Our model outperforms non-ROI methods in ROI compression, thus contributing to higher object detection and instance segmentation performance. The binary ROI mask is integrated into different layers of the network to provide spatial information guidance. A ROI-based deep image compression model with Swin transformers is proposed in Chapter 7. Region-of-interest (ROI) coding methods encode the foreground with better quality than the background. At last, we design learned image compression models and test the reconstructed images with the downstream computer vision tasks.
Our model gets higher or comparable performance compared with other variable-rate learned image compression models. The residual coding is adopted as an enhancement layer to obtain results across a range of bit rates with a single trained model.
Deep image compression models are trained separately for each bit rate which is quite time-consuming. A base layer that incorporates vision transformers for variable-rate image compression is presented in Chapter 6. Since the gradient of quantization is zero almost everywhere and the discrete probability distribution is non-differentiable, a soft approximation is applied to backpropagate gradients through the quantizer during training. In Chapter 5, we embed the Trellis Coded Quantizer (TCQ) into a deep learning-based image compression framework. Experiments show that our model outperforms other methods with low complexity. In Chapter 4, a stacked multi-context channel-wise attention network is built, where it adaptively integrates features from different scales along the channel dimension to remove JPEG compression artifacts. Traditional codecs such as JPEG usually have inevitable compression artifacts. The motivations of this thesis are to apply deep learning and computer vision to address these problems in various aspects. Traditional image compression generally relies on linear transform, and does not have knowledge of the content of the image.
0 kommentar(er)
