Learned Image Transmission with Hierarchical Variational Autoencoder
Authors: Guangyi Zhang, Hanlei Li, Yunlong Cai, Qiyu Hu, Guanding Yu, Runmin Zhang
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on images of varying resolutions demonstrate that our proposed model outperforms existing baselines in rate-distortion performance and maintains robustness against channel noise. |
| Researcher Affiliation | Academia | College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China EMAIL |
| Pseudocode | No | The paper describes methods using text and diagrams (Figure 3, Figure 4, Figure 5) but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | 1Codes are given in https://github.com/zhang-guangyi/HJSCC. |
| Open Datasets | Yes | Kodak (Kodak 1993): The dataset consists of 24 images of resolution 512 768 or 768 512. CLIC2022 Test (Toderici et al. 2022): The test set contains 30 images up to size 1365 2048. Kodak. 1993. Kodak Photo CD dataset. http://r0k.us/ graphics/kodak/. |
| Dataset Splits | No | The paper mentions 'Kodak' and 'CLIC2022 Test' datasets but does not provide specific training/test/validation splits (e.g., percentages or sample counts) used in their experiments. It only states 'The dataset consists of 24 images' for Kodak and 'The test set contains 30 images' for CLIC2022 Test. |
| Hardware Specification | No | The paper does not explicitly provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers like Python 3.8, PyTorch 1.9) needed to replicate the experiment. |
| Experiment Setup | No | The paper mentions some experimental settings like 16-order quadrature amplitude modulation (16QAM), an LDPC rate of 2/3, a test SNR of 10 dB, and a CBR of 0.0625. It also states 'For Deep JSCC and NTSCC, the training SNR equals the testing SNR to achieve optimal performance' and 'All the models are optimized on Image Net dataset.' However, it does not provide specific deep learning hyperparameters such as learning rate, batch size, number of epochs, or optimizer details for their proposed HJSCC model. |