# Channel-wise Feature Decorrelation for Enhanced Learned Image Compression

arXiv: https://arxiv.org/abs/2403.10936 · HTML: https://mlsanity.com/paper/2403.10936/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 16 Mar 2024.

## Builds on (most cited first, 22 of 22)

- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [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)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [Learned Image Compression with Mixed Transformer-CNN Architectures](https://mlsanity.com/paper/2303.14978/) (2023)
- [Checkerboard Context Model for Efficient Learned Image Compression](https://mlsanity.com/paper/2103.15306/) (2021)
- [Lossy Image Compression with Conditional Diffusion Models](https://mlsanity.com/paper/2209.06950/) (2022)
- [Neural Video Compression with Diverse Contexts](https://mlsanity.com/paper/2302.14402/) (2023)
- [Practical Full Resolution Learned Lossless Image Compression](https://mlsanity.com/paper/1811.12817/) (2018)
- [HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation](https://mlsanity.com/paper/2306.09818/) (2023)
- [ELF-VC: Efficient Learned Flexible-Rate Video Coding](https://mlsanity.com/paper/2104.14335/) (2021)
- [Image coding for machines: an end-to-end learned approach](https://mlsanity.com/paper/2108.09993/) (2021)
- [Variable Rate Deep Image Compression with Modulated Autoencoder](https://mlsanity.com/paper/1912.05526/) (2019)
- [Self-Organized Variational Autoencoders (Self-VAE) for Learned Image Compression](https://mlsanity.com/paper/2105.12107/) (2021)
- [Reducing Redundancy in the Bottleneck Representation of the Autoencoders](https://mlsanity.com/paper/2202.04629/) (2022)
- [Multistage Spatial Context Models for Learned Image Compression](https://mlsanity.com/paper/2302.09263/) (2023)
- [Learning distinct features helps, provably](https://mlsanity.com/paper/2106.06012/) (2021)
- [Comprehensive Complexity Assessment of Emerging Learned Image Compression on CPU and GPU](https://mlsanity.com/paper/2212.05466/) (2022)
- [WLD-Reg: A Data-dependent Within-layer Diversity Regularizer](https://mlsanity.com/paper/2301.01352/) (2023)

## Built on by (most cited first, 2 of 2)

- [ChWDTA: Channel-wise Wavelet-Domain Transformer Attention and Entropy Modeling for Learned Image Compression](https://mlsanity.com/paper/2606.00111/) (2026)
- [You've Seen Enough: Quality-Constrained Image Coding for Machines](https://mlsanity.com/paper/2609.25108/) (2026)

## Abstract (arXiv)

The emerging Learned Compression (LC) replaces the traditional codec modules with Deep Neural Networks (DNN), which are trained end-to-end for rate-distortion performance. This approach is considered as the future of image/video compression, and major efforts have been dedicated to improving its compression efficiency. However, most proposed works target compression efficiency by employing more complex DNNS, which contributes to higher computational complexity. Alternatively, this paper proposes to improve compression by fully exploiting the existing DNN capacity. To do so, the latent features are guided to learn a richer and more diverse set of features, which corresponds to better reconstruction. A channel-wise feature decorrelation loss is designed and is integrated into the LC optimization. Three strategies are proposed and evaluated, which optimize (1) the transformation network, (2) the context model, and (3) both networks. Experimental results on two established LC methods show that the proposed method improves the compression with a BD-Rate of up to 8.06%, with no added complexity. The proposed solution can be applied as a plug-and-play solution to optimize any similar LC method.