# Towards Conceptual Compression

arXiv: https://arxiv.org/abs/1604.08772 · HTML: https://mlsanity.com/paper/1604.08772/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2016.

## Built on by (most cited first, 30 of 36)

- [Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples](https://mlsanity.com/paper/2302.04578/) (2023)
- [An Introduction to Neural Data Compression](https://mlsanity.com/paper/2202.06533/) (2022)
- [Densely connected normalizing flows](https://mlsanity.com/paper/2106.04627/) (2021)
- [Slimmable Compressive Autoencoders for Practical Neural Image Compression](https://mlsanity.com/paper/2103.15726/) (2021)
- [Image Compression with Product Quantized Masked Image Modeling](https://mlsanity.com/paper/2212.07372/) (2022)
- [DPICT: Deep Progressive Image Compression Using Trit-Planes](https://mlsanity.com/paper/2112.06334/) (2021)
- [AI-Generated Content (AIGC) for Various Data Modalities: A Survey](https://mlsanity.com/paper/2308.14177/) (2023)
- [Context-Based Trit-Plane Coding for Progressive Image Compression](https://mlsanity.com/paper/2303.05715/) (2023)
- [Cauchy-Schwarz Regularized Autoencoder](https://mlsanity.com/paper/2101.02149/) (2021)
- [Learning-Driven Lossy Image Compression; A Comprehensive Survey](https://mlsanity.com/paper/2201.09240/) (2022)
- [ProgDTD: Progressive Learned Image Compression with Double-Tail-Drop Training](https://mlsanity.com/paper/2305.02145/) (2023)
- [Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility](https://mlsanity.com/paper/2207.04895/) (2022)
- [Thousand to One: Semantic Prior Modeling for Conceptual Coding](https://mlsanity.com/paper/2103.07131/) (2021)
- [Pragmatic Image Compression for Human-in-the-Loop Decision-Making](https://mlsanity.com/paper/2108.04219/) (2021)
- [Reducing Redundancy in the Bottleneck Representation of the Autoencoders](https://mlsanity.com/paper/2202.04629/) (2022)
- [Entropy-Informed Weighting Channel Normalizing Flow for Deep Generative Models](https://mlsanity.com/paper/2407.04958/) (2024)
- [Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding](https://mlsanity.com/paper/2402.08919/) (2024)
- [A Non-negative VAE:the Generalized Gamma Belief Network](https://mlsanity.com/paper/2408.03388/) (2024)
- [Efficient Progressive Image Compression with Variance-aware Masking](https://mlsanity.com/paper/2411.10185/) (2024)
- [What Is Considered Complete for Visual Recognition?](https://mlsanity.com/paper/2105.13978/) (2021)
- [ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE](https://mlsanity.com/paper/2107.09286/) (2021)
- [STR-GQN: Scene Representation and Rendering for Unknown Cameras Based on Spatial Transformation Routing](https://mlsanity.com/paper/2108.03072/) (2021)
- [An Empirical Analysis of Recurrent Learning Algorithms In Neural Lossy Image Compression Systems](https://mlsanity.com/paper/2201.11782/) (2022)
- [RD-Optimized Trit-Plane Coding of Deep Compressed Image Latent Tensors](https://mlsanity.com/paper/2203.13467/) (2022)
- [Diffusion Probabilistic Multi-cue Level Set for Reducing Edge Uncertainty in Pancreas Segmentation](https://mlsanity.com/paper/2404.07620/) (2024)
- [NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation](https://mlsanity.com/paper/2106.13435/) (2021)
- [Latent Discretization for Continuous-time Sequence Compression](https://mlsanity.com/paper/2212.13659/) (2022)
- [Compression of GPS Trajectories using Autoencoders](https://mlsanity.com/paper/2301.07420/) (2023)
- [LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices & Networks](https://mlsanity.com/paper/2504.13736/) (2025)
- [Neural JPEG: End-to-End Image Compression Leveraging a Standard JPEG Encoder-Decoder](https://mlsanity.com/paper/2201.11795/) (2022)

## Abstract (arXiv)

We introduce a simple recurrent variational auto-encoder architecture that significantly improves image modeling. The system represents the state-of-the-art in latent variable models for both the ImageNet and Omniglot datasets. We show that it naturally separates global conceptual information from lower level details, thus addressing one of the fundamentally desired properties of unsupervised learning. Furthermore, the possibility of restricting ourselves to storing only global information about an image allows us to achieve high quality 'conceptual compression'.