Deep learning models for image compression often face practical limitations in hardware-constrained applications. Although these models achieve high-quality reconstructions, they are typically complex, heavyweight, and require substantial training data and computational resources. We propose a methodology to partially compress these networks by reducing the size of their encoders. Our approach uses a simplified knowledge distillation strategy to approximate the latent space of the original models with less data and shorter training, yielding lightweight encoders from heavyweight ones. We evaluate the resulting lightweight encoders across two different architectures on the image compression task. Experiments show that our method preserves reconstruction quality and statistical fidelity better than training lightweight encoders with the original loss, making it practical for resource-limited environments.

翻译：深度学习图像压缩模型在硬件受限应用中常面临实际限制。尽管这些模型能够实现高质量重建，但通常结构复杂、参数量大，且需要大量训练数据和计算资源。本文提出一种通过缩减编码器规模来部分压缩此类网络的方法。我们采用简化的知识蒸馏策略，以更少的数据和更短的训练时间逼近原始模型的潜在空间，从而从重型编码器中提取轻量级编码器。我们在图像压缩任务中对两种不同架构生成的轻量级编码器进行了评估。实验表明，与使用原始损失函数训练轻量级编码器相比，本方法能更好地保持重建质量和统计保真度，使其在资源受限环境中具有实用价值。