Improving The Reconstruction Quality by Overfitted Decoder Bias in Neural Image Compression
Not on the map. Why?
Abstract (arXiv)
End-to-end trainable models have reached the performance of traditional handcrafted compression techniques on videos and images. Since the parameters of these models are learned over large training sets, they are not optimal for any given image to be compressed. In this paper, we propose an instance-based fine-tuning of a subset of decoder's bias to improve the reconstruction quality in exchange for extra encoding time and minor additional signaling cost. The proposed method is applicable to any end-to-end compression methods, improving the state-of-the-art neural image compression BD-rate by 3-5%.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 17 of its 24 references that are in the map. First posted on arXiv 10 Oct 2022.
Builds on
17 of 24 references.
References · 17
- 2013Auto-Encoding Variational Bayescited by 3,980
- 2018Variational image compression with a scale hyperpriorcited by 910
- 2016End-to-end Optimized Image Compressioncited by 673
- 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
- 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
- 2017Lossy Image Compression with Compressive Autoencoderscited by 289
- 2020CompressAI: a PyTorch library and evaluation platform for end-to-end compression researchcited by 271
- 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 255
- 2018Inference Suboptimality in Variational Autoencoderscited by 131
- 2021Enhanced Invertible Encoding for Learned Image Compressioncited by 102
- 2019Video Compression With Rate-Distortion Autoencoderscited by 97
- 2020Improving Inference for Neural Image Compressioncited by 81
5 more
- 2020Content Adaptive and Error Propagation Aware Deep Video Compressioncited by 72
- 2019Content Adaptive Optimization for Neural Image Compressioncited by 40
- 2021Overfitting for Fun and Profit: Instance-Adaptive Data Compressioncited by 38
- 2021Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Setcited by 18
- 2018Block-optimized Variable Bit Rate Neural Image Compressioncited by 7
Built on by
Citing papers per year: 2024: 2.
2 papers.