# Learning Content-Weighted Deep Image Compression

arXiv: https://arxiv.org/abs/1904.00664 · HTML: https://mlsanity.com/paper/1904.00664/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2019.

## Built on by (most cited first, 28 of 28)

- [Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform](https://mlsanity.com/paper/2108.09551/) (2021)
- [Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules](https://mlsanity.com/paper/2107.06463/) (2021)
- [Image Coding for Machines with Omnipotent Feature Learning](https://mlsanity.com/paper/2207.01932/) (2022)
- [Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression](https://mlsanity.com/paper/2209.04847/) (2022)
- [Causal Context Adjustment Loss for Learned Image Compression](https://mlsanity.com/paper/2410.04847/) (2024)
- [Learning Scalable ℓ_∞-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression](https://mlsanity.com/paper/2103.17015/) (2021)
- [Neural Distributed Image Compression with Cross-Attention Feature Alignment](https://mlsanity.com/paper/2207.08489/) (2022)
- [Invertible Rescaling Network and Its Extensions](https://mlsanity.com/paper/2210.04188/) (2022)
- [Content Adaptive Latents and Decoder for Neural Image Compression](https://mlsanity.com/paper/2212.10132/) (2022)
- [Learning-Driven Lossy Image Compression; A Comprehensive Survey](https://mlsanity.com/paper/2201.09240/) (2022)
- [LC-FDNet: Learned Lossless Image Compression with Frequency Decomposition Network](https://mlsanity.com/paper/2112.06417/) (2021)
- [Semantically Structured Image Compression via Irregular Group-Based Decoupling](https://mlsanity.com/paper/2305.02586/) (2023)
- [Prompt-ICM: A Unified Framework towards Image Coding for Machines with Task-driven Prompts](https://mlsanity.com/paper/2305.02578/) (2023)
- [Pseudocylindrical Convolutions for Learned Omnidirectional Image Compression](https://mlsanity.com/paper/2112.13227/) (2021)
- [Learned Image Compression with Generalized Octave Convolution and Cross-Resolution Parameter Estimation](https://mlsanity.com/paper/2209.03353/) (2022)
- [Variable Bitrate Residual Vector Quantization for Audio Coding](https://mlsanity.com/paper/2410.06016/) (2024)
- [PILC: Practical Image Lossless Compression with an End-to-end GPU Oriented Neural Framework](https://mlsanity.com/paper/2206.05279/) (2022)
- [Transfer-based adaptive tree for multimodal sentiment analysis based on user latent aspects](https://mlsanity.com/paper/2106.14174/) (2021)
- [RFD-ECNet: Extreme Underwater Image Compression with Reference to Feature Dictionar](https://mlsanity.com/paper/2308.08721/) (2023)
- [Learned HDR Image Compression for Perceptually Optimal Storage and Display](https://mlsanity.com/paper/2407.13179/) (2024)
- [CANeRV: Content Adaptive Neural Representation for Video Compression](https://mlsanity.com/paper/2502.06181/) (2025)
- [RedBit: An End-to-End Flexible Framework for Evaluating the Accuracy of Quantized CNNs](https://mlsanity.com/paper/2301.06193/) (2023)
- [Deep Network for Image Compressed Sensing Coding Using Local Structural Sampling](https://mlsanity.com/paper/2402.19111/) (2024)
- [Exploiting Inter-Image Similarity Prior for Low-Bitrate Remote Sensing Image Compression](https://mlsanity.com/paper/2407.12295/) (2024)
- [Asymmetric Learned Image Compression with Multi-Scale Residual Block, Importance Map, and Post-Quantization Filtering](https://mlsanity.com/paper/2206.10618/) (2022)
- [Joint Hierarchical Priors and Adaptive Spatial Resolution for Efficient Neural Image Compression](https://mlsanity.com/paper/2307.02273/) (2023)
- [Region-Adaptive Generative Compression with Spatially Varying Diffusion Models](https://mlsanity.com/paper/2604.01122/) (2026)
- [Clear-Weighted Bit Allocation for Satellite Downlinks](https://mlsanity.com/paper/2608.01457/) (2026)

## Abstract (arXiv)

Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance. Most existing methods adopt spatially invariant bit length allocation and incorporate discrete entropy approximation to constrain compression rate. Nonetheless, the information content is spatially variant, where the regions with complex and salient structures generally are more essential to image compression. Taking the spatial variation of image content into account, this paper presents a content-weighted encoder-decoder model, which involves an importance map subnet to produce the importance mask for locally adaptive bit rate allocation. Consequently, the summation of importance mask can thus be utilized as an alternative of entropy estimation for compression rate control. Furthermore, the quantized representations of the learned code and importance map are still spatially dependent, which can be losslessly compressed using arithmetic coding. To compress the codes effectively and efficiently, we propose a trimmed convolutional network to predict the conditional probability of quantized codes. Experiments show that the proposed method can produce visually much better results, and performs favorably in comparison with deep and traditional lossy image compression approaches.