# ProgDTD: Progressive Learned Image Compression with Double-Tail-Drop Training

arXiv: https://arxiv.org/abs/2305.02145 · HTML: https://mlsanity.com/paper/2305.02145/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 47 references that are in the map.
- First posted on arXiv 3 May 2023.

## Builds on (most cited first, 29 of 29)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [Generative Adversarial Networks for Extreme Learned Image Compression](https://mlsanity.com/paper/1804.02958/) (2018)
- [Full Resolution Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1608.05148/) (2016)
- [Variable Rate Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06085/) (2015)
- [Context-adaptive Entropy Model for End-to-end Optimized Image Compression](https://mlsanity.com/paper/1809.10452/) (2018)
- [Real-Time Adaptive Image Compression](https://mlsanity.com/paper/1705.05823/) (2017)
- [Density Modeling of Images using a Generalized Normalization Transformation](https://mlsanity.com/paper/1511.06281/) (2015)
- [Variable Rate Deep Image Compression With a Conditional Autoencoder](https://mlsanity.com/paper/1909.04802/) (2019)
- [Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks](https://mlsanity.com/paper/1703.10114/) (2017)
- [Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation](https://mlsanity.com/paper/2003.02012/) (2020)
- [Deep Generative Models for Distribution-Preserving Lossy Compression](https://mlsanity.com/paper/1805.11057/) (2018)
- [JALAD: Joint Accuracy- and Latency-Aware Deep Structure Decoupling for Edge-Cloud Execution](https://mlsanity.com/paper/1812.10027/) (2018)
- [Variable Rate Deep Image Compression with Modulated Autoencoder](https://mlsanity.com/paper/1912.05526/) (2019)
- [Slimmable Compressive Autoencoders for Practical Neural Image Compression](https://mlsanity.com/paper/2103.15726/) (2021)
- [Towards Conceptual Compression](https://mlsanity.com/paper/1604.08772/) (2016)
- [Edge-Host Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained Internet-of-Things Platforms](https://mlsanity.com/paper/1802.03835/) (2018)
- [DPICT: Deep Progressive Image Compression Using Trit-Planes](https://mlsanity.com/paper/2112.06334/) (2021)
- [FastDeepIoT: Towards Understanding and Optimizing Neural Network Execution Time on Mobile and Embedded Devices](https://mlsanity.com/paper/1809.06970/) (2018)
- [Stochastic Bottleneck: Rateless Auto-Encoder for Flexible Dimensionality Reduction](https://mlsanity.com/paper/2005.02870/) (2020)
- [Neural Multi-scale Image Compression](https://mlsanity.com/paper/1805.06386/) (2018)

## Built on by (most cited first, 13 of 13)

- [HydraViT: Stacking Heads for a Scalable ViT](https://mlsanity.com/paper/2409.17978/) (2024)
- [Process Mining for Unstructured Data: Challenges and Research Directions](https://mlsanity.com/paper/2401.13677/) (2023)
- [Remote Inference over Dynamic Links via Adaptive Rate Deep Task-Oriented Vector Quantization](https://mlsanity.com/paper/2501.02521/) (2025)
- [ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization](https://mlsanity.com/paper/2603.02897/) (2026)
- [Deep Learning-Based Image Compression for Wireless Communications: Impacts on Reliability,Throughput, and Latency](https://mlsanity.com/paper/2411.10650/) (2024)
- [Learned Compression of Point Cloud Geometry and Attributes in a Single Model through Multimodal Rate-Control](https://mlsanity.com/paper/2408.00599/) (2024)
- [LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices & Networks](https://mlsanity.com/paper/2504.13736/) (2025)
- [Progressive Learned Image Compression for Machine Perception](https://mlsanity.com/paper/2512.20070/) (2025)
- [ProDAT: Progressive Density-Aware Tail-Drop for Point Cloud Coding](https://mlsanity.com/paper/2510.17068/) (2025)
- [PAT-VCM: Plug-and-Play Auxiliary Tokens for Video Coding for Machines](https://mlsanity.com/paper/2604.13294/) (2026)
- [Coarse-to-Fine: Progressive Image Compression for Semantically Hierarchical Classification](https://mlsanity.com/paper/2605.08266/) (2026)
- [Every Packet Counts: Dispersing Information for Loss-Resilient Learned Image Compression](https://mlsanity.com/paper/2608.11096/) (2026)
- [Tree-VQ: Progressive Image Compression from Pretrained Vector Quantizers](https://mlsanity.com/paper/2609.03641/) (2026)

## Abstract (arXiv)

Progressive compression allows images to start loading as low-resolution versions, becoming clearer as more data is received. This increases user experience when, for example, network connections are slow. Today, most approaches for image compression, both classical and learned ones, are designed to be non-progressive. This paper introduces ProgDTD, a training method that transforms learned, non-progressive image compression approaches into progressive ones. The design of ProgDTD is based on the observation that the information stored within the bottleneck of a compression model commonly varies in importance. To create a progressive compression model, ProgDTD modifies the training steps to enforce the model to store the data in the bottleneck sorted by priority. We achieve progressive compression by transmitting the data in order of its sorted index. ProgDTD is designed for CNN-based learned image compression models, does not need additional parameters, and has a customizable range of progressiveness. For evaluation, we apply ProgDTDto the hyperprior model, one of the most common structures in learned image compression. Our experimental results show that ProgDTD performs comparably to its non-progressive counterparts and other state-of-the-art progressive models in terms of MS-SSIM and accuracy.