QARV: Quantization-Aware ResNet VAE for Lossy Image Compression
This paper addresses the problem of lossy image compression, a fundamental problem in image processing and information theory that is involved in many real-world applications. We start by reviewing the framework of variational autoencoders (VAEs), a powerful class of generative probabilistic models that has a deep connection to lossy compression. Based on VAEs, we develop a novel scheme for lossy image compression, which we name quantization-aware ResNet VAE (QARV). Our method incorporates a hierarchical VAE architecture integrated with test-time quantization and quantization-aware training, without which efficient entropy coding would not be possible. In addition, we design the neural network architecture of QARV specifically for fast decoding and propose an adaptive normalization operation for variable-rate compression. Extensive experiments are conducted, and results show that QARV achieves variable-rate compression, high-speed decoding, and a better rate-distortion performance than existing baseline methods. The code of our method is publicly accessible at https://github.com/duanzhiihao/lossy-vae
Code (2)
Tasks
Image CompressionQuantizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Lossy Image Compression with Quantized Hierarchical VAEs
Recent research has shown a strong theoretical connection between variational autoencoders (VAEs) and the rate-distortion theory. Motivated by this, we consider the problem of lossy image compression from the perspective…
Image CompressionQuantizationAttention Round for Post-Training Quantization
At present, the quantification methods of neural network models are mainly divided into post-training quantization (PTQ) and quantization aware training (QAT). Post-training quantization only need a small part of the dat…
Combinatorial OptimizationQuantizationUniversal Deep Neural Network Compression
In this paper, we investigate lossy compression of deep neural networks (DNNs) by weight quantization and lossless source coding for memory-efficient deployment. Whereas the previous work addressed non-universal scalar q…
Neural Network CompressionQuantizationQuantization-aware Matrix Factorization for Low Bit Rate Image Compression
Lossy image compression is essential for efficient transmission and storage. Traditional compression methods mainly rely on discrete cosine transform (DCT) or singular value decomposition (SVD), both of which represent i…
Image CompressionQuantizationModeling Image Quantization Tradeoffs for Optimal Compression
All Lossy compression algorithms employ similar compression schemes -- frequency domain transform followed by quantization and lossless encoding schemes. They target tradeoffs by quantizating high frequency data to incre…
Quantization