Elena Alshina — accepted AI-conference papers

2024

Quantized Decoder in Learned Image Compression for Deterministic Reconstruction

Esin Koyuncu, Timofey Solovyev, Johannes Sauer, Elena Alshina, André Kaup

ICASSP 2024accepted

Learned image compression has a problem of non-bit-exact reconstruction due to different calculations of floating point arithmetic on different devices. This paper shows a method to achieve a deterministic reconstructed image by quantizing only the decoder of the learned image compression model. Fro…

Cited by 0 Source ↗Scholar ↗

2022

Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression

A. Burakhan Koyuncu, Han Gao, Atanas Boev, Georgii Gaikov, Elena Alshina, Eckehard Steinbach

ECCV 2022poster

"Entropy modeling is a key component for high-performance image compression algorithms. Recent developments in autoregressive context modeling helped learning-based methods to surpass their classical counterparts. However, the performance of those models can be further improved due to the underexplo…

Cited by 88 Source ↗PDF ↗Scholar ↗