mlsanity.com/paper/2107.02790/) (2021)
- [Generative Semantic Segmentation](https://mlsanity.com/paper/2303.11316/) (2023)
- [On the Challenges and Opportunities in Generative AI](https://mlsanity.com/paper/2403.00025/) (2024)
- [Position, Padding and Predictions: A Deeper Look at Position Information in CNNs](https://mlsanity.com/paper/2101.12322/) (2021)
- [A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information](https://mlsanity.com/paper/2206.02846/) (2022)
- [Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2205.11083/) (2022)
- [Texture Learning Domain Randomization for Domain Generalized Segmentation](https://mlsanity.com/paper/2303.11546/) (2023)
- [Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learning](https://mlsanity.com/paper/2309.07742/) (2023)
- [Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning](https://mlsanity.com/paper/2203.07677/) (2022)
- [Concept Embedding Analysis: A Review](https://mlsanity.com/paper/2203.13909/) (2022)
- [Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?](https://mlsanity.com/paper/2409.13456/) (2024)
- [XAI Handbook: Towards a Unified Framework for Explainable AI](https://mlsanity.com/paper/2105.06677/) (2021)
- [A Review of Change of Variable Formulas for Generative Modeling](https://mlsanity.com/paper/2308.02652/) (2023)
- [Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models](https://mlsanity.com/paper/2110.02891/) (2021)
- [Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability](https://mlsanity.com/paper/2304.14864/) (2023)
- [Formation of Representations in Neural Networks](https://mlsanity.com/paper/2410.03006/) (2024)
- [Verification of Size Invariance in DNN Activations using Concept Embeddings](https://mlsanity.com/paper/2105.06727/) (2021)
- [Review of Disentanglement Approaches for Medical Applications -- Towards Solving the Gordian Knot of Generative Models in Healthcare](https://mlsanity.com/paper/2203.11132/) (2022)

## Abstract (arXiv)

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations are lacking interpretability: Since distributed coding is optimal for latent layers to improve their robustness, attributing meaning to parts of a hidden feature vector or to individual neurons is hindered. We formulate interpretation as a translation of hidden representations onto semantic concepts that are comprehensible to the user. The mapping between both domains has to be bijective so that semantic modifications in the target domain correctly alter the original representation. The proposed invertible interpretation network can be transparently applied on top of existing architectures with no need to modify or retrain them. Consequently, we translate an original representation to an equivalent yet interpretable one and backwards without affecting the expressiveness and performance of the original. The invertible interpretation network disentangles the hidden representation into separate, semantically meaningful concepts. Moreover, we present an efficient approach to define semantic concepts by only sketching two images and also an unsupervised strategy. Experimental evaluation demonstrates the wide applicability to interpretation of existing classification and image generation networks as well as to semantically guided image manipulation.