用可学习的STanH量化器实现单模型多速率图像压缩，节省存储和训练开销。
STanH : Parametric Quantization for Variable Rate Learned Image Compression
- 设计可微分的STanH量化层，通过参数化双曲正切求和替代传统阶梯量化
- 在固定训练模型上微调即可实现不同比特率，实测性能接近当前最优
- 适合需要多码率支持且资源受限的移动端图像压缩场景
在端到端学习的图像压缩中，编码器与解码器联合训练以最小化 $R + λD$ 损失函数，其中 $λ$ 控制量化隐表示的码率与图像质量之间的权衡。然而，每个 $λ$ 值都需要训练一个独立的编码器-解码器对，导致需在用户设备上部署并存储多个模型。本文提出一种基于可参数化双曲正切之和的可微分量化器——STanH，其可松弛阶梯式量化函数。STanH 作为可学习的激活层嵌入预训练的固定码率模型中，通过微调即可实现不同目标比特率。实验表明，该方法在保持与当前最优方案相当的压缩效率的同时，显著降低了部署复杂度、训练时间和存储成本。
原文摘要 · Abstract (English)
In end-to-end learned image compression, encoder and decoder are jointly trained to minimize a $R + λD$ cost function, where $λ$ controls the trade-off between rate of the quantized latent representation and image quality. Unfortunately, a distinct encoder-decoder pair with millions of parameters must be trained for each $λ$, hence the need to switch encoders and to store multiple encoders and decoders on the user device for every target rate. This paper proposes to exploit a differentiable quantizer designed around a parametric sum of hyperbolic tangents, called STanH , that relaxes the step-wise quantization function. STanH is implemented as a differentiable activation layer with learnable quantization parameters that can be plugged into a pre-trained fixed rate model and refined to achieve different target bitrates. Experimental results show that our method enables variable rate coding with comparable efficiency to the state-of-the-art, yet with significant savings in terms of ease of deployment, training time, and storage costs
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。