Table 2 Results of ablation experiments by sequentially stacking different modules.
From: Deep Learning Image Compression Method Based On Efficient Channel-Time Attention Module
Experiment | Baseline | ETAM | Residual Module | Entropy Coding | PSNR/dB | MS-SSIM | LPIPS |
|---|---|---|---|---|---|---|---|
Experiment I | √ | 27.0 | 0.78 | 0.52 | |||
Experiment II | √ | 28.5 | 0.81 | 0.42 | |||
Experiment III | √ | √ | 29.2 | 0.83 | 0.37 | ||
Experiment IV | √ | √ | √ | 31.5 | 0.85 | 0.26 |
