Variable Rate Allocation for Vector-Quantized Autoencoders

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(2023)

引用 0|浏览12
Vector-quantized autoencoders have recently gained interest in image compression, generation and self-supervised learning. However, as a neural compression method, they lack the possibility to allocate a variable number of bits to each image location, e.g. according to the semantic content or local saliency. In this paper, we address this limitation in a simple yet effective way. We adopt a product quantizer (PQ) that produces a set of discrete codes for each image patch rather than a single index. This PQ-autoencoder is trained end-to-end with a structured dropout that selectively masks a variable number of codes at each location. These mechanisms force the decoder to reconstruct the original image based on partial information and allow us to control the local rate. The resulting model can compress images on a wide range of operating points of the rate-distortion curve and can be paired with any external method for saliency estimation to control the compression rate at a local level. We demonstrate the effectiveness of our approach on the popular Kodak and ImageNet datasets by measuring both distortion and perceptual quality metrics.
compression rate,discrete codes,image compression,image location,image patch,local rate,local saliency,neural compression method,PQ-autoencoder,product quantizer,rate-distortion curve,self-supervised learning,semantic content,simple yet effective way,variable rate allocation,vector-quantized autoencoders
AI 理解论文
Chat Paper