Compression with Bayesian Implicit Neural Representations
Authors: Zongyu Guo, Gergely Flamich, Jiajun He, Zhibo Chen, José Miguel Hernández-Lobato
NeurIPS 2023 | Venue 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 EMAIL Gergely Flamich University of Cambridge EMAIL Jiajun He University of Cambridge EMAIL Zhibo Chen University of Science and Technology of China EMAIL Jos e Miguel Hern andez-Lobato University of Cambridge EMAIL |
| 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. |