Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression
This addresses the problem of efficient and high-performance variable-rate image compression for applications requiring flexible compression ratios, with incremental improvements in parameter and dataset efficiency.
The paper tackles variable-rate image compression by proposing a progressive learning paradigm with a Layer-adaptive Prompt Module, achieving the same performance as multiple-model methods with 80% savings in parameter storage and 90% savings in datasets, while outperforming current variable bitrate methods and approaching state-of-the-art fixed bitrate methods.
In this paper, we propose a progressive learning paradigm for transformer-based variable-rate image compression. Our approach covers a wide range of compression rates with the assistance of the Layer-adaptive Prompt Module (LPM). Inspired by visual prompt tuning, we use LPM to extract prompts for input images and hidden features at the encoder side and decoder side, respectively, which are fed as additional information into the Swin Transformer layer of a pre-trained transformer-based image compression model to affect the allocation of attention region and the bits, which in turn changes the target compression ratio of the model. To ensure the network is more lightweight, we involves the integration of prompt networks with less convolutional layers. Exhaustive experiments show that compared to methods based on multiple models, which are optimized separately for different target rates, the proposed method arrives at the same performance with 80% savings in parameter storage and 90% savings in datasets. Meanwhile, our model outperforms all current variable bitrate image methods in terms of rate-distortion performance and approaches the state-of-the-art fixed bitrate image compression methods trained from scratch.