The latest advancements in neural image compression show great potential in surpassing the rate-distortion performance of conventional standard codecs. Nevertheless, there exists an indelible domain gap between the datasets utilized for training (i.e., natural images) and those utilized for inference (e.g., artistic images). Our proposal involves a low-rank adaptation approach aimed at addressing the rate-distortion drop observed in out-of-domain datasets. Specifically, we perform low-rank matrix decomposition to update certain adaptation parameters of the client's decoder. These updated parameters, along with image latents, are encoded into a bitstream and transmitted to the decoder in practical scenarios. Due to the low-rank constraint imposed on the adaptation parameters, the resulting bit rate overhead is small. Furthermore, the bit rate allocation of low-rank adaptation is \emph{non-trivial}, considering the diverse inputs require varying adaptation bitstreams. We thus introduce a dynamic gating network on top of the low-rank adaptation method, in order to decide which decoder layer should employ adaptation. The dynamic adaptation network is optimized end-to-end using rate-distortion loss. Our proposed method exhibits universality across diverse image datasets. Extensive results demonstrate that this paradigm significantly mitigates the domain gap, surpassing non-adaptive methods with an average BD-rate improvement of approximately $19\%$ across out-of-domain images. Furthermore, it outperforms the most advanced instance adaptive methods by roughly $5\%$ BD-rate. Ablation studies confirm our method's ability to universally enhance various image compression architectures.

翻译：神经图像压缩的最新进展在超越传统标准编解码器的率失真性能方面显示出巨大潜力。然而，用于训练的数据集（如自然图像）与用于推理的数据集（如艺术图像）之间存在难以消除的领域差距。我们提出了一种低秩自适应方法，旨在解决跨领域数据集中观察到的率失真下降问题。具体来说，我们对客户端解码器的部分自适应参数进行低秩矩阵分解以更新这些参数。在实际场景中，这些更新后的参数与图像潜变量一起被编码为比特流并传输给解码器。由于对自适应参数施加了低秩约束，由此产生的比特率开销很小。此外，考虑到不同输入需要不同的自适应比特流，低秩自适应的比特率分配并非平凡。因此，我们在低秩自适应方法之上引入了一个动态门控网络，以决定应使用自适应功能的解码器层。该动态自适应网络通过率失真损失进行端到端优化。我们提出的方法在不同图像数据集上展现出通用性。大量实验结果表明，该范式显著缓解了领域差距，在跨领域图像上平均BD率改进约19%，优于非自适应方法。此外，它在BD率上还比最先进的实例自适应方法高出约5%。消融研究证实了我们的方法能够通用地增强各种图像压缩架构。