Compression with Bayesian Implicit Neural Representations

Authors: Zongyu Guo, Gergely Flamich, Jiajun He, Zhibo Chen, José Miguel Hernández-Lobato

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments show that our method achieves strong performance on image and audio compression while retaining simplicity.
Researcher Affiliation Academia Zongyu Guo University of Science and Technology of China guozy@mail.ustc.edu.cn Gergely Flamich University of Cambridge gf332@cam.ac.uk Jiajun He University of Cambridge jh2383@cam.ac.uk Zhibo Chen University of Science and Technology of China chenzhibo@ustc.edu.cn Jos e Miguel Hern andez-Lobato University of Cambridge jmh233@cam.ac.uk
Pseudocode Yes Algorithm 1 Learning the model prior
Open Source Code Yes Our code is available at https://github.com/cambridge-mlg/combiner.
Open Datasets Yes We evaluate COMBINER on the CIFAR-10 [24] and Kodak [25] image datasets and the Libri Speech audio dataset [26]
Dataset Splits No The paper describes using a training set to learn the model prior and a test set for evaluation, but does not explicitly define a separate validation split for hyperparameter tuning.
Hardware Specification Yes encode 500 CIFAR-10 images in parallel with a single A100 GPU
Software Dependencies No The paper mentions using the 'ffmpeg package' but does not specify versions for core software dependencies like PyTorch or Python.
Experiment Setup Yes We use a 4-layer MLP with 16 hidden units and 32 Fourier embeddings for the CIFAR-10 dataset. The model prior is trained with 128 epochs... We use the Adam optimizer with learning rate 0.0002. The posterior variances are initialized as 9 ˆ 10 6. ...After obtaining the model prior, given a specific test CIFAR-10 image to be compressed, the posterior of this image is optimized for 25000 iterations, with the same optimizer.