Documents
Poster
Multi_Scale Information Can Do More: Attention Aggregation Mechanism for Image Compression
![](https://sigport.org/sites/default/files/styles/home/public/DCC_2023_3_0.jpg?itok=Df5ZzK3h)
- Citation Author(s):
- Submitted by:
- Bo Li
- Last updated:
- 15 February 2023 - 4:52am
- Document Type:
- Poster
- Document Year:
- 2023
- Event:
- Presenters:
- Bo Li
- Categories:
- Log in to post comments
The semantic information obtained from large-scale computation in image compression is not practical. To solve this problem, we propose an Attention Aggregation Mechanism (AAM) for learning-based image compression, which is able to aggregate attention map from multiple scales and facilitate information embedding. Based on AAM and Swin Transformer, we design a Multi-scale Self-Attention Image Compression (MSAIC) approach, which is using Multi-scale Swin Transformer blocks (MSTB) and convolutional layers stacks in the down-sampling encoder and up-sampling decoder to the best embed information. Meanwhile, we use the channel-wise autoregressive entropy model for the accurate and efficient entropy probability estimation. Extensive experiments show MSAIC is effective and attain the state-of-the-art (SOTA) compression performance, also outperform the SOTA method at the high bit rate.