InfoDisent: Explainability of Image Classification Models by Information Disentanglement
Reviewed by Pithpith:YSSI4YESopen to challenge →
read the original abstract
In this work, we introduce InfoDisent, a hybrid approach to explainability based on the information bottleneck principle. InfoDisent enables the disentanglement of information in the final layer of any pretrained model into atomic concepts, which can be interpreted as prototypical parts. This approach merges the flexibility of post-hoc methods with the concept-level modeling capabilities of self-explainable neural networks, such as ProtoPNets. We demonstrate the effectiveness of InfoDisent through computational experiments and user studies across various datasets using modern backbones such as ViTs and convolutional networks. Notably, InfoDisent generalizes the prototypical parts approach to novel domains (ImageNet).
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models
CEDAR learns an invertible rotation of vision-language embeddings to concentrate semantics into sparse, axis-aligned coordinates for improved interpretability.
-
ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
ProDG uses generative models to create data-free prototypes from model weights for post-hoc explainability of image predictions.
-
ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
ProDG generates high-fidelity prototypes from model weights alone for data-free post-hoc explainability in prototype-based networks.
-
APEX: Audio Prototype EXplanations for Classification Tasks
APEX generates four types of prototype-based explanations for pre-trained audio classifiers that preserve output invariance and target acoustic properties better than gradient methods applied to spectrograms.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.