Research map / Label-efficient and robust learning / Recognition and long-tail
A Disentangling Invertible Interpretation Network for Explaining Latent Representations
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Translate autoencoder latents into normally distributed interpretable factors for sampling | Autoencoder-based image generation · The evaluated datasets | FID | Helped |
| Sample from the interpreted factor space rather than the autoencoder latent space | Autoencoder-based image synthesis · CelebA, Cifar10, FashionMNIST | image coherence | Helped |
| Vary the color factor while holding other factors fixed | ColorMNIST digit classifier · ColorMNIST | classifier prediction | No clear effect |
| Vary the digit factor while holding other factors fixed | ColorMNIST digit classifier · ColorMNIST | classifier prediction | Mixed |
| Vary the grayscale factor while holding other factors fixed | ResNet-50 classifier · AnimalFaces | classifier prediction | No clear effect |
| Vary the roundness factor while holding other factors fixed | ResNet-50 classifier · AnimalFaces | classifier prediction | Mixed |
| Walk linearly in the interpreted space and map back to the autoencoder latent space | Autoencoder representations · CelebA | decoded interpolation quality | Helped |
Closest papers by meaning
- Restyling Unsupervised Concept Based Interpretable Networks with Generative Models (ICLR 2025 · similarity 0.89)
- PICNN: A Pathway towards Interpretable Convolutional Neural Networks (AAAI 2024 · similarity 0.87)
- Enhancing Pre-trained Representation Classifiability can Boost its Interpretability (ICLR 2025 · similarity 0.86)
- Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models (CVPR 2025 · similarity 0.86)
- Q-SENN: Quantized Self-Explaining Neural Networks (AAAI 2024 · similarity 0.86)
- Towards flexible perception with visual memory (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.